557 papers with open-source code, published in 2026.
Octi Zhang, Mateo Guaman Castro, Patrick Yin et al.
General-purpose robots must perform a wide range of tasks from agile locomotion to dexterous manipulation.
Colin Rubow, Haohan Zhang
Powered neck exoskeletons are developed to restore head-neck motions for those with neck muscle weakness. Current methods using hand-held input devices to control these robotic systems are unintuitive or non-viable for these populations.
Santiago Fernandez, Angel da Silva, Hiago Sodre et al.
Aerial tracking of autonomous ground vehicles can provide useful situational awareness in environments where fixed external perception infrastructure is unavailable.
Hanjun Kim, Sixu Zhou, John Shim et al.
Existing biomimetic lower-limb prosthesis controllers are commonly designed for discrete locomotion modes, requiring separate parameterizations for level walking, ramps, and stairs.
Mozes Jacobs, Aiden Swann, Mathilde Papillon et al.
Robotic manipulation is inherently geometric, but what shape does the world take inside the policy that performs it?
Chen Cai, Steven Liu
Close-proximity multi-arm manipulation requires collision models that are both geometrically accurate and differentiable enough for real-time optimization.
Marco Giberna, Miguel Fernandez-Cortizas, Jose Luis Sanchez Lopez et al.
Models based on graphs have emerged in robotics as a powerful foundation for internal world representations, where factor and scene graphs are among the most prominent model types found in the related literature and in successful robotic solutions.
Dang Viet Anh Nguyen, Rajesh Piplani, Aldy Gunawan
We introduce the two-echelon covering tour vehicle routing problem (2E-CTVRP) for the distribution of relief supplies after a disaster. In the first echelon, a fleet of trucks transports supplies and drones from a central depot to satellites at the periphery of the affected area.
Jinwoo Hwang, Ilseung Park, Changseob Song et al.
Objective: Data-driven models that estimate physiological states, particularly biological joint moments, are widely used in exoskeleton control.
Jiangtao Liu, Zishang Xiang, Yage He et al.
World action models jointly learn visual predictionand robot actions, providing a way to use observations ofscene evolution for policy learning. Their video and actionlosses, however, provide no explicit target for the geometricconsequences of a demonstrated action sequence.
Ryo Terashima, Yuga Yano, Hakaru Tamukoh
In this study, we propose an adaptive question generation mechanism that addresses uncertainty arising from ambiguous instructions. Natural-language instructions for service robots often contain ambiguities.
I-Chia Chang, Jacob Stewart, Petros A. Ioannou et al.
Legged robot control is not yet practical in non-inertial environments, where the ground and surroundings accelerate in the inertial Earth frame, mainly because of the unknown, time-varying, persistent perturbations caused by environmental motion, compounded by the associated hybrid robotic dynamics.
Gokul Puthumanaillam, Tao Sun, Elie Aljalbout et al.
The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale.
Helena Merker, Nick Walker, Andreea Bobu
Reward learning typically assumes the human's input covers everything that matters for the task. In practice, humans can only attend to so much at once, so their teaching naturally captures some features---or aspects of the task---better than others.
Oleg Kushnarev, Alexander Belyaev
For ground robots operating in outdoor environments, understanding the properties of the underlying terrain is essential for ensuring reliable operation. In most perception-based studies, this problem is formulated as categorical classification with a fixed number of classes defined during training.
Florian Lercher, Karan Mahesh, Yujun Huang et al.
When robots are deployed in the real-world, they must interact with other agents and accomplish their own goals while adhering to legal constraints. These potentially conflicting objectives are often only partially prioritized, making scalarized objectives or fully specified hierarchies unsuitable.
Rajneesh Anand, Mayuresh V. Kothare
Self-driving laboratories (SDLs) are transforming chemical and materials discovery through closed-loop automation, yet automated infrastructure for physical manipulation of soft, deformable matter remains beyond current robotic platforms.
Tao Lin, Yikeng Chen, Qiwei Liang et al.
Layer pruning reduces the size and inference cost of vision-language-action (VLA) models, but selecting a deployable configuration requires deciding both which layers to remove and how to recover task performance.
Yu Otsuki, Teja Emmey, Sena Matsushita et al.
Autoware is an open-source autonomous driving software platform widely adopted by researchers and industry developers.
PhysicalRSI Team, Danjiao Ma, Enhui Ma et al.
Generating useful robot-training data requires more than visually plausiblescenes: objects must support interaction, placements must remain physicallyvalid, and tasks must admit repeatable execution.
Wenbo Yu, Jifan Li, Wenke Xia et al.
While asynchronous execution enables VLA models to operate in real-time environments by predicting the next chunk during execution, it inevitably introduces boundary misalignment with the committed action stream.
Seohong Park, Sergey Levine
Behavioral cloning (BC), despite its simplicity, exhibits many counterintuitive phenomena in the real world. For example, the performance of BC often keeps increasing as the model overfits more to the dataset, and fully closed-loop policies often completely fail without action chunking.
Peter M. Donley, Joseph L. Moore
Belief-space planners with separately designed or off-the-shelf estimators may have access to state-relevant information the estimator does not observe.
Haoran Chen, Jingtian Ji, Samuel Wheeler et al.
Autoregressive action-token policies such as vision-language-action models require action tokenizers to translate discrete token sequences into precise control actions in continuous space. Many action tokenizers learn the mapping between tokens and actions via a reconstruction objective.
Elizabeth Peiros, Moira Bohley, Lucas Yager et al.
The neck, specifically the cervical spine, is a highly fragile and mobile part of the body with a high risk of catastrophic injury.
Elliot Preston-Krebs, Abhishek Goudar, Timothy D. Barfoot
We present Informed Belief Localization Trees* (Informed BLT*), a sampling-based belief space planning (BSP) algorithm that scales to large outdoor digital twins with point-cloud observations. We adapt RRT* and Informed RRT* to belief space using the $2$-Wasserstein ($W_2$) metric.
Xue Qin, Simin Luan, Cong Yang et al.
Sim-to-real research pursues physics fidelity as a primary objective: simulators are judged by how closely they reproduce real-world contact dynamics.
Sudarshan Harithas, Chen Yu, Juan Borbon et al.
Whole-body tracking has become the interface through which operators drive humanoid robots, yet the references it consumes are recorded on level ground and carrying nothing, so the tracker is aware of neither the forces the robot must exchange with objects nor the terrain it must stand on.
Yu-Lin Tsai, Muxi Lyu, Roei Herzig et al.
Foundation models are expanding robot capabilities, enabling robots to handle more diverse objects, follow sophisticated instructions, and operate in complex environments. These advances bring us to a future in which robots become part of everyday household life.
Haoran Chen, Jingtian Ji, Samuel Wheeler et al.
Action tokenization converts continuous robot actions into discrete symbols that can be modeled autoregressively.
Yinlong Dai, Homanga Bharadhwaj, Dylan P. Losey
Prior research on learning from humans often requires real human demonstrations. But advances in video generation models offer a new paradigm: we can now prompt these generators to make synthetic videos of the task.
Aiden Swann, Mathilde Papillon, Mozes Jacobs et al.
Vision-language-action (VLA) models are a promising approach to general purpose robot manipulation.
Shutong Ding, Zhaoyang Liu, Yimiao Zhou et al.
Diffusion policies are increasingly used in robotic control and manipulation, vision-language-action models, and world-model-based agents. Their ability to represent multimodal action distributions offers rich opportunities for exploration in reinforcement learning (RL).
Ci Zhang, Enfu Nan, Arman Akbari et al.
Household robots must accommodate new user instructions while executing ongoing tasks. Existing agents often regenerate or extensively revise the remaining task sequence, introducing plan ambiguity, logical inconsistency, and redundant execution.
Kavin M. Govindarajan, Kaleb Ben Naveed, David Li et al.
This paper presents a comprehensive methodology, backed by simulation and experimental results, for an adaptive mission planning strategy that is mathematically grounded in the maximization of the information-driven quantity of clarity.
Moyang Li, Zihan Zhu, Wei Zhang et al.
Feedforward foundation models have recently shown remarkable 3D reconstruction capabilities. However, existing models exhibit large tracking drift in long-context streaming reconstruction due to error accumulation.
Xilun Zhang, Maggie Wang, Erik Bauer et al.
Vision-language-action (VLA) policies trained on large datasets are capable within their training domains, yet they still fail to generalize to the variety of situations a robot meets in real-world deployment.
Tianjiao Yu, Zhilin Ou, Yifan Shen et al.
Generative simulation can automate robot environment construction, but physically valid environments are not necessarily useful for training. The challenge is to identify environments that address a policy's failures and supervision that helps it overcome them.
Shaocheng Liu, Yuan Meng, Zhenshan Bing et al.
Learning a collective policy for state-based Cartesian manipulation across diverse robotic embodiments presents a fundamental challenge due to embodiment-dependent transition dynamics.
Cong-Thanh Vu, Yen-Chen Liu
Precision pesticide spraying is essential for optimizing application efficiency and ensuring uniform chemical distribution.
Pranav Kedia, Edwin Redhead, Heiko Hamann
Reliable obstacle perception is challenging for small autonomous surface vessels (ASVs): reflections and glare confound visible-light cameras, vessel motion shifts the apparent waterline, and darkness removes the dominant sensing modality altogether.
Zhewen He, Hao Huang, Geeta Chandra Raju Bethala et al.
Humanoid whole-body controllers can now track a diverse set of dynamic motions, but they are typically trained offline and then frozen, so teaching such a controller a new skill tends to erode the skills it already mastered.
Zhiwei Xue, Jia Yue Kam, Jinhang Qiu et al.
Diffusion models can represent complex, multimodal trajectory distributions, but extracting uncertainty from them typically requires costly Monte Carlo sampling. This limits their use in real-time control, where robots must rapidly assess risk and maintain safety margins.
Huang Huang, Sriram Yenamandra, Arjun Majumdar et al.
The diversity of robot embodiments and action spaces makes it challenging to build robot world models that generalize across different embodiments.
Lizhi Yang, Yiling Hou, Yao Tang et al.
Text-conditioned motion generators produce trackable whole-body motion, but they have no notion of scene-dependent safety: the same action may target an object or a person.
Zerui Kang, Yishen Lim, Zhouyou Gu et al.
An electromagnetic (EM) digital twin gives mobile robots wireless situational awareness but depends on material conductivities that change with the environment. Online calibration faces initialization sensitivity and measurement travel costs.
Alperen Kenan, Juan José García Cárdenas, Adriana Tapus et al.
Multi-robot systems that combine the complementary capabilities of specialised platforms are critical for complex missions in challenging, inaccessible environments.
Jusuk Lee, Sungha Kim, Yeonsoo Park et al.
While learning dexterous manipulation from a single human video offers a promising alternative to costly robot demonstrations, many recent methods predominantly imitate demonstrated motions.
Amber Xie, Jiawei Fu, Xiaofeng Guo et al.
Collecting high-quality demonstrations remains a central bottleneck for learning dexterous manipulation. Teleoperation records executable robot actions, but it requires a complete robot setup and places the burden of coordinating many finger joints on the operator.
Botao He, Yiming Dou, Yiannis Aloimonos et al.
How can robots autonomously collect the contact-rich experience needed to learn dexterous manipulation?
Pranav Wagh, Yu Fang, Yue Yang et al.
Long-horizon robotic manipulation is often built by chaining independently trained skills.
Jitian Liu, Subhrajit Bhattacharya
We consider hole closure in a planar multi-agent system whose sensing disks form a time-varying \v{C}ech complex. We propose a harmonic-covariance feedback that uses harmonic edge signals to locate holes and converts those signals into agent forces.
Chenchao Sheng, Zhuang Jiang, Liuhaichen Yang et al.
Before deploying runtime recovery for a frozen vision-language-action (VLA) policy, one must establish that an intervention improves success beyond ordinary run-to-run variation and that its complexity adds value over a simple action.
Zekui Xue
Dynamic-point filters are routinely added to feature-based visual SLAM, and several recent systems argue that removing dynamic features can leave too few static features in low-texture regions. So far, these systems have been evaluated only on texture-rich benchmark sequences.
David Nguyen, Marcelo Coelho, Sangbae Kim
Robot performance is often limited by the cost of iterating on morphology and control together, since every computer-aided design (CAD) change has to be carried into a simulation-ready model before control work begins.
Junyan Li, Ruizhi Li, Yu Liu et al.
We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction.
Youngjun Jun, Kyumin Choi, Youngmin Kim et al.
Vision-Language-Action (VLA) models increasingly rely on action experts that generate short action chunks under receding-horizon control.
Wei Wang (Robostreet research team Cambridge, MA, USA) et al.
Three dimensional modeling for autonomous driving must continuously estimate road geometry, obstacle occupancy, traffic participant behavior, and observational uncertainty under limited computational resources.
Kapalik Khanal, Biswash Khatiwada, Stephen Afrifa et al.
Changing a humanoid robot's manipulation policy should not require retraining the controller that maintains the robot's balance.
Hanchu Zhou, Dechen Gao, Hang Wang et al.
Vision-language models (VLMs) and vision-language-action models (VLAs) have recently driven rapid progress in general-purpose robots, yet most progress has focused on single-robot settings.
Jiajian Zheng, Bin Zhang, Wen Fan et al.
Multi-finger hands contact objects at different times, so a global close command can overload early-contact fingers while others are still moving. Dense tactile arrays address this problem but add hardware, calibration, bandwidth, and computation.
James Lott, Vahraz Honary
Multi-robot task allocators in dynamic missions commonly admit newly released tasks immediately, potentially invoking allocation for each new arrival.
Kairui Hu, Siyuan Hu, Fangzhou Hong et al.
Most robot policies keep a model in the control loop: a VLA maps observations to actions, and an Agent Harness, such as Agent-as-Policy or Harness VLA queries a VLM for decision making at run time.
Devin Han, Hershraj Niranjani
Flow-based policies such as $\pi_0$ are trained on a fixed set of embodiments, and transferring them to new ones is an open problem.
ZhiYuan Feng, Zhuoshi Pan, Zhaolu Kang et al.
Embodied agents built on foundation models rely on an execution harness to organize observations, guide actions, and incorporate execution feedback into subsequent decisions.
Sitan Huang, Grace Gao
Surface navigation on the Moon is subject to extreme illumination contrast and deployment-time perceptual disturbances.
Zhi Cao, Yining Hong, Jiaolong Yang et al.
Human demonstrations offer a scalable alternative to costly robot data collection for dexterous manipulation, but most human datasets lack force measurements.
Songyuan Zhang, Baljeet Singh, Sarthak Ranjeet Kaingade et al.
Safe reinforcement learning commonly places safety and task performance in the same policy objective, where they can introduce competing updates.
Zhengming Zhu, Yang Liu, Xiao Gao et al.
Robot throwing has emerged as a promising technique for improving efficiency in logistics and warehouse automation, by enlarging the workspace and speeding up the process. To significantly increase the throwing system's throughput, we develop strategies for throwing multiple objects in one swipe.
Dmytro Babarytskyi
A mesh of interceptors defending a fixed site must spread over the predicted arrival point of an approaching object.
Sebastian Sanokowski, Alireza Sarmadi, Majid Khadiv
Several state-of-the-art methods for online reinforcement learning in continuous control improve policies using action gradients of a learned critic.
Pavel Bushuyeu, Yujin Chen, Anton Nikolaev et al.
Existing benchmarks evaluate tabletop manipulation, flat-floor household activity, or humanoid locomotion and manipulation as separate task groups; none scores vertical mobility and dexterous work on a fragile payload in one long-horizon episode.
Pranit Mohnot, Christian Helten, Daniele Gammelli et al.
Safe whole-body motion is essential for deploying humanoid robots in unstructured environments.
Mohammadmehdi Ataei, Mohammad Amin Nabian, Jie Xu et al.
Compared with analytical physics, learned dynamics models promise robot simulation that is faster, inherently differentiable, and easily adaptable to real data.
Sicong Leng, Yunze Man, Zhiqi Li et al.
Flora bundles three open models, for segmentation, captioning and reward, so one data engine can produce timestamped captions, process rewards and outcome rewards for robot datasets.
Jaewoo Lee, Jeongyeon Seo, Sihyun Cho et al.
Embodied coding agents construct robot policies from natural-language instructions by generating executable programs and refining them from execution feedback.
Xiao Tan, Yixuan Wang, Zhexi Wang et al.
FORCA lets a coding agent use wrist force/torque readings both while its robot program runs and when it revises that program between real-robot attempts, without demonstrations or task-specific training.
Jin Rhee, Yuhao Zhang, Frank Dellaert et al.
Feed-forward geometric foundation models (GFMs) directly predict dense geometry and camera poses from batches of images. Emerging visual SLAM methods chain together consecutive GFM batches to form dense point cloud maps.
Tuo Feng, Yue Zhang, Shiji Zhou et al.
Embodied Artificial Intelligence (AI) introduces cyber-physical risks because digital failures and attacks can cause physical harm.
Ruitong Tian, Fang Xu, Noah B. Wilson et al.
Unlike conventional teleoperation, wearable interfaces allow operators to collect dexterous demonstrations through their own hand motions while directly interacting with task objects.
Luis Pabon, Johannes K\"{o}hler, Revant Kasichainula et al.
Reduced-order models (ROMs) make model predictive control (MPC) of high-dimensional nonlinear systems tractable, but the resulting modeling error can lead to constraint violations on the real system.
Khizra Sohail, Miren Illarramendi, Aitor Arrieta
**Context:** Deep Neural Networks (DNNs) increasingly control Cyber-Physical Systems (CPSs), yet small input perturbations can cause unsafe system-level behavior.
Dechen Gao, Yue Yang, Ben Abbatematteo et al.
Human demonstrations are a scalable data source for learning dexterous manipulation, but the embodiment gap prevents human motion from being executed directly on robots. Inverse kinematics (IK) retargets human motion to robots efficiently but ignores dynamics, often producing infeasible motions.
Phone Thiha Kyaw, Ben Wei, Sepehr Samavi et al.
Planning motions that respect the intrinsic geometry of a robot's configuration space, including its curvature and a configuration-dependent notion of cost, yields shorter, lower-energy, and more natural trajectories than planning under the ambient flat metric.
Prajwal Vijay
We study assignment quality in 3D heterogeneous multi-agent reach-avoid games and identify a recurring failure mode of cardinality-only matching in geometrically structured scenarios, which we term \emph{Geometric Sprawl}.
Hongchang Liu, Jian Liu, Yujuan Ding et al.
Recent 3D world models increasingly use features from geometry foundation models (GFMs) as predictive world states, benefiting from their rich geometric priors.
Bosong Ding, Xianglin Zhang, Miao Xin et al.
Co-speech gestures for robots must adapt not only to speech and embodiment, but also to the workspace available for performing the motion. Since the same speech can be accompanied by different gestures, a robot can respond to workspace constraints, e.g., gestures for speech next to a wall.
Hanwen Guo, Zhengzhi Lin, Yusen Xie et al.
Transparent and specular surfaces pose a serious challenge to LiDAR-based SLAM and navigation because laser returns may pass through glass, leaving collision boundaries absent from the map.
Qi Zhang, Xikun Liu, Qijun Qin et al.
Globally consistent, real-time state estimation in large-scale, perceptually degraded environments is essential for autonomous vehicles and aerial robots, and requires fusing LiDAR, inertial, and GNSS measurements.
Yulin Liu, Lai Wei, Yen-Jen Wang et al.
Foundation models and large-scale human data provide rich sources of manipulation intent, but translating this intent into multi-fingered robot behavior remains difficult. Dexterous hands still lack a reusable low-level primitive that reliably establishes contact across tasks and embodiments.
Antony Thomas, Fulvio Mastrogiovanni, Marco Baglietto
Humanoid and service robots operating in clut- tered human environments may encounter motion planning problems that are infeasible when all surrounding objects are treated as fixed obstacles.
Navid Zarrabi, Nariman Yousefi, Sajad Saeedi
Environmental robotic sampling requires considering the dual influence of water currents on robotic motion and particle transport. Existing marine robotics simulators generally model flow, autonomy, and sampling targets separately, limiting joint evaluation of mission cost and sampling performance.
SenseNova, Joint Research Team, : et al.
GPT-6-Astra demonstrates a level of competence in robotic manipulation and navigation that challenges the conventional paradigm of building specialized models for individual tasks and embodiments.
Derek You, Zafir Shamsi, Keqin Wang et al.
Actuator degradation turns quadruped locomotion into a coordination problem requiring joints to compensate for lost actuation. Prior work suggests that morphology-aware graph policies improve learning and generalization under body perturbations.
Xihan Ma, Bo Zhang, Boxiong Li et al.
HoloBoxing presents a simple recipe for learning humanoid boxing by building on a pretrained whole-body controller. The recipe separates reusable motor skills from task decisions: a compact planner requests future body-point targets, while the frozen controller handles joint-level execution.
An Dang, Arturo Flores Alvarez, Yu-Ming Chen et al.
Humanoid loco-manipulation of large, heavy objects demands forceful interaction across the entire body. However, such payloads shift a humanoid's center of mass and impose sustained loads across the upper body, challenging balance and command tracking.
Yangzhi Yang, Xiansheng Lin, Zhaoming Xie et al.
Humanoid robots could transport payloads substantially heavier than themselves by pulling passive wheeled vehicles instead of carrying the load.
Kyochul Jang, Seohyeon Park, Ohchul Kwon et al.
As robotic hardware and learning methods advance, humanoids need tools to perform tasks beyond their inherent physical limits. Successful tool use requires selecting a suitable tool and coordinating manipulation and, when needed, locomotion to complete the task.
Jingtai Yang, Yining Wu, Yanjun Li et al.
Recent advances in motion generation and whole-body tracking have enabled humanoid robots to execute increasingly diverse motions, yet the same motion capabilities may be requested repeatedly during continual deployment.
Vincenzo Guarino, Emanuele Musumeci, Vincenzo Suriani et al.
Agentic AI based on Large Language Model generalization capabilities offers a wide range of potential applications, including planning for embodied tasks. For example, embodied agents based on Foundation models can generate plausible plans in autonomous robotics scenarios.
Thomas Landeg, Thierry Tambe
Vision-Language-Action (VLA) models perform well on robotic manipulation, yet remain brittle once their own actions carry them into states their training data barely covers.
Sagarika Rao Valluri, Benjamin Riviere
Harsh and rapidly varying orbital illumination introduces failure modes during spacecraft inspection. Existing planners rely on line-of-sight inspection metrics which perform occlusion checks against a known target and conflate geometric visibility with task-relevant information.
George Dimas, Panagiotis G. Kalozoumis, Panagiotis Vartholomeos et al.
Recently, soft robotic procedures are being developed aiming at achieving targeted minimally invasive operations or drug administration in specific locations in the human body.
Haichuan Li
Efficient indoor LiDAR perception is challenging because mobile robots must understand cluttered three-dimensional environments under strict latency and memory constraints.
Sangwoo Shin, Ashvin Anilkumar, Ryan Gao et al.
Sampling-based system identification estimates physically meaningful parameters by tuning a simulator to reproduce the target system dynamics, providing an interpretable approach to improving sim-to-real transfer.
Zhuo Lin, Sirui Xu, Liuyu Bian et al.
We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills, improving from its own attempts, and retaining what it learns, without retraining.
Junyi Hu, Zhewen He, Zhenhua Li et al.
A robot demonstration records two things in the same frames: what happened to the objects, and how one particular arm made it happen. We condition on the first.
Shuangyu Xie, Kaiyuan Chen, Muhammad Zubair Irshad et al.
KiRoSe segments robot demonstrations from compact kinematic tokens instead of raw multi-camera video, which the authors note is costly for multimodal models and quickly exhausts context windows.
Yuming Fu, Weijia Wu, Jing Chen et al.
Self-driving laboratories (SDLs) aim to automate the full experimental loop, from scientific decision-making to physical execution.
Han Fang, Yunpeng Jiang, Jianshu Hu et al.
Privileged 3D supervision uses additional geometric information during training to guide RGB-based visuomotor policy learning, without requiring geometric inputs at deployment. However, low reconstruction error does not ensure that visual representations capture geometry useful for control.
Shichao Zhai, Shuhao Ye, Rong Xiong et al.
Object-goal navigation (ObjectNav) in multi-floor scenarios presents a challenge due to sparse rewards caused by long-horizon decision-making.
Qinglian Wu, Yidian Hu, Weiqi Fan et al.
Long-range throwing on unstructured terrain is a key capability for mobile robots in delivery and retrieval tasks, but it requires high release velocity, coordinated whole-body motion, and robustness to terrain-induced disturbances.
Shashank Hegde, Alexander Popov, Elie Aljalbout et al.
World action models (WAMs) predict actions and future observations, typically from a reconstruction-based representation that carries noisy, redundant information which can complicate downstream predictions.
Zhixu Li, Keqian Tang, Litian Gong et al.
Personalization is essential for general-purpose robots to transition into household environments and achieve true practicality.
Lipeng Zhuang, Yingdong Ru, Shiyu Fan et al.
Generative motion planners typically use learned trajectory priors for initial generation, while leaving test-time repair to local continuous refinement. We introduce Masked Generative Motion Planning (MGMP), which extends the learned prior from efficient parallel generation to structural repair.
Yun Zhang, Zhiyu Huang, Tianhui Cai et al.
Long-horizon robotic manipulation fundamentally requires memory: agents must retain task-relevant information from past observations and interactions and use it to guide future actions.
Ke Zhang, Danica J. Sutherland, Chao Liu
Training data variation, whether through designing a domain randomization (DR) scheme in simulation or curating demonstrations for imitation learning, is a primary lever for improving the robustness of robotic manipulation policies.
Aaron Wilhelm, Marina de Albuquerque Marcon, Emith Uyanwatte et al.
We demonstrate high-precision global localization using natural ground texture viewed through microscope optics, achieving localization in the tens-of-micrometers regime.
Shuaijun Liu, Chenglong Zhang, Xuhao Liu et al.
Human videos provide rich motion targets for humanoid learning, yet visually plausible references can still produce persistent failures under physics-based execution. These failures reveal where training supervision should change.
Mohamed Abouagour, Junhyun Nam, Wonse Jo et al.
Robots following persistent language instructions must decide which cached room judgments remain valid as their environment changes.
Zewen He, Taiki Ishigaki, Ko Yamamoto
Physical flexibility plays a significant role not only in human motions but also in robot motions.
Wensen Liu, Jerry Peng, Shravani Vedagiri et al.
Model-based control of an aquatic robotic platform depends on a hydrodynamic model that is costly to identify and specific to the hull, payload, and conditions it was measured in.
Zirun Ma, Jindou Jia, Tuo An et al.
In robotic manipulation, the same observation often admits multiple feasible actions. Generative policies such as diffusion and flow matching naturally capture such multimodal behaviors, yet which mode is executed is left to random sampling and cannot be actively controlled.
Wei Wang (Robostreet research team. Cambridge, MA, USA) et al.
Refuse collection in pedestrian campuses, parks and mixed-use districts remains manual because compaction trucks cannot reach bins located on walkways, courtyards and building service doors.
Aiden Swann, Mozes Jacobs, Mathilde Papillon et al.
Can better feature discovery improve control over robot behavior through internal interventions and training data? Recent work in vision and language models reveals multidimensional features, motivating block-sparse featurizers (BSFs), which represent each feature in a low-dimensional subspace.
Marcel Moll, Timo Oksanen
Guiding a tractor along a predefined reference path is a key component of precision agriculture. This study develops a path tracking controller based on Nonlinear Model Predictive Control, which incorporates multiple segments of a piecewise-linear reference path directly into the objective function.
Gengze Zhou, Yicong Hong, Jiazhao Zhang et al.
Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, raising the ceiling on what an embodied agent can understand and decide.
Ben Potter, Eslam Mounier, Aboelmagd Noureldin et al.
Reliable absolute heading estimation is critical for road-vehicle navigation, particularly when magnetic, inertial, or GNSS-based references are degraded.
Juntao Ren, Yifan Hou, Shuran Song
Robot demonstrations may contain useful behavior even when individual episodes are inefficient or unsuccessful.
Pranay Dugar, Mohitvishnu S. Gadde, Rajesh Mangannavar et al.
Recent progress in learned whole-body controllers for humanoid robots has enabled robust free-space motion by tracking kinematic targets such as joint or end-effector trajectories.
Ting Mao, Yanming Shao, Ziheng Wang et al.
Monocular videos of human manipulation provide abundant dexterous demonstrations, yet reconstructing hand-object interaction from a single view and transferring it to robot hands remain difficult, limiting their direct use for robot execution.
Marwah Basuhai, Tingcong Liu, Ibrahim Alsarraj et al.
Soft continuum robots can exploit distributed compliance for whole-body manipulation, but synthesizing behavior through changing contacts remains difficult. We address whole-body grasping and pick-and-throw from an initially ungrasped state through outcome-based actuation-space optimization.
Chang Liu, Sibo Tian, Litian Gong et al.
Robotic disassembly of end-of-life (EoL) products requires robots to accommodate product variation, follow prerequisite sequences, and approach components precisely for contact-rich manipulation.
Xiaomeng Xu, Han Zhang, Zhian Ruan et al.
Humanoid robots have many degrees of freedom and contact surfaces, yet most loco-manipulation research restricts manipulation to the hands and avoids other body contacts with the environment.
Zirui Wu, Chen Guo, Tianjian Jiang et al.
We introduce P$^{3}$-WAM, a unified world action model for egocentric dexterous manipulation that learns 3D perception, action-conditioned prediction, and goal-directed planning through three complementary modes: Perceive, which reconstructs articulated hand motion and camera trajectories from video; Predict, which generates visual futures under prescribed actions; and Plan, which jointly generates action trajectories and their anticipated visual consequences conditioned on an initial image, a language instruction, and an optional visual goal.
Minjoong Kim
Damage-recovery algorithms often rank gaits from short trials, yet a gait that performs well briefly may not remain effective during continued execution. In reset-free recovery, each trial also changes the physical state inherited by the next.
Wenqing Tian, Zeyu Zhang, Zhaocheng Liu et al.
Astra can act, yet reliable manipulation depends on the system through which it observes and controls the world. We introduce PhysEvo, a framework for physical recursive self-improvement (RSI) around a single frozen model.
Elizabeth Peiros, Derek Chen, Lucas Yager et al.
Improvements in human-robot physical interaction (pHRI) can have major implications for physical therapy, search and rescue, and telemedicine. However, a major challenge concerns human constraints and safety in human-robot physical experiments.
Maria Attarian, Yifan Ruan, Claas Voelcker et al.
While Vision-Language-Action models have enabled impressive cross-task transfer in zero-shot settings, \emph{adaptation} methods are often necessary to achieve consistent performance on novel tasks.
Ruiqi Wang, Dezhong Zhao, Xuesu Xiao et al.
PrefO2O aims to remove the per-task cost of preference-based RL by reusing human preferences from related source tasks, so a new target task needs no human preference labels.
Shizuo Tian, Haodong Luo, Yutong Li et al.
Rapid adaptation to a new environment requires a robot to acquire useful knowledge about local objects, states, and interactions from limited experience.
Michele Persiani, Thomas Hellstr\"om
Legible planning is the creation of plans that best disambiguate their goals from a set of other candidates from an observer's perspective.
Teodor Ilie, Kleber Cabral, Sidney Givigi
Vehicles that lose control at the handling limit through icing, hydroplaning, or an abrupt evasive maneuver fall outside the operating envelope of production safety systems such as electronic stability control, which focus on preventing instability rather than recovering from it.
Seunghun Lee, Kyuhwan Shim, Yeogyeong Song et al.
Existing vision-language-action (VLA) models benefit from large-scale vision-language pretraining, but tend to memorize training trajectories, limiting their ability to adapt learned interactions to new task and scene configurations.
Fangju Yang, Siyi Ma, Tonghao Guan et al.
Real-time motion generation for tendon-driven continuum robots requires accurate modeling of nonuniform bending and whole-body collision avoidance. This paper presents a unified actuation-space framework for planar multi-segment tendon-driven continuum robots.
Yen-Jen Wang, Haozhe Jiang, Shuying Deng et al.
Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perception with control.
Yu Zhang, Jiazhuo Li, Yancong Wei et al.
Robots can acquire bad habits from a few defective moments in otherwise useful teleoperation. In mixed-quality robot data, normal and problematic demonstrations share most task behavior and differ only at a local action continuation.
Ryan Gao, Ashvin Anilkumar, Nicholas Corrado et al.
A longstanding goal for robot reinforcement learning (RL) is that robots learn from their own physical experience, as humans and animals do.
Chunyu Jiang, Yichen Cai, Shuai Li et al.
Contact-rich manipulation requires a robot to be precise in free space to establish the intended contacts, and compliant once in contact to avoid excessive forces.
Shukai Gong, Xuanran Zhai, Yintianrun Zhang et al.
Long-horizon compositional manipulation has become increasingly important for real-world robot deployment, where a single task involves multiple coordinated subtasks.
Jiaming Wang, Zhiwei Xue, Chen Jizhuo et al.
Long-term object search requires learning where objects usually appear from repeated but uneven observations of a changing environment.
Prajit Krisshnakumar, Fan Yang, Koichiro Niinuma
Micro aerial vehicles (MAVs) enable rapid indoor 3D reconstruction for inspection and time-critical situational awareness, but must operate under strict flight-time budgets and safety constraints that require explicit return-to-home (RTH) feasibility with a conservative margin.
Ryan Li, Yigit Korkmaz, Erdem B{\i}y{\i}k
Recent advances in robot learning have enabled generalist control policies capable of completing a wide range of tasks. However, their performance degrades when deployed in unseen environments, making it critical to detect failures and teach recovery behaviors.
Minhyeong Kang, Sanghyun Kim
This paper presents a motion planning framework that unifies equality and inequality constraints within a single geometric formulation for sampling-based planning in high-dimensional robotic systems.
Bince Qu, Wei Chen, Bo Zhang
The rise of large language models (LLMs) has opened a path toward generalist embodied AI, raising the question of how LLMs can act in the physical world.
Zimo Wen, Yijin Chen, Yuxuan Cao et al.
A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns during execution into capabilities that later tasks can reuse.
Matteo Dalle Vedove, Fares J. Abu-Dakka, Luigi Palopoli et al.
All the objects composing our world are enclosed within surfaces. Yet, most robot learning and motion generation frameworks treat surfaces as constraints ignoring their intrinsic geometry.
Chaoyu Zhang, Guangshen Ma, Mark Draelos
In medical robotics, data-driven soft-tissue shape control requires deforming tissue toward desired morphologies through sequential physical interactions.
Madison Book, Justin Bradley
Safe multi-agent coordination typically assumes what real-world, deployed, resource-constrained robots cannot provide: continuous, perfect state sharing. Robust control strategies must be complemented with robust communication strategies to deliver resilient deployments.
Xi Chen, Fengqi Hu, Zeyu Shen et al.
Robust reinforcement learning (RL) is critical for reliable real-world deployment, where policies may fail under diverse shifts and disruptions.
Ruoxuan Feng, Yutong Chen, Ruihua Song et al.
Humans inherently understand the physical world through an active process. When sensory evidence is insufficient to infer physical properties, we naturally interact with the environment by deciding what information is missing, how to acquire it, and when sufficient evidence has been obtained.
Jan Steckel, Vincent Katter, Wouter Jansen
Echolocating bats navigate dense forests using sonar alone, and in-air 3D imaging sonars now capture the entire frontal hemisphere with every pulse.
Minghao Zhu, Bohan Hou, Kun Xiang et al.
We introduce RynnUnify, a 16B unified embodied model that combines strong embodied understanding with long-horizon visual planning through interleaved video--language reasoning.
Elena Wittemyer, Graco Gao
Propulsive drones are a promising new technology for generating high-resolution terrain models of the Moon. In future lunar missions, propulsive drones will complete a series of hops across the lunar surface while capturing images with downward-facing cameras.
Zerun Wang, Vivek Kamat, Shekhar Bhansali
Manipulating fragile objects remains challenging as robots must understand the state of what they grasp, such as slip or fracture, to respond appropriately, especially when material properties are unknown.
Mahed Dadgostar, Guillem Aleny\`a, J\'ulia Borr\`as
Although cloth is known to exhibit different outcomes under repeated fast dynamic motions, even when the same trajectory is applied, this variability has not yet been systematically characterized.
Runhan Huang, Xiangcheng Zhang, Haoyu Chen et al.
Robot learning has advanced by scaling demonstration datasets and model capacity; however, deploying a new robot embodiment or task typically necessitates a dedicated teleoperation corpus.
Yuhan Liu, Lianhui Qin, Shenji Wan
Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. Language-guided methods support semantic planning and object-level reasoning, but precise spatial grounding remains difficult.
Jiawei Chen, Yinxi Wang, Zihan Yang et al.
RepresentNav lets the navigation objective build the visual representation the policy acts on from three frozen vision foundation models, instead of accepting whatever their final layers expose.
Jinshi Zhao, Libaihe Tian, Alex Ranne et al.
Long, slender instruments are essential for minimally invasive surgery (MIS), but achieving precise distal manipulation becomes increasingly difficult when actuation extends along the entire instrument.
Shaekh Mohammad Shithil, Lantao Liu
SEVI targets unsafe interactions during online reinforcement learning on physical robots by deciding when a proposed action should be replaced with a recovery behavior.
Al Bashir, Partho Ghose, Yibin Wang et al.
Robotic harvesting requires precise manipulation to ensure accurate positioning of the end-effector, especially in a constraint workspace.
Juyi Sheng, Hua Wang, Mengyuan Liu
World action models (WAMs) combine robot action generation with future state prediction. Existing WAMs typically predict videos or learned visual latents, which represent interaction geometry only implicitly and may retain appearance information unrelated to control.
Wenhao Wang, Yanyan Li, Jiawei Yuan
Small language models (SLMs) have been increasingly adopted for onboard robot operation because they enable intelligent decision-making. However, existing approaches are mainly distillation-oriented and rely on enumerating representative task-solution pairs.
Sofya Konstantinova, Miguel Altamirano Cabrera, Artem Lykov et al.
Vision-language-action (VLA) policies enable diverse robotic manipulation but can fail during execution without recognizing their own errors. Human observers provide complementary signals, as unexpected robot behavior can trigger rapid vocal, facial, or verbal reactions before failure is completed.
Jingyun Yang, Baiyu Shi, Timothy Yu et al.
A growing body of work suggests that tactile sensing gives robot policies contact information that complements vision in dexterous manipulation. However, visuo-tactile robot data remains scarce: dexterous demonstrations require teleoperating robots, which limits dataset scale.
Tianxing Chen, Wenwei Lin, Chuqiao Lyu et al.
Generalist robot policies benefit from large-scale visual pretraining but often struggle with contact-rich dexterous manipulation, where force, compliance, and incipient slip are hard to observe from images.
Myeongju Cha, Pilwon Hur
This paper presents sparse calibration-based personalization for kernel-based gait phase and walking speed co-estimation from wearable inertial measurement units (IMUs). A 28-speed reference library was constructed from bilateral thigh and shank trajectories in a 20-subject locomotion dataset.
Jiayu Wang, Yue Yu, Bin Zhu et al.
Frontier multimodal foundation models (e.g., GPT-6 Astra) have recently shown strong potential for direct robotic control, yet their performance on fine manipulation remains limited.
Hiago Sodre, Sebastian Barcelona, Vincent Sandin et al.
Integrating Vision-Language Models (VLMs) into autonomous UAV navigation enables high-level semantic reasoning but introduces critical temporal bottlenecks that can destabilize flight control.
Rhythm Syed, Jean Mercat, Sedrick Keh et al.
Vision-language-action models (VLAs) inherit strong semantic grounding from pretrained vision-language backbones but are typically optimized for predicting actions rather than future observations. They can see and act, but they do not imagine the future before acting.
Liao, Qiayuan, Shao, Yiyang, Long, Junfeng et al.
Tracking large human-motion datasets has become the dominant route to general, expressive humanoid whole-body control, but scaling across many motions is expensive.
Mousumi Das, Aditeya Prajapati, Abrar Anwar et al.
Robot manipulation systems using Vision-Language-Action (VLA) model backbones typically use just one VLA for task execution. However, individual VLAs do not perform well across different task states and environments.
Yuto Tanaka, Kyo Kutsuzawa, Martina Doku et al.
Imitation learning enables robots to acquire complex skills directly from massive demonstration datasets, but its performance degrades severely when datasets are contaminated with suboptimal or noisy demonstrations.
Chenyuan Zhou, Yining Hong, Huang Huang et al.
Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither directly observable nor explicitly specified, from physical properties such as friction and mass to human-defined environmental rules.
Sungsan Park, Young-Sik Shin, Sanghyun Kim
Quadruped robots entering hospitals, care homes, and quiet offices must be context-appropriate not only in where they move but in how loudly they move: a legged robot's locomotion noise, dominated by foot-ground impacts, is itself a social variable.
Ruiyi Hu, Yongqiang Zhao, Daniel Bak et al.
Hair stroking is common in daily grooming and personal care, and is also widely used in hair-product evaluation, motivating robots with similar physical interaction capabilities.
Guangxin Zhao, Yiran Hu, Yuan Cao et al.
Existing LLM-driven robot task planners rely on a taken-for-granted assumption of an ideal user whose instructions are clear, complete, and task-focused.
Joochan Kim, Chanuk Yang, Tackgeun You et al.
We present Go2-DrivoR, a goal-conditioned adaptation of the end-to-end autonomous driving trajectory planning framework DrivoR for urban navigation with quadrupedal robots.
Huaze Liu, Zhenyu Wu, Jaehwi Jang et al.
Navigation in vision-denied environments is challenging for humanoid robots because proprioceptive odometry drifts and localization uncertainty accumulates rapidly.
Lemon Foxmere, Anthony Furman, Yizheng Du et al.
Reinforcement Learning (RL) has enabled legged robots to perform a range of skills in single-task settings. However, applications such as farm robotics or space exploration require diverse skills such as locomotion, digging, or close-range surveying.
Zhendai Huang, Aleksi Vilkki, Jianan Huang et al.
Robotic haircutting requires controlled tool motion near the head while simultaneously accounting for communication, visual feedback, tool actuation, and interruption handling.
Long Zhao, Xingjue Liao, Feifei Qian
Locomotion on granular slopes such as sand dunes remains a fundamental challenge for legged robots due to reduced shear strength and gravity-induced anisotropic yielding of granular media.
Yitao Zhang, Hong Ying, Haoran Guo et al.
Robotic simulation and virtual reality increasingly require object assets that capture not only visual geometry but also the physical cues underlying tactile and thermal interaction.
Ignacio G Lopez-Francos, Alexis Gallagher, Samira Shalal
Deep-space crews cannot rely on real-time ground support for urgent off-nominal events. Initial alerts may underdetermine cause, while discriminating evidence may reside in crew observations or at locations that are unsafe, costly, or unavailable for crew inspection.
Demetrious T. Kutzke, Junaed Sattar
Scuba divers are taught to control their depth to avoid rapid ascents and descents, which could result in serious injuries such as gas embolisms and barotrauma.
Michael Y. Fatemi, Jinhao Liang, Ferdinando Fioretto
Path finding and multi-robot motion planning require trajectories that are smooth, goal-directed, and collision-free in environments with complex geometric constraints.
Fan Pu, Keshu Wu, Jiwan Jiang et al.
Real-world Vision-Language Navigation (VLN) requires agents to act under partial observability, where map structure, semantic cues, and target locations may be incomplete or incorrectly inferred by foundation models.
Silong Yong, Anji Liu, Cunxi Dai et al.
A common way for trajectory planning is to leverage generative models trained on large collections of expert trajectories. At inference time, the model generates executable trajectories by conditioning on task goal constraints.
Jiayi Chen, Wenxuan Song, Jingbo Wang et al.
Vision-language-action models benefit from the understanding and reasoning capabilities of pretrained vision-language models, but action-only supervision provides limited grounding in world dynamics.
Wenye Yu, Yijin Chen, Kaiyi Xiong et al.
Real-world post-training of generalist robot policies faces two challenges: partial observability makes action selection ambiguous, while offline post-training methods delay feedback from deployment experience.
Boyao Han, Chen Shi, Jingjing Qian et al.
Vision-Language-Action (VLA) models have emerged as powerful foundations for robotic manipulation, but their reliance on fixed camera configurations during training makes them brittle to changes in camera count or pose during deployment.
Mert Albaba, Jens Beißwenger, Anna Manasyan et al.
Teaching a humanoid to follow instructions with its whole body runs into two obstacles. Its action space is large and tightly coupled: legs, arms, and fingers must move together while the robot keeps its balance, which makes joint-level actions hard to learn.
Zimo He, Tianyi Bian, Zizhong Yang et al.
Learning humanoid control from monocular human videos offers a scalable way to acquire diverse whole-body behaviors.
Suyu Ye, Zheyuan Zhang, Vaishnav Tadiparthi et al.
Robots operating in the physical world will increasingly need to coordinate with other robots, particularly in manipulation tasks where an object may be too large or heavy for a single robot to carry alone.
Junxiang Wang, Yuchen Liu, Yi Wu et al.
Memory allows large language model (LLM) agents to use past experience, often stored as textual records, when responding to requests.
Jasper Gerigk, Kenzo Aspuru-Takata, Chin-Hsuan Wu et al.
Shortcut learning is a prevalent issue in robot learning. The limited diversity of robot demonstration datasets can mislead policies into exploiting spurious correlations between tasks and irrelevant features, such as viewpoint or background.
Victoria Smelova, Daniil Kazachkov, Georgiy Kazantsev et al.
Long-horizon, multi-stage Vision-Language-Action (VLA) policies often require visual information that is no longer present in the current observation. Retaining the complete observation history is computationally expensive and highly redundant, motivating selective visual memory.
Hu, Songbo, Liao, Qiayuan, Chi, Yufeng et al.
Humanoid robots still struggle to plan contact-rich whole-body manipulation from egocentric RGB and proprioception. Workhorse learns such manipulation from robot-free human demonstrations. A visual planner predicts five-link targets: the poses of the torso, both wrists, and both feet.
Jie He, Wei Li, Junwen Tong et al.
Flow-based Vision-Language-Action (VLA) policies generate action chunks by transporting samples from a task-agnostic isotropic Gaussian source.
Jiuyi Xu, Xiao Hu, Meida Chen et al.
Robot world models support policy evaluation, planning, and synthetic data generation, but these applications require predictions that distinguish successful actions from failures.
Tianling Xu, Weijie Wan, Honghao Su et al.
WorldMirror turns recorded robot videos and trajectories into interactive simulation twins, because building simulation scenes and tasks by hand limits how far simulated robot learning can scale.
Mohammed Bajja, Abdoul Karim A. H. Saliah, Hajar El Hammouti et al.
Maritime Air-to-Sea links are dominated by a line-of-sight ray and a sea-surface reflected ray whose destructive combination produces deep fades. Existing mitigation strategies optimize Unmanned Aerial Vehicle position or trajectory but leave attitude unexploited.
Xumin Wu, Jun Zhou, Jilin Mei et al.
Research on 4D millimeter-wave radar perception algorithms has flourished in recent years, extending from signal processing and object detection to semantic segmentation, motion estimation, occupancy prediction, and dynamic scene reconstruction.
Tengyue Liu, Xincheng Li, Sofia Morales Ferreira et al.
Bioinspired feedback controls for pursuit, tracking, and collective motion are often expressed in terms of the relative configuration between interacting agents.
Xinyu Liu, Qiqi Dong, Boya Jia et al.
A confidence-aware multimodal fusion framework (CAMF) is proposed to realize reliable human intention prediction for industrial human-robot collaboration. This framework fuses four heterogeneous modalities including object 6D pose, gaze, skeletal motion and IMU-based hand motion.
Diyari Mohammed Salih, Ilyes Chaabeni, Naima Ait Oufroukh
Vision-based gesture control accepts commands from any hand in the camera field of view, which is unsafe in shared indoor spaces.
Gustavo Claudio Karl Couto, Eric Aislan Antonelo, Gabriel George Zipperer
This paper presents a low-cost, open experimental platform for research in end-to-end autonomous driving with miniature Ackermann vehicles.
Mathilde Kappel, Clémence Grislain, Mohamed Chetouani et al.
Vision-Language-Action (VLA) models have become a prominent paradigm for mapping multimodal inputs, including semantic instructions, visual observations of the scene, and proprioceptive observations, to robot actions.
Iana Zhura, Didar Seyidov, Dmitrii Plotnikov et al.
Navigating toward human callers is an important capability for rescue robots operating where visual contact is degraded or occluded. We present AcousticDiffusion, a semantically conditioned, audio-guided diffusion policy for human-directed navigation.
Zachary Ravichandran, Jonathan Diller, Fernando Cladera et al.
Foundation models provide robots with the ability to interpret natural language and reason about environmental context, yet most language-conditioned policies assume that goals are well-specified and that task-relevant information is provided upfront via a prior map.
Jiabin Qiu, Zixuan Chen, Hongye Cao et al.
Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A model can therefore achieve low factual prediction error yet poorly distinguish candidate actions.
Mehran Rostamnia, Gianluca Filippone, Ricardo Caldas et al.
Robotic systems increasingly operate in dynamic, uncertain, and open-ended environments, where design-time assumptions may no longer hold, and adaptation becomes necessary to maintain effective and safe operation.
Sixu Yan, Shikang Wang, Binhua Huang et al.
This paper proposes AdaRoboVLG, a task-adaptive Vision-Language-Grasp (VLG) framework that supports generalizable grasp synthesis across different robotic hands.
Caleb Polillio, Petras Swissler
Close-proximity pipeline inspection is challenging for standard drones due to high hovering power consumption, airflow sensitivity, and propeller wash interference with gas sensing. To address this, we present AeRove, a compact bimodal aerial-terrestrial robot.
Xvyuan Liu, Jianjie Fang, Chen Gao et al.
Planners built on visual world models commonly score each predicted outcome by its distance to the encoded goal image. We show that this target can limit control even with exact dynamics and globally optimal short-horizon search: reaching a goal may require actions that initially move away from it.
Teeratham Vitchutripop, Alyssa Quarles, Wenhe Zhang et al.
Over the course of a lifetime, robots may encounter novel scenarios unaccounted for in its original training that result in performance degradation. One common approach to mitigating this issue is to further grow the offline training dataset in hopes of producing a policy robust to these changes.
Jan C. L. Lau, Christian Mele, Jonathan Feng-Shun Lin et al.
Human gait in reality extends beyond straight-line walking, with some situations even requiring drastic back-and-forth rotations. A smooth and stable execution may seem intuitive, but the underlying mechanics remains unknown.
Andrew S. Morgan, Gregory Xie, Capprin Bass et al.
AthenaZero is a bimanual manipulator designed to minimize inertia without compromising control authority.
Kalin Norman, Joshua G. Mangelson
Sidescan sonar is a common sensor for both manned and autonomous marine exploration and mapping, yet very few methods build upon or exploit the geometric projection model of the sensor.
Namiko Saito, Hiroshi Kera
Manipulation requires not only reasoning about the external environment, but also about the robot's physical condition.
Zongyuan Zhang, Christopher Lehnert, Will N. Browne et al.
Forceful manipulation is challenging for humanoid robots because interaction forces can disturb whole-body balance. We introduce the Supporting Hand Strategy (SHS), which enables a humanoid to brace against the environment with one hand while performing forceful manipulation with the other.
Philipp Ausserlechner, Bernhard Neuberger, Alessandro Scherl et al.
Detecting and grasping small objects remains a significant challenge in robotics. Active vision, where the robot moves closer to the object, is an intuitive solution, yet comparing approaches on common ground is difficult since identical physical scene setups are required.
Hu, Jun, Chen, Sihan, Jovanovic, Kosta et al.
Most robots manipulate objects solely with their end effectors, whereas humans flexibly leverage different body parts, such as the forearm and elbow, especially when handling oversized objects.
Fabrizio Cesareo, Sebastiano Mengozzi, Nicola Mimmo et al.
Deep Reinforcement Learning has demonstrated remarkable capability in quadrotor control, yet learned policies offer no guarantee of respecting safety constraints during training or deployment.
Xiang Li, Koya Dendo, Keigo Minamida et al.
Can people distinguish between human and AI agency in humanoid teleoperation?
Hongjin Chen, Zijun Xu, Shihao Ma et al.
Humanoid locomotion across complex terrain demands forward-looking exteroception to anticipate obstacles, yet this signal is unreliable in real-world deployment, failing partially and intermittently.
Zhaoda Du, Michael Bowman, Xiaoli Zhang
Shared control often allocates robot authority based on confidence in inferred human intent, assuming reliable autonomous execution. When this assumption fails, high intent confidence can cause over-helping.
Patrick Rebling, Philipp Nenninger, Reiner Kriesten
The development of autonomous driving demands comprehensive testing in mixed-traffic scenarios involving vulnerable road users (VRUs), where purely artificial agents often fail to capture authentic human social negotiations.
Abilash Philip Madavath, Chandra Yuvesh Aubeeluck, Augustin Raju et al.
Verifying that manufactured batches of milling tools or carbide rotary burrs conform to production order sheets remains a largely manual and error-prone quality assurance task.
Ziyi Sun, Jingwen Chen, Yuxi Wang et al.
Recent advances in humanoid robotics have produced diverse skills through reinforcement learning, motion imitation, and generative modeling. Yet these capabilities remain siloed because they are built around incompatible representations, interfaces, and controllers.
Matteo Merler, Bowen Li, Josh Roy et al.
Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic constraints.
Taehyung Kim, Jongeun Choi
The generation of safety-critical traffic scenarios is essential for training and evaluating autonomous vehicles.
Yuming Chen, Yang Liu
Learned world models may have compact interventions even when their recurrent state is high-dimensional, but it is unclear what happens to such a correction after it enters the model.
Al Jaber Mahmud, Shuai Li, Xuan Wang
In this paper, we study the joint selection of an environmental support contact and a whole-body configuration for a prescribed loco-manipulation task. A contact may provide greater physical support while restricting the motion required for the task.
Jiayun Li, Georgia Chalvatzaki
Contact-rich motion planning (CRMP) is essential for robotic manipulation and locomotion, yet remains computationally challenging due to combinatorial contact decisions.
Ruoyu Yao, Yusen Xie, Qingzhao Liu et al.
Bridging the gap between the discrete reasoning of Vision-Language Models and the continuous, physics-constrained nature of autonomous driving remains a significant challenge.
Riikka Soitinaho, Timo Oksanen
This paper presents a new method for headland coverage path planning for arable fields. Several earlier approaches suggest covering the headland with nested polygons and smooth turns, however, covering the field corners entirely requires manoeuvres with reversing.
Zhihang Qin, Linxin Hou, Zeyu Zhong et al.
Cosserat rod models for soft robots usually construct sectional stiffness by summing material properties over a common cross-section. This assumption becomes inaccurate for trimmed helicoid arms, where load-bearing helix domains are separated and connected only through sparse fused crossings.
Ben Washburn, Clayton Smith, Eli Gaskin et al.
Cylindrical watertight enclosures are widely used across various underwater systems, from unmanned underwater vehicles (UUVs), to remotely operated vehicles (ROVs), to various sensor platforms.
Samer Abualhanud, Max Mehltretter
Reliable 3D understanding of the surrounding environment is a core requirement for autonomous driving. Multi-view surround camera rigs provide broad scene coverage, but the spatially adjacent images typically overlap only minimally.
Zahra Jooyandeh, Masato Kobayashi, Yuki Uranishi
The Dynamic Window Approach (DWA) is widely used for local navigation, but its performance depends strongly on parameters that are typically fixed before navigation.
Kosar Behnia, Ville Kyrki, Gokhan Alcan
Manipulating deformable objects (DOs) is challenging due to their high-dimensional state space, underactuated dynamics, and partial observability.
Thang Tran Viet, Thanh Nguyen Canh, Huy Uong Gia et al.
Human-robot interaction (HRI) enables intuitive and intelligent collaboration between humans and robots in real-world environments. This paper introduces a humanoid robot prototype designed as a flexible testbed for developing and integrating artificial intelligence (AI) modules in HRI tasks.
Liang Zhou, Jiaming Su, Yancong Wei et al.
Quadruped manipulators enable mobile grasping in complex environments, yet their whole-body control policies remain vulnerable to unreliable onboard visual perception.
Jaskrit Singh, Kashif K. Noori, Jing Xiao et al.
Off-road traversability is direction-dependent and vehicle specific, yet most global maps assign a single isotropic cost to each location.
Chang Liu, Chenhao Yu, Honghao Zhao et al.
Current robot-assisted minimally-invasive surgery (RMIS) platforms provide a fixed console for the surgeon to view stereo endoscopic images and teleoperate instruments inside the patient.
Ning Hu, Shuai Li, Jindong Tan
This study asks whether training-time motion-prior regularization can improve insertion success when a diffusion policy is learned from only 15 demonstrations.
Joaquin Palacios, Katelyn Lee, Cheng Zhang et al.
Collecting data for manipulation with high-DOF hands is challenging, as interfaces must capture rich hand motion while rendering the contact interactions essential for precise manipulation.
Eric Xie, Daniil Lisus, Timothy D. Barfoot
Spinning frequency-modulated continuous-wave (FMCW) radars have been gaining popularity in autonomous vehicle perception on account of their robustness to adverse weather conditions and 360{\deg} field of view.
Abdelhakim Amer, Andriy Sarabakha
This work presents a control framework that enables a multicopter equipped with a two-axis gimbal to emulate the flight dynamics of a fixed-wing aircraft.
Junjie Yang, Qingwei Zeng, Youyou Li et al.
World models support autonomous driving by predicting the scene evolution associated with candidate trajectories. Driving dynamics differ in predictability, motivating a distinction between regular evolution and event-induced deviations that call for selective correction.
Jimin An, Ryan Lee, Jingshu Peng et al.
Biological torque control directly maps an estimated human joint moment to exoskeleton assistance, providing a task-agnostic strategy for supporting diverse locomotor activities.
Duo Zhang, Zhizhuo Zhang, Xiaoli Bai et al.
We present FAVOR (Free-floating Arm Velocity Optimization with Recursive Sensitivities), a planner for collision-free reaching, tracking, and prescribed-time pre-grasp interception on an unactuated spacecraft.
Abhiram Maddukuri, Georgios Pavlakos
Ego-Exo4D is a large-scale dataset providing synchronized egocentric and multi-view exocentric video, a rich resource for skill learning and assessment, procedural activity understanding, and embodied AI.
Mattia Piccinini, Lucas Schulze, Alice Plebe et al.
The rapid progress of artificial intelligence is reshaping robotics and accelerating the adoption of learning-based approaches.
Vicky Feliren, A. Taufiq Asyhari, Muhamad Risqi U. Saputra
Uncertainty estimation for Vision-Language-Navigation (VLN) models is a critical task since it can help identify ambiguous and unreliable predictions, enabling agents to make safer navigation decisions.
Dexter Ong, Vijay Kumar, Pratik Chaudhari
Reliable relative localization between aerial and ground robots is a key requirement for tightly coordinated heterogeneous teams.
Haoran Pei, Mingrui Luo, Senbao Wang et al.
Reliable robot deployment requires online failure monitoring, yet existing monitors mainly derive risk from proxy signals or train dedicated monitoring components.
S. Talha Bukhari, Austin Garrett, Yi Wei et al.
Visuomotor policies learn a direct map from raw sensory observations to robot action sequences. Policies based on Diffusion and Flow Matching capture the multimodal distribution over action sequences in an end-to-end manner.
Kun Hu, Menggang Li, Kaidi Wu et al.
Achieving robust SLAM in large-scale underground coal mines with complex structures and severe degeneracies remains highly challenging.
Daniel Huczala, Michael Pieber, Johannes Gerstmayr et al.
Overconstrained rational single-loop linkages are efficient, compact, and low-cost custom mechanisms, yet their deployment in industrial settings is limited. In simulations, rigid body formulations fail due to redundant constraints.
Chenhuan Liu, Yi Xu, Feng Wu et al.
Embodied AI, including vision-language-action and world-action models, must operate reliably in the physical world.
Zhengyu Tao, Xin Li, Xin Wang
Vision-language-action (VLA) models have demonstrated strong capabilities in robotic manipulation, yet their reliance on visual perception limits robustness in contact-rich environments, where critical physical interaction states may not be visually observable.
Martín Crespo, Sergio Junco, Matías Nacusse
This paper presents an energy-based controller for a multiagent robotic system designed to achieve and maintain a specific formation while moving on a plane and avoiding collisions between agents. The controller emulates a network of elementary spring-damper modules connecting pairs of agents.
Lav R. Varshney
Open-loop multilegged locomotion over rough terrain has been interpreted as matter transport over a noisy channel: leg-ground interactions are discrete basic active contacts, terrain deletes or perturbs those contacts, and spatial redundancy concentrates the resulting thrust and arrival time.
Sichang Su, Benjamin Yang, Zhiyun Deng et al.
A pretrained robot foundation policy may execute most of a long-horizon task yet repeatedly fail at a few critical subtasks. Collecting additional full-task demonstrations for supervised fine-tuning (SFT) requires operators to repeat behaviors the policy already performs well.
Guillermo Legarda Herranz, Gianpiero Francesca, Mauro Birattari
Robot swarms, by virtue of their decentralised architecture, are a natural tool for scalable, robust modelling of spatial fields, such as water temperature, wind velocity, or terrain elevation.
Yifan Xie, Hekun Tian, Jinkun Liu et al.
Human videos provide rich manipulation experience, but extracting action representations that preserve useful motion remains challenging. Visual reconstruction alone can entangle manipulation-related motion with appearance changes and camera movement.
Yupeng Zheng, Xiang Li, Songen Gu et al.
Vision-language pre-training and predictive world modeling provide robot policies with rich semantic and dynamic visual features, but their native action and visual-prediction objectives may omit critical physical and task structure while retaining control-irrelevant visual redundancy.
Chankyo Kim, Minghan Zhu, Tzu-Yuan Lin et al.
Neural inertial odometry increasingly uses networks as learned measurements inside filtering pipelines.
Julien Vanderheyden, Guillaume Drion, Fulvio Forni et al.
Dexterous robot hands must often grasp objects whose shape, size, and pose are known only approximately. Grasp planners typically require accurate object models or correct errors with feedback, but how much inaccuracy a closing motion can tolerate on its own remains unclear.
Jinu Pahk, Jesoon Kang, Taegeon Park et al.
Vision-language-action policies benefit from geometric supervision, but current-frame geometry alone does not explicitly describe the changes associated with manipulation.
Javier Borquez, Shuang Peng, Somil Bansal
Hybrid dynamical systems provide a powerful modeling framework for robotic systems, particularly in contact-rich environments. However, ensuring safety and performance in such systems remains challenging due to the intricate coupling between continuous dynamics and discrete mode transitions.
Zengjue Chen, Peidong Liu, Jiawei Li et al.
Generalist robot policies have demonstrated strong generalization across robotic manipulation tasks, yet their success rates remain limited in com- plex long-horizon scenarios.
Toan Nguyen, Weiduo Yuan, Siheng Zhao et al.
Object transportation is a fundamental capability for humanoid robots operating in real-world, human-centric environments, yet existing methods struggle when clutter constrains free space around both the robot and its carried payload.
Ryohei Kobayashi, Kosei Isomoto, Yuga Yano et al.
We propose a framework that transfers tacit human subjective criteria to robotic systems for the appropriate grasping of deformable objects. Achieving such behavior is challenging because a semantic gap exists between qualitative human expectations and quantitative robotic measurements.
Morgan Masters, Nikolaas Bender, T. Luca Altaffer et al.
Real-world perception systems must adapt to changing environments, but manual image annotation cannot scale to field data volumes.
Jingzhi Cui, Zhexiong Wang, Bangjie Xu et al.
High-speed racket sports provide a demanding testbed for humanoid robots, requiring time-critical decisions, precise striking, and dynamic whole-body coordination.
Haojian Huang, Zexi Li, Junhao Guo et al.
General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action.
Yiqi Wang, Zhifeng Rao, Jiaqi Zhang et al.
Open robot policies increasingly follow two paradigms: vision-language-action models (VLAs) directly map observations and instructions to actions, whereas world-action models (WAMs) incorporate learned video or world dynamics into policy learning or action generation.
Tobias Schaffer, Mohab Elkhayat, Daniela Nicklas et al.
Vision-language-action (VLA) systems already bring together two valuable resources for robot learning: rich visual representations and demonstrations of successful task execution.
Chuyang Xiao, Peilin Meng, David Held
Coordinated bimanual manipulation is challenging because the motion of either arm can alter the shared 3D scene and thereby affect the other arm.
Jie Xu, Kangjin Yu, Ziyi Jin et al.
Standard behavior cloning supervises actions without explicitly constraining the future representation paired with each demonstrated action chunk. We introduce JEPA Policy, a diffusion-free framework that uses the action chunk and its observed future representation as paired training targets.
Zeyu Lou, Yanhong Zeng, Yong Wang et al.
A general-purpose vision-language model can understand a task goal without knowing how a particular robot's motion and functional parts produce the intended effect.
Binbin Lian, Xinyu Liu, Tao Sun
A hybrid hierarchical learning framework is proposed to achieve high-precision assembly of 170mm cylindrical components with tolerance of 0.1mm.
Yikai Wang, Honghao Zhu, Xiao Hu et al.
Humanoids now walk, balance and reach with remarkable generality: one whole-body tracking policy follows references from a human, or from an end-to-end policy.
Yongshuo Liu, Xu Gao, Morui Zhu et al.
We present LANTERN, a closed-loop benchmark for temporally grounded cooperative warnings.
\"U. Bora G\"okbakan (WILLOW), St\'ephane Caron (ISIR), Philippe Sou\`eres (LAAS-GEPETTO)
Active perception allows autonomous agents to select their viewpoints rather than passively process the viewpoints given to them, enabling them to target where to reduce uncertainty about their environment.
Jiaming Zhong, Reza Valiollahi Mehrizi, Mohammad Pirani et al.
Agent-based model predictive control (AMPC) has recently been proposed as a distributed scheme that collaborates with all agents to achieve optimal holistic performance.
Elvin Yang, Christoforos Mavrogiannis
We focus on human-robot collaborative transport, a challenging task of broad relevance spanning logistics, manufacturing, and the home, in which a user and a robot work together to relocate a large or heavy object.
Sreejan Kumar, Marcelo Mattar, Lea Duncker
Learning flexible motor primitives is a hallmark of skilled motor control. Recent neuroscience theory proposes that motor primitives may be implemented as low-rank perturbations of a shared recurrent network, but leaves open how such a system is learned.
William D. Compton, Zachary Olkin, Ryan Bena et al.
Research in humanoid robotics has achieved rapid progress in locomotion, and recent results have pushed the boundary on autonomous navigation.
Junnosuke Kamohara, Feiyang Wu, Andy Ningan Zong et al.
Humanoid locomotion on granular terrain remains a significant challenge due to its complex foot-terrain interaction dynamics that are difficult to model. Existing approaches either ignore granular contact dynamics or incorporate simplified normal force models with heuristic tangential components.
Afagh Mehri Shervedani, Siyu Li, Natawut Monaikul et al.
Robot assistants for older adults and people with disabilities need to perform collaborative tasks with users effectively.
Juliette Grosset, Marie Dubromel, Hélène Lechêne et al.
Offshore maintenance requires operations in the air, the surface, and the subsea domain and include human supervision. This paper presents LOTUSim-Energy, a real-time maritime simulator designed for multi-domain human--drone interaction for offshore operation and maintenance.
Sota Yuzaki, Temma Suzuki, Hiromi Tada et al.
The performance improvement of high-power flat BLDC motors has accelerated the development of dynamic robots. However, many commercially available servo motors assume operating voltages of 48 V or lower, which limits the maximum rotational speed.
Yang Zhou, Jiuhong Xiao, Shizhao Ye et al.
Robotic novel view synthesis (NVS) must recover both visual appearance and metric 3D structure, yet most generative NVS methods rely only on images, overlooking LiDAR, a complementary sensor common on robotic platforms.
Arpita Kumari, Anupam Chatterjee, Richa Srivastava
Two-Wheeled Inverted Pendulum (TWIP) robots are useful for studying how to control systems that are naturally unstable and have fewer actuators than degrees of freedom. Adding autonomous line-following to these robots is challenging because steering and balancing are closely linked.
Sizhe Zhao, Haozhe Xie, Weiyu Zhao et al.
Mainstream robotic policies often adopt a Markovian formulation, but many complex real-world manipulation tasks are inherently non-Markovian, requiring long-horizon memory beyond the current observation.
Adam Hung, Bardienus P. Duisterhof, Deva Ramanan et al.
World-action models (WAMs) jointly model future observations and actions, typically predicting the future as RGB images. Other visual modalities such as depth, pretrained visual features, and point tracks can more efficiently capture geometric, semantic, and motion features.
Tara Sadjadpour, Siming He, C. K. Wolfe et al.
Human hand-object interactions (HOIs) provide a rich source of demonstrations for dexterous manipulation, but learning directly from them presents challenges in bridging morphology gaps, ensuring dynamical feasibility, and sim-to-real deployment.
Seongjin Bien, D\'ebora Oliveira Makowski, Roberto Calandra et al.
Large-scale datasets are essential for training generalist robot control policies. Collecting real-world tactile data is costly and time-consuming, motivating the use of tactile simulations. However, current tactile simulators capture only overall contact geometry and miss fine details like texture.
Vittorio Palladino, Teaya Yang, Ruiqi Zhang et al.
Autonomous UAV flight through cluttered and partially unknown environments requires reasoning not only about observed obstacles but also about occluded regions that the sensor cannot observe.
Jack B. Jedlicki, Tanguy Dieudonn\'e, Heng Yang
Long-horizon manipulation often requires reasoning about state absent from the current view, such as a vanished object's location, temporal identity, or the contents of a shuffled container.
Joaquin Caballero, Emilio Garcia-Fidalgo, Alberto Ortiz et al.
Despite significant progress in odometry estimation, long-term drift remains a fundamental limitation of incremental pose integration, especially in large-scale or loop-free environments.
Xiangrui Wang, Yuetong Wu, Jalen Beeman et al.
Open datasets describing human behavior in environments shared with mobile robots remain limited, particularly for retail activities that combine locomotion, reaching, object handling, and robot guided movement.
Mohamed Dawod
Large-scale egocentric and whole-body human demonstrations are becoming a primary source of data for embodied intelligence. They record what people perceive and do, but rarely the external specification that gave an action its purpose.
Friedrich Graaf, Elias Birkefeld, Christian Eichmann et al.
Legged robots offer a variety of automation applications in real-world scenarios. But areas that are difficult to traverse, like slopes, caves, or scaffolding, still pose a great challenge for traversal.
Zhengran Ji, Jonathan Hyun, Boyuan Chen
Collective intelligence depends not only on the capabilities of individual members, but also on how those members are organized.
Sai Krishna Reddy Sathi, Anuj Tiwari
Adapting language models to new domains via continual pre-training raises a basic evaluation problem: if the training corpus overlaps with what the model already knows, performance gains cannot be cleanly attributed to new learning rather than pre-existing knowledge.
Christian Sternitzke, Sebastian Blumenthal, Lukas Kleedoerfer et al.
Many publications on robotic systems in healthcare describe early-stage work on low technology readiness levels.
Dibyendu Ghosh
Homes change between a robot's visits. Navigation benchmarks pose their goals in the world the agent currently sees, and the two-visit benchmarks that exist score recall or rearrangement rather than navigation.
Li, Chuqiao, Xie, Xianghui, Cao, Yong et al.
Text-conditioned full-body human-object interaction (HOI) generation requires synthesizing human motion and object trajectories that match the input text while remaining precisely coordinated over time.
Abolfazl Babanazari, Carson Cramer, Tyler Summers et al.
Global point-cloud registration remains challenging when limited overlap, repetitive geometry, and sensor noise produce correspondence sets dominated by outliers.
Hyeonjin Choi, Joongheon Kim, Daekyum Kim
Learning energy-efficient humanoid locomotion requires discovering mechanically economical gait coordination, not merely reducing actuator effort. Reinforcement learning promotes efficiency through effort-related reward penalties, which guide the step-to-step mechanics of walking only indirectly.
Marat Agranovskiy
Autonomous navigation in dynamic environments is a critical challenge, particularly when spaces are shared with other mobile agents whose future trajectories are known.
Hang Yu, James Staley, Cheng Xi Tsou et al.
Human demonstrations provide dense policy-level information but sometimes lack local precision. Human feedback presents accurate local critiques, but offers sparse evaluations rather than direct policy guidance.
Aoran Jiao, Wenda Zhao, Hshmat Sahak et al.
Terrain assessment is a critical capability for off-road mobile robots, enabling safe and reliable navigation through unstructured and geometrically complex environments. Conventional geometry-based terrain assessment is fast to compute but often overly conservative in unstructured environments.
Sang Min Kim, Jinwoo Seo, Hyeongjun Heo et al.
We present POIL, a point-based one-shot imitation learning framework with stable dynamical systems.
Jenny Wang, George Kantor
Policies trained with imitation learning can accumulate errors over time, causing the robot to drift outside the training distribution. Existing methods mitigate this covariate shift by collecting additional data where the policy fails or is likely to fail.
Kaizhen Tan, Diyu Zheng, Tim Guangyu Wu et al.
Social-navigation algorithms are often evaluated under a fixed pedestrian-behavior distribution, despite substantial variation in pedestrian responses to robots across individuals and social contexts.
Angelo Ferrando, Matt Luckcuck, Pedro Ribeiro
Runtime Verification is well suited to autonomous and robotic systems because it checks the behaviour that is actually observed during execution. Its main limitation, however, is that it is usually reactive: the monitor detects a violation only after the system has already performed a bad event.
Azmain Yousuf, Siwei Cai, Knut Peterson et al.
The rapid proliferation of unauthorized unmanned aerial vehicles (UAVs) has created a growing need for robust, jamming-resistant counter-UAV systems for perimeter defense.
Léonie Plancoulaine, Sylvain Guégan, Franck Plestan et al.
Underactuated robotic hands achieve adaptive and robust grasping with a reduced number of actuators, but predicting the stable equilibrium pose of the grasped object remains a significant challenge.
Dogun Kim, Yongjae Lee, Joonhee Lim et al.
Recent Vision-Language-Action (VLA) models for autonomous driving have incorporated world modeling by predicting future driving scenes alongside driving actions, demonstrating strong planning performance.
Kai Stewart, Yasunori Toshimitsu, Robert K. Katzschmann
Dexterous in-hand manipulation of a grasped object with an anthropomorphic hand is an unsolved frontier for robot dexterity. The contact-richness and highly dynamic nature of object-hand interactions tend to require extensive modeling or data-collection efforts for learning-based approaches.
Yuyao Liu, Jiayuan Mao, David Hsu et al.
Coding agents have demonstrated enormous success in solving complex programming problems.
Geoffroy Keime, Nicolas Cuperlier, Benoit R. Cottereau
Robotic systems operating in dynamic environments require visual perception that evolves continuously with the incoming sensory stream.
Sang Min Kim, Alexander Alexiev, Tzu-Yuan Lin et al.
Robust dexterous grasping requires maintaining physical stability despite contacts interactively evolving across the entire hand. A precomputed force distribution can easily fail under object motion, modeling errors, or external disturbances.
Ryo Terashima, Yuga Yano, Koshun Arimura et al.
Service robots must respond to unexpected instructions in real-world environments. However, robots cannot detect all failures and exceptions during a task. To address these issues, we propose a real-time feedback function that enables robots to modify their behavior based on human feedback.
David C. Conner, Joshua Luzier, William J. Doyle et al.
High-level robotic supervisors coordinate capabilities whose reported outcomes determine the robot's next action. Reactive synthesis can generate such supervisors with formal guarantees, but deployment requires more than proving a Generalized Reactivity (1) (GR(1)) specification realizable.
Jiyul Lee, Dongho Yee, Juahn Oh et al.
Most minimally invasive procedures are still performed with hand-held laparoscopic instruments, yet only the endoscopic video is retained; the instrument motion that expresses surgical skill, and that could support skill assessment and robot learning, is lost.
Natapat Kirdwichai, Tobias Driskell-Poole, Andrei Sontea et al.
Depth-conditioned locomotion policies have demonstrated impressive agile maneuvers, but can be steered to unpredictable actions when observations are outside their training distribution.
Ke Wu, Fangju Yang, Xiaohui Zhang et al.
Many planning and control tasks for tendon-driven continuum robots (TDCRs) require the complete Cartesian backbone geometry.
Jian Zhou, Xingyu Zhang, Rui Ma et al.
Muscle-driven locomotion provides a physically grounded approach to generating realistic human movement. However, achieving both physiological plausibility and adaptability to changes in musculoskeletal capacity and external disturbances remains a fundamental challenge.
Linan Deng, Xing Liu, Lin Hong et al.
Dexterous in-hand manipulation requires coordinated control of multiple actuated joints, and a runtime joint fault can abruptly disrupt the contact configuration required for successful manipulation.
Shrutheesh R. Iyer, Thomas Cohn, Zachary Kingston
Robots often must satisfy one or more constraints during motion planning for real-world tasks. When such constraints reduce the valid configuration space to a measure-zero subset, sampling based planning algorithms require modifications to draw feasible samples.
Han Qi, Heng Yang
Robot manipulation policies must generalize across visual shifts while preserving scene context relevant to action.
Zhenxuan Fan, Bo Zhang, Yutong Lin et al.
Vision-Language-Action (VLA) models have shown promising progress in language-conditioned robotic manipulation.
Sida He, Lingxi Xie, Yunning Cao et al.
General-purpose multimodal agents can write robot-control programs, but repeated exploration and model-mediated action selection can make execution slow.
Yinghua Zhou, Junjie Ye, Yiqi Zhao et al.
World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action denoising process at each replanning cycle incurs substantial latency, delaying action updates and limiting closed-loop responsiveness.
A K M Nadimul Haque, Sheila Sutjipto, Marc G. Carmichael et al.
Skill adaptation frameworks based on reinforcement learning often require restrictive assumptions to maintain stability, such as fixed observations or tightly controlled exploration schedules.
Yijie Lu, James Zhao, Weiming Zhi
Learning from human videos offers a promising route to acquiring diverse manipulation skills. Extending this capability beyond tabletop settings to long-horizon mobile manipulation requires adapting and composing demonstrated interactions across changing scenes and robot configurations.
Wonje Jeung, Sangyeon Yoon, Hyesoo Hong et al.
Vision-language models are increasingly used as reward functions for robotic learning, but this role requires paraphrase invariance: the same trajectory should receive the same reward under semantically equivalent goal descriptions. We show that current VLM reward models often violate this property.
Yishu Li, Liyuan Geng, Xinyi Mao et al.
While pretrained robotic policies exhibit impressive capabilities in controlled environments, unobserved physical properties and dynamics require these policies to rapidly adapt during deployment.
Tengbo Yu, Jiahao Wu, Daohan Li et al.
Imitation learning for dexterous hands is bottlenecked by the difficulty of collecting contact-rich demonstrations that transfer faithfully to the robot.
Hongxin Zhang, Chunru Lin, Tsun-Hsuan Wang et al.
While Vision-Language-Action (VLA) models demonstrate impressive capabilities in robotic manipulation, their memoryless nature renders them brittle to test-time environment shifts, particularly hardware shifts caused by wear or imperfect calibration.
Gopi Krishna Erabati, Bjarne Johannsen, Angus Stewart et al.
Autonomous wheel-loader control requires joint reasoning over task semantics, egocentric vision, proprioception, and 3D scene geometry.
Wen Sin Lor, Jun Wang, Suyi Li
Many physical properties relevant to robotic manipulation are hidden from vision. A sealed object, for example, may reveal little about its center of mass (COM) or internal contents until it is lifted, shaken, or otherwise dynamically perturbed.
He Zhu, Lusen Zhao, Kwan Man Cheng et al.
Large-scale demonstrations have driven unprecedented progress in robot learning, yet collecting robot data through teleoperation is expensive and difficult to scale to diverse environments and long-horizon tasks.
Gjergj Plepi, Sven Behnke
Text-conditioned latent diffusion models perform strongly in video generation and are promising backbones for robotic applications.
Hshmat Sahak, Aoran Jiao, Nicholas Rhinehart et al.
Temporary obstacles that may block a robot's planned route create a sequential navigation problem: a robot must decide whether to wait for a blockage to clear, reroute, or acquire more information about the obstacle before acting.
Yutai Zhou, Erdem Bıyık
Reinforcement learning from human feedback (RLHF) has emerged as a powerful yet sample-inefficient approach for learning reward models from human preferences, making active learning a critical component in synthesizing informative preference queries.
Tingcong Liu, Aye Phyu Phyu Aung, Junjie Xiong et al.
Soft and continuum robots enable manipulation through distributed body deformation and contact, yet translating language and visual context into executable whole-body actuation remains a fundamental challenge.
Yujie Xiong, Peng Zhai, Taixian Hou et al.
Brachiation enables primates to move across overhead supports when ground paths are blocked, suggesting a complementary locomotion mode for robots operating in cluttered or hazardous environments.
Zhaofeng Luo, Xinyu Lu, jaehoon Choi et al.
Applying adhesive tape to secure wire harnesses or seal packages requires robots to coordinate a flexible strip, a moving roll, and surfaces that attach and detach.
Niloufar Amiri, Houman Masnavi, Farrokh Janabi-Sharifi
This paper investigates temporal neural networks for \mbox{end-effector} position \mbox{estimation} of an aerial continuum manipulator (ACM) operating under aerodynamic effects induced by the unmanned aerial vehicle (UAV).
Som Sagar, Ransalu Senanayake
Robot manipulation policies are usually trained under the assumption that a commanded action produces the same motion as it did during training even after hours of operation.
Haoying Li, Qihang Liu, Yifan Peng et al.
Neural inertial odometry has demonstrated strong potential for motion estimation in challenging environments, yet inertial-only preintegration remains sensitive to IMU bias and uncertainty.
Kejia Gao, Liguo Zhou, Lei Yu et al.
We study whether a manually specified runtime supervisor can correct recurring failures of an existing end-to-end parking policy in a fixed CARLA parking lot.
Derin Ozturk, Kaan Akan, Irwin Wang et al.
Nanodrones require accurate, real-time state estimation under severe sensing and computational constraints. We present TinyCVIO, a visual-inertial odometry system that co-designs miniature sensing, visual processing, and estimation for a commodity dual-core microcontroller with 520 kB SRAM.
Cong-Thanh Vu, Yen-Chen Liu
In the field of Human-Robot Interaction (HRI), achieving flexibility in human-accompanying within real-world environments holds great potential for various applications but also poses significant challenges.
Vivek Chavan, Yahuan Shi, Oliver Heimann et al.
Vision-language-action (VLA) models can execute short manipulation skills, but remain brittle in long-horizon procedures requiring persistent task state, dependency-aware reasoning, conditional decisions, and reliable grounding.
Zongyuan Shen, Haodong Liu, Gao Wang et al.
This paper presents a novel online coverage path planning (CPP) algorithm, called TRACE, for real-time coverage of unknown environments. TRACE is built upon a hierarchical coverage tree that provides a global representation of the evolving connectivity of the uncovered space.
Ayush Jain, Sreeharsha Paruchuri, Ishita Gupta et al.
Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over long horizons, or track all points across only short clips.
Maximilian Adang, Timothy Chen, Lars Osterberg et al.
Neural behavior cloning compresses demonstrations into large models, making individual actions difficult to trace and policy updates costly. Retrieval policies retain access to demonstrations but struggle with mismatch between recorded and live behavior.
Masato Kobayashi, Takeru Tsunoori
Underwater visuomotor policy learning has focused primarily on single manipulators, while bimanual imitation learning has been studied largely in air.
Yuncong Yang, Jinlong Li, Yulong Xue et al.
We present Underwater C$^{3}$-JEPA (cross-view, control-conditioned, context-extended), an object-centric multi-view predictive world model for near-field heavy-load underwater ROV salvage.
Wei Li, Rui Shao, Jie He et al.
Recent advances in Vision-Language-Action (VLA) models have improved robotic manipulation, yet observation-to-action learning remains limited by a fundamental transition realizability gap, manifested in three tightly coupled problems: (i) Transition ambiguity.
Riccardo Donà, Espedito Rusciano, Germana Trentadue et al.
European Union (EU) policymakers adopted revolutionary data collection provisions for Automated Driving Systems (ADS) in the recently approved regulation that allows driverless vehicles to be operated on public roads.
Jeon Ho Kang, Igal Tamarkin, Ethan Niu et al.
Real-world robotic disassembly requires long-horizon execution, where robots must perform ordered sequences of manipulation tasks across multiple parts within a single scene.
Fernando Cañadas-Aránega, José C. Moreno, José L. Blanco-Claraco et al.
Advanced crop monitoring inside greenhouses is becoming one of the primary objectives of research centers. High-performance sensors, such as LiDAR or stereo cameras, have traditionally been employed for this purpose, though these often have a high cost.
Ole Hoffmann, Mateo de Mayo, Daniel Cremers
Perception in robotics and XR fundamentally relies on good state estimation. Visual-inertial odometry (VIO) and Simultaneous Localization and Mapping (VI-SLAM) are proven ways of achieving this goal in a cost-effective and accurate manner.
Chang Song, Bin Qian, Yan Feng et al.
Long-horizon robot manipulation with Vision-Language-Action (VLA) policies remains vulnerable to execution-time deviations, as final task success provides little information for diagnosing and correcting failures caused by action noise, object displacement, or goal misalignment.
Jiuyi Xu, Qing Jin, Meida Chen et al.
Post-training quantization reduces the memory requirements of vision-language-action (VLA) models, but precision selection must account for the interaction between layer scope, numerical format, and calibration.
Mingkai Jia, Jiaxin Guo, Zhijian Shu et al.
Driving world models learn rich predictive representations of the surrounding environment from visual observations, yet accurate visual prediction does not necessarily translate into effective trajectory planning.
Vivek Chavan, Pengtao Xie, Yahuan Shi et al.
Visuomotor imitation policies can achieve high performance under in-distribution visual conditions yet fail when visually similar objects or receptacles are introduced.
Jiaming Wang (National University of Singapore)
Can a robot improve itself the way coding agents now improve software? We built an agentic system to find out.
Zhengshu Zhang
When a robot faces unfamiliar physical conditions, a common approach is to collect evidence about what changed and adapt.
Guanzhong Sun, Junyi Ma, Yixuan Zhou et al.
Closed-loop visual servoing requires predictions that indicate whether an action reduces task error, not only whether the action is plausible.
Edward Holmberg, Elias Ioup, Mahdi Abdelguerfi
Repeated in-situ evaluation of ocean-glider planners requires scarce vehicles, operators, deployment and recovery resources, and ocean conditions that cannot be reset for competing algorithms.
Omar Curiel, Jing-Yuan Huang, Po-Chih Chen et al.
We present a MR safe, master-slave robot manipulator for abdominal interventions in the MRI chamber. A human operated 2+1-DoF master controller manipulator transmits motion and force to a 2+1-DoF slave manipulator via fluid transmission.
Zheyu Zhuang, Ruiyu Wang, Nick Heppert et al.
Visual bottlenecks that focus policy inputs on regions of interest (ROIs) can improve data-efficient visuomotor learning by separating where to look from how to act. Many ROI interfaces rely on external spatial labels, such as gaze, object classes, or affordance annotations.
Kechen Liu, Ola Shorinwa
State-of-the-art action-conditioned video models are typically restricted to a single robot embodiment, preventing them from leveraging the vast corpus of heterogeneous video data that contains rich signals for learning generalizable physics.
Gehan Zheng, Matthew Johnson-Roberson, Weiming Zhi
Contact-rich manipulation failures are often detected only after the robot has committed to contact.
Ann-Kathrin Schwehn, Alexander Langmann, Mattia Piccinini et al.
Autonomous racecars operate at the limits of vehicle dynamics, where small control errors translate into safety-critical behavior and lost performance. Trajectory planners assume perfect tracking and remain blind to execution errors.
Anisa Saleem, Duksu Kim
Reinforcement learning is promising for autonomous urban driving, but long-horizon goal-directed navigation asks a policy to acquire several competing behaviors at once--reaching a distant goal, tracking a route, avoiding obstacles, obeying signals--and a fixed objective gives no order in which to learn them.
Yu Hu, Fangzhou Zhao, Liang Chen et al.
Airborne torque reaction cannot recover takeoff errors beyond the wheel angular-momentum budget. DART-S applies ramp-face suspension preconditioning to change pitch, pitch rate, and wheel spin before liftoff, thereby shifting the queried state and altering the remaining authority budget.
Atiksh Bhardwaj, Edward Weiyi Duan, Prithwish Dan et al.
Vision-language-action models (VLAs) are moving rapidly towards deployment as general-purpose manipulation policies, but we currently lack basic tools for understanding what these models represent internally or for monitoring them at runtime.
Siyuan Ma, Boshi Zhang, Yutian Zhang et al.
Mobile manipulation requires a robot to predict how locomotion and arm motion jointly alter future observations and control. Existing world-action models, developed largely for fixed-base platforms, do not explicitly distinguish camera ego-motion from base and arm actions.
Shivam Vats, Sudarshan Harithas, Mete Tuluhan Akbulut et al.
We consider the problem of autonomously learning robot skills under a limited practice budget for sequential tasks.
Juan José García Cárdenas, Alperen Kenan, Hamidreza Raei et al.
Intuitive teleoperation interfaces are crucial for the safe and effective operation of robotic manipulators in challenging environments.
DreamX Team, Rui Chen, Xiangxiang Chu et al.
We present \textbf{DreamX-Phi 1.0}, an action-conditioned video world model for robotic manipulation that, given an observed frame, a language instruction, and a prescribed action sequence comprising end-effector poses and gripper states, predicts the resulting future observations.
Junfeng Li, Junjie He, Zhide Zhong et al.
Vision-Language-Action (VLA) models have become a powerful paradigm for robot manipulation, but training a single generalist policy for heterogeneous robot embodiments remains an open problem. Existing methods have two main limitations.
Ishtia Zahir, Eslam Saleh, Maryam Rezayati et al.
Textile-integrated capacitive sensors offer flexible and conformable tactile sensing for wearable electronics and human-robot interaction; however, the influence of yarn-level architecture on capacitive transduction characteristics remains insufficiently quantified.
Canzhi Chen, Zan Wang, Siqi Zhu et al.
This paper introduces Embodied Scene Rearrangement Planning (ESRP), a novel task requiring embodied agents to rearrange furniture in 3D scenes to match a target configuration using only egocentric observations and a top-down target layout.
Alexei Odinokov, Rostislav Yavorskiy
As heterogeneous robotic systems deploy across diverse urban zones, maintaining safety amid complex human-robot interactions remains a critical challenge. We present a unified framework that bridges systematic hazard analysis and runtime enforcement using hazard-informed safety envelopes.
Stefan Schneyer, Timo Bachmann, Maged Iskandar et al.
Contact-centric tasks on surfaces, ranging from inspection and cleaning to sanding and polishing, require robots to systematically cover the surface while maintaining stable contact.
Tsunehiko Tanaka, Matthew Stephenson, Alistair Macvicar et al.
Robots executing long-horizon manipulation tasks from natural-language instructions must reason about both semantic task structure and geometric feasibility. However, under partial observability, the availability of goal-relevant objects may be uncertain.
Ajith Anil Meera, Pablo Lanillos, Wouter Kouw
An autonomous robot efficiently exploring an unknown environment, such as looking for water sources on Mars, faces two simultaneous demands: building an accurate information map while quickly finding the regions of greatest value, and paying for every meter of travel and the cost of every measurement it takes.
Zekai Li, Jiaming Tang, Zhijian Liu
Vision-Language-Action (VLA) models are increasingly promising for robotic manipulation, yet their real-world deployment remains bottlenecked by high inference latency and unstable asynchronous execution.
Chenghao Gu, Hanyang Yu, Jingbo Zhang et al.
Generalist robot policies exhibit strong capabilities, but their robustness in complex and unseen environments remains limited. Scaling robot learning and evaluation in diverse real-world environments remains costly and challenging.
Dairu Liu, Zekun Qi, Jiayu Zeng et al.
Humanoid motion tracking is central to teleoperation and whole-body imitation, yet evaluation often disagrees with what people perceive in videos.
Lee, Yumin, Ju, Hyoseok, Kim, Giseop
Long-term robot operation in evolving environments requires object-level understanding that persists across repeated revisits.
Mehdi El Krari, Jonathan Smith, Maria Fox
The marine science community increasingly relies on Marine Autonomous Vehicles (MAVs) to collect the critical environmental data required to understand global ocean systems.
Rafal Robert Karpinski, Fethiye Irmak Dogan, Nikhil Churamani et al.
Social robots are expected to operate across diverse environments, where similar arrangements can imply different socially appropriate actions, e.g., starting a conversation may be acceptable in a crowded home but disruptive in an office meeting.
Yanchen Guan, Xingcheng Liu, Bin Rao et al.
End-to-end autonomous driving has evolved from camera-to-control regression toward planning-oriented systems that use structured representations, trajectory-level outputs, and increasingly realistic evaluation protocols.
Yuxuan Chen, Wanruo Zhang, Xiao Li
Vision-Language-Action (VLA) models have recently achieved promising performance in robotic manipulation. However, existing benchmarks mainly evaluate generalization on static manipulation tasks and largely overlook dynamic interaction scenarios.
Alperen Kenan, Paul Bremner, Manuel Giuliani
Learning from demonstration (LfD) provides a developmental framework through which robots can develop motor skills by observing and imitating human dynamics, reducing reliance on explicit programming to teach a skill to a robot.
Mohd. Faizuddin Faruqui, Ratnangshu Das, Ravi Kumar L et al.
Articulated vehicles are the workhorses of freight transportation, and their autonomous navigation is challenging. Their physical characteristics and motion constraints pose significant challenges in manoeuvring these vehicles on narrow routes.
Maitrey Gramopadhye, Prakash Baskaran, Xiao Liu et al.
Effective human-robot collaboration in industrial settings requires robots to understand human intentions and assist with task planning, reducing workload.
Su Wang, Yaochen Li, Min Yang et al.
Most single-stage 3D object detectors complete different tasks with the same extracted features. Nevertheless, it is impossible to project features into a common space that is adaptive for all the tasks.
Nithin S. Kumar, Joshua Gaston, D. Caleb Rucker et al.
Soft actuators enable dexterous and compliant interaction, but closed-loop task-space control remains challenging due to strong nonlinearities, distributed deformation, and uncertainty in their dynamics.
Mahmud Hasan Saikot, Sydney Spiegel, Sudheera Akalanka Kariyawasam et al.
Robots that can change their morphologies and behaviors for different tasks and environments hold great promise for adaptable, multifunctional systems.
Jin Xu, Yu-Ping Chen, Ayanna Howard
This paper presents THRIVE (Therapeutic Humanoid Robot In Virtual Environment), an at-home rehabilitation platform that integrates a suite of virtual-reality upper-body rehabilitation games, a real-time camera-based motion-tracking system, and a socially interactive robot therapist.
Tao Huang, Ruofei Liu, Xuchen Tang et al.
Humanoid robots have recently demonstrated promising capabilities in real-world ball sports. However, achieving professional motion styles while maintaining strong task performance remains challenging.
Weiliang Huang, Huanrong Liu, Bob Zhang et al.
Reliable surgical planning requires models to anticipate not only how instruments will move, but also how the operative visual state will evolve together with such motion. Existing approaches typically treat future scene generation and instrument trajectory prediction as two separate tasks.
Xincheng Tang, Yiji Chen, Youhan Xie et al.
Door opening and traversal is a long-horizon loco-manipulation task that requires precise handle interaction and coordinated base-arm control. We present Video2DoorTraversal, a single-video real-to-sim-to-real framework for wheel-legged mobile manipulators.
Hisham Khalil, Neil Fernandes, Thomas M. Kwok et al.
Contact-rich manipulation requires precise tracking and mechanical compliance, where variable impedance control can improve robustness in task success, whereas static compliance cannot adapt to varying contact constraints.
G. Q. Bao Tran, Takanori Miyoshi, Ho Duc Tho
We study bilateral teleoperation between nonlinear, multi-DOF robotic manipulators in the presence of constant communication delays.
Zhe Li, Zhenzhe Zhang, Yangyang Wei et al.
Humanoid household tasks often require concurrent loco-manipulation, where the robot must move, adjust posture, maintain balance, and manipulate objects as a single coordinated behavior.
Rosanna Coccaro, Enrico Ferrentino, Antonio Parziale et al.
As human-robot interaction rapidly spreads in numerous fields, the subject of robot acceptance gains increasing importance.
Satoshi Yamamori, Koji Ishihara, Kentaro Minamikawa et al.
Instead of making simulation imitate every motor imperfection, this work shapes the physical actuator to follow the simulated reference.
Seok Joon Kim, Junho Lee, Federica Spinola et al.
Direct hand-driven teleoperation maps an operator's hand motion to robot end-effector commands at every frame, enabling precise control, but it requires constant monitoring and correction during approach, grasp, and placement, which can be slow and fatiguing.
Kaifeng Zhao, Mathis Petrovich, Haotian Zhang et al.
Generating realistic 3D human motions in real-time within interactive applications is key for animation, simulation, and humanoid robotics.
Aniol Civit, Antonio Andriella, Alba Martínez et al.
Frailty assessments are crucial to evaluate the risk of adverse events and the health and social care needs of older adults, yet their administration remains resource-intensive and typically relies on coarse clinical outcomes, such as task completion times, which may overlook biomechanical indicators of functional decline.
Mengfei Zhao, Dihong Huang, Yikai Tang et al.
Learning effective robot manipulation policies requires diverse, high-quality demonstrations, yet existing data pipelines are often difficult to scale because they rely on specialized hardware, centralized operators, or fixed task suites.
Qi Li, Xingyi Yang, Xinchao Wang
World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generation with future world prediction.
Zikui Cai, Kaushal Janga, Tan Dat Dao et al.
Embodied question answering (EQA) is traditionally evaluated under an episodic formulation, where agents solve each task independently and reset internal state between episodes.
Jonathan Rainer Lippert, Kai Ploeger, Abir Chowdhury et al.
Dynamic object exchange between humans and robots remains a challenging problem due to uncertainty in perception, timing, and contact-rich interaction.
Gil Lifshits, Igal Bilik, Gilad Katz
Coordinating autonomous vehicles at unsignalized intersections remains a critical challenge for multi-agent reinforcement learning (MARL) systems, which typically struggle with combinatorial action spaces, reliance on privileged information, or rigid agent designs.
Xinyao Li, Xialin He, Runpei Dong et al.
Keypoint tracking alone is insufficient for object interaction tasks such as sitting on a chair, wiping a board, or pushing furniture, where the robot can reach the correct pose without making meaningful physical contact with the object.
Hexian Ni, Tao Lu, Yinghao Cai
CoRe combines code-based rewards with learned visual preferences so that neither reward source has to capture the entire task alone.
Yunchao Yao, Zhuxiu Xu, Tianqi Zhang et al.
Building general-purpose dexterous manipulation policies requires benchmarks that go beyond isolated tasks to systematically evaluate policies across diverse interaction modes, sensory conditions, and robot embodiments.
Lifeng Zhuo, Wendi Chen, Han Xue et al.
In contact-rich manipulation, action multimodality and reactivity dominate different stages of a single episode. Before contact, multiple trajectories might be equally valid, making it important to preserve diverse action modes.
Shiyuan Yang, Borong Zhang, Jizheng Zhang et al.
We present FabriVLA, a lightweight Vision-Language-Action model for Precise Multi-Task Manipulation.
Xiaofan Lu, Kaiji Huang, Jiahui Chen et al.
Curved tactile fingertips for dexterous manipulation must resolve fine contact geometry, distinguish normal and tangential loads, and capture transient signals.
Chenyang Ma, Yue Yang, Radu Corcodel et al.
FurnitureVLA makes assembly progress an explicit prediction, helping a bimanual policy decide when to move to the next subtask.
Panagiotis Mermigkas, Argyris Manetas, Petros Maragos
Existing Gaussian-splatting-based monocular Simultaneous Localization and Mapping (SLAM) systems are either tailored to short sequences, are not real-time, or suffer from prohibitive GPU memory requirements, limiting their applicability in realistic, long-horizon scenarios.
Wenjie Liu, Yansha Deng
Vehicle coordination at unsignalized intersections relies on accurate real-time vehicle state acquisition and reliable command-and-control (C&C) signal delivery.
Wun Lam Yeung, Wenjun Liu, Yui Cheung Yu et al.
Bimanual object reorientation - picking an object, handing it over between two arms, and placing it in a desired target pose - is valuable when direct placement from the initial grasp is infeasible due to collisions, kinematic constraints, or poor final orientation.
Hongxin Zhang, Chunru Lin, Junyan Li et al.
Creating dynamic and physically realistic 4D worlds from natural language descriptions is both fascinating and challenging. Traditional computer graphics methods rely on manual creation, requiring extensive human effort to fine-tune materials, motions, and visual fidelity.
Chi Zhang, Penglin Cai, Ziheng Xi et al.
TTP transfers tactile experience from human demonstrations into robot policies for contact-sensitive manipulation.
Chuning Zhu, Eva Xu, Jose Barreiros et al.
Human decision-making is highly flexible -- some actions are taken immediately; others require longer deliberation.
Jaeho Shin, Maani Ghaffari, Yulun Tian
Modern robotic perception increasingly involves large-scale geometric optimization problems distributed across multiple robots or sessions. However, existing distributed solvers often depend on brittle hand tuning and primarily target rigid body pose graphs.
Cheng Siong Chin, Jianhua Zhang, Mohan Venkateshkumar
Autonomous systems inevitably age, yet their artificial intelligence typically assumes hardware remains in its original condition.
Qihang Zhang, Lin Li, Luyao Zhang et al.
The advent of video-action models offers a promising path for robot control. Nevertheless, we argue that repurposing video generative models designed for digital content creation is inherently inadequate for physical environments.
William English, Hao Zheng, Rickard Ewetz
This method checks a predicted action sequence for future collisions while the VLA is still generating it, rather than correcting only the next action.
Yuwan Liu, Hongze Yu, Song Liu et al.
Learning effective robot control policies on physical hardware is challenging due to costly data collection and the difficulty of reward specification.
Alan-Barsag Gazzaev, Alexey Garvilov, Sergey Muravyov
Can every robot in a swarm predict the same future collective state from only local observations and bandwidth-limited messages?
Lizhi Yang, Junheng Li, Aaron D. Ames
We present PAC-MAN, a perception-aware CBF-RL framework that couples control-barrier safety with deployment-realistic onboard sensing for whole-body humanoid dodgeball.
Zhoushun Yu, Xiaoyu Hu, Xiangyu Xu
Latent world models enable efficient planning by predicting future states in a compact representation space, but their performance depends critically on the quality of the learned latent distribution.
Yunfan Jiang, Yevgen Chebotar, Ruijie Zheng et al.
Recent robot foundation models operate with single-step or short-history visuomotor context.
Yu Qi, Zhang Ye, Xinyi Xu et al.
Compositional generalization is essential for robot to follow diverse instructions. However, pretrained policies are known to take shortcuts, deferring to salient cues rather than grounding language.
Weishuai Zeng, Kangning Yin, Xiaojie Niu et al.
Humanoid control requires natural whole-body coordination, precise real-time responses to control signals, and robust generalization across diverse environmental contexts, making it a cornerstone for generalist embodied agents.
Aditya Dutta, Joon-Seok Kim
Automated fulfillment warehouses must continuously assign and execute pickup-and-delivery work while avoiding congestion.
Xiaobei Zhao, Xingqi Lyu, Xin Chen et al.
Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an agent to follow a natural language instruction, predicting a sequence of low-level actions to navigate a robot from a starting point to a target location.
Jiabin Lou, Haopeng Wang, Yuanshuai Wang et al.
Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions.
Yuquan Xue, Le Xu, Zeyi Liu et al.
Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction beyond the states observed in demonstrations.
Tianyu Yang, Yiming Zeng, Wenzhe Cai et al.
Pretraining navigation diffusion policies rely on large-scale expert demonstrations. These data are typically generated by a fully-informed oracle planner suited to a single nominal robot.
Jiaxin Shi, Xidong Zhang, Fucai Zhu et al.
We propose a 3D-thinking-guided co-training framework that enables vision-language-action (VLA) models to perform 3D spatial reasoning implicitly during action prediction.
Arthur Allshire, Himanshu Gaurav Singh, Ritvik Singh et al.
We introduce ABC, a fully open-source stack for manipulation with behavior cloning. At its core is ABC-130K: the largest open-source teleoperation dataset to date, featuring 3,500 hours of data spanning over 130K episodes across 195 diverse tasks.
Junheng Li, Liang Wu, Sergio A. Esteban et al.
In humanoid motion control, model predictive control (MPC) offers physically grounded prediction and constraint handling, while reinforcement learning (RL) enables robust whole-body skills through large-scale simulation. However, using MPC inside RL often requires time-consuming problem construction or excessive training overhead, making such frameworks difficult to justify in practice. This work studies efficient training-time MPC guidance for humanoid locomotion and manipulation, termed MPC-RL. We introduce a centroidal-dynamics MPC reward formulation that leverages guidance from MPC trajectories in training time. To make this practical in massively parallel RL, we develop π^nMPC, a parallel-in-horizon and construction-free batched GPU MPC solver that operates directly on time-varying dynamics to avoid high memory usage and pre-compilation. Through a variety of comparative studies and hardware validations, we have found that MPC-RL achieves superior performance in locomotion and manipulation skills.
Jianli Sun, Bin Tian, Qiyao Zhang et al.
Aerial manipulation systems have long suffered from representation coupling in end-to-end control, as platform-level Unmanned Aerial Vehicle (UAV) movement and end-effector-level arm manipulation differ substantially in action scale, dynamics, and control objectives.
Jonathan Green, Jiaxu Xing, Nico Messikommer et al.
Autonomous drone racing is a fundamentally challenging regime for autonomous aerial robots, requiring time-optimal control while operating under persistent actuation saturation.
Yandong Wang, Jiaqian Yu, Xiongfeng Peng et al.
Vision-language-action (VLA) models show strong capabilities in single and dual-arm robotic manipulation. Prior works show coordinated bimanual behaviors can emerge from end-to-end learning, leveraging large vision-language backbones with continuous action prediction.
Yandong Wang, Jiaqian Yu, Xiongfeng Peng et al.
Vision-language-action (VLA) models show strong capabilities in single and dual-arm robotic manipulation. Prior works show coordinated bimanual behaviors can emerge from end-to-end learning, leveraging large vision-language backbones with continuous action prediction.
Mehmet Turan Yardımcı
Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy.
Alexey Zemtsov, Maxim Bobrin, Alexander Nikulin et al.
Offline goal-conditioned reinforcement learning requires both long-horizon reachability estimates and local action comparisons. Dual goal representations provide value fields that capture global goal reachability, but they do not directly specify which action should be preferred at a given state.
Wen Ye, Peiyan Li, Tingyu Yuan et al.
Recently, a few works have made early attempts to study test-time scaling for embodied tasks.
Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha et al.
Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose prohibitive computational burdens during downstream fine-tuning and real-time inference.
Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha et al.
Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose prohibitive computational burdens during downstream fine-tuning and real-time inference.
Arman Akbari, Ci Zhang, Arash Akbari et al.
World-action models (WAMs) jointly generate future video and robot actions through iterative diffusion, achieving strong performance on manipulation benchmarks but requiring tens of denoising steps, a cost that precludes real-time control.
Jianing Guo, Fangzheng Chen, Zihao Mao et al.
Flow matching has emerged as a standard paradigm for robotic manipulation owing to its strong expressive power for modelling complex, multimodal action distributions, alongside similar approaches like diffusion policy.
Jianing Guo, Fangzheng Chen, Zihao Mao et al.
Flow matching has emerged as a standard paradigm for robotic manipulation owing to its strong expressive power for modelling complex, multimodal action distributions, alongside similar approaches like diffusion policy.
Luca Zanatta, Grzegorz Malczyk, Kostas Alexis
World models, learned generative models that predict how an environment evolves, have become a promising tool for sample-efficient robot learning. Yet how robust they are to environmental variability remains poorly understood.
Zhihai Bi, Qiang Zhang, Guoyang Zhao et al.
Humanoid-Object Interaction (HOI) is a fundamental capability for humanoid robots, yet it remains challenging due to the tight coupling between dynamic balance and stable interaction with diverse objects.
Tianyi Xie, Haotian Zhang, Jinhyung Park et al.
Scaling humanoid loco-manipulation requires robot-compatible demonstrations across diverse objects, whole-body motions, and scene geometries, but teleoperation and motion capture are difficult to scale because each collection depends on physical setups, instrumented actors, and robot operation.
Haoxuan Han, Chen Chen, Linao Gong et al.
Humanoid robots have achieved strong locomotion capabilities, but reliable navigation on versatile terrains remains challenging because obstacle avoidance must be coordinated with dynamically feasible motion.
Hongwu Wang, Chenhao Yu, Youhao Hu et al.
HumanoidUMI moves demonstration collection off the robot, then translates human motion into executable humanoid skills.
Andy Tang, William Chen, Andrew Wagenmaker et al.
Generalist policies can learn a wide range of skills from diverse robot datasets. In order to solve or improve on challenging news tasks, we need a way to infer and invoke the appropriate actions from the policy's rich behavioral prior, especially when directly commanding the policy fails.
Yu Zhang, Kangyi Ji, Yongxiang Zou et al.
This paper presents an invertible neural network adapter for general robotic manipulation, designed to generate precise high-dimensional actions conditioned on multimodal observations, including visual, linguistic, and proprioceptive inputs, through a one-step denoising process.
Yu Zhang, Kangyi Ji, Yongxiang Zou et al.
This paper presents an invertible neural network adapter for general robotic manipulation, designed to generate precise high-dimensional actions conditioned on multimodal observations, including visual, linguistic, and proprioceptive inputs, through a one-step denoising process.
Tao Lin, Yuxin Du, Yiran Mao et al.
Vision-Language-Action (VLA) models are commonly pretrained on robot demonstrations by jointly mapping visual observations and language instructions to actions. However, dense visual-action supervision can dominate the comparatively sparse language-action signal.
Siheng Zhao, Yuanhang Zhang, Ziqi Lu et al.
Humanoid robots hold great promise for operating in human-centered environments, yet ladder climbing remains one of the most challenging tasks due to sparse footholds and handholds, complex whole-body coordination, and sensitivity to perception and control errors.
Zhu, Xinghao, Liu, Zixi, Jain, Shalin et al.
Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging.
Ilia Larchenko
I describe my solution to the LeHome Challenge 2026, an ICRA 2026 competition on bimanual garment folding. The system placed 1st of 62 teams in the online (simulation) round and 2nd in the real-world final. It improves a vision-language-action (VLA) policy with a reinforcement-learning loop.
Zuxing Lu, Ziang Zheng, Yao Lyu et al.
Building a general-purpose whole-body controller is essential for enabling diverse motion capabilities in humanoid robots across a wide range of downstream tasks, including locomotion and loco-manipulation.
Sizhe Yang, Juncheng Mu, Tianming Wei et al.
Robust robotic manipulation in the real world requires not only an understanding of the current observation, but also memory and dynamics modeling.
Sizhe Yang, Juncheng Mu, Tianming Wei et al.
Robust robotic manipulation in the real world requires not only an understanding of the current observation, but also memory and dynamics modeling.
Video
Jiye Lee, Yonghun Choi, Jungdam Won
Two-stage framework that enhances noisy multi-human object interaction (MHOI) data by generating plausible hand grasps and refining full-body motion via diffusion-based optimization.
Kinam Kim, Namiko Saito, Heecheol Kim et al.
Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-based policies remain brittle in precise physical interactions due to compounding execution errors; Can a reinforcement learning policy trained purely in simulation improve the robustness of real-world VLAs zero-shot?
Kinam Kim, Namiko Saito, Heecheol Kim et al.
Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-based policies remain brittle in precise physical interactions due to compounding execution errors; Can a reinforcement learning policy trained purely in simulation improve the robustness of real-world VLAs zero-shot?
Siqiao Huang, Kun-Ying Lee, Dongming Qiao et al.
Humanoid whole-body control has made significant progress in recent years, yet existing approaches remain limited to few-skill policies with heavy reward engineering, or motion trackers that are difficult to extend to new input modalities.
Junhao Shi, Zezheng Huai, Siyin Wang et al.
Building persistent embodied agents in unstructured environments demands unified orchestration of heterogeneous tools spanning both cyber (APIs, IoT) and physical (manipulation, navigation) domains, coupled with autonomous recovery from physical failures that inevitably arise over extended operation.
Arnav Balaji, Arpit Bahety, Sriniket Ambatipudi et al.
While robotic manipulation capabilities have advanced rapidly, physical safety remains a major barrier to deploying household robots: task success is insufficient if the robot damages itself or its surroundings.
Jonghoon Lee, Seong Hyeon Park, Byungwoo Jeon et al.
Vision-language-action (VLA) policies have shown strong potential for general-purpose manipulation, yet they often fail on novel, out-of-distribution objects whose appearance or geometry deviates from the training distribution.
Jonghoon Lee, Seong Hyeon Park, Byungwoo Jeon et al.
Vision-language-action (VLA) policies have shown strong potential for general-purpose manipulation, yet they often fail on novel, out-of-distribution objects whose appearance or geometry deviates from the training distribution.
Xiao Ren, Yuhui Yang, Zongbiao Weng et al.
Recent reinforcement learning approaches have shown great promise in improving humanoid motion tracking performance and achieving fall recovery under disturbances.
Ariel Herrera, Xueyang Kang, Atal Anil Kumar
Robotic manipulation of textiles remains challenging because continuous deformation and self-occlusions hinder the robust visual perception required to estimate the cloth's state.
Arunim Joarder, Arjun Bhardwaj, René Zurbrügg et al.
Tactile sensing provides direct measurements of contact interactions that are essential for robotic manipulation.
Arunim Joarder, Arjun Bhardwaj, René Zurbrügg et al.
Tactile sensing provides direct measurements of contact interactions that are essential for robotic manipulation.
Ralf Römer, Maximilian Seeliger, Saida Liu et al.
Quantifies epistemic uncertainty in flow-matching VLAs using velocity-field disagreement (VFD) across a small ensemble, enabling failure detection at deployment and sample-efficient active fine-tuning (SAVE).
Yuemin Mao, Uksang Yoo, Jean Oh et al.
Dexterous manipulation depends on contact events that are fast, local, and often visually occluded.
Jaehwi Jang, Zhaoyuan Gu, Alfred Cueva et al.
Whole-body humanoid manipulation of bulky, deformable, and shared-load objects requires distributed contact sensing and explicit force regulation, yet most imitation policies treat contact force only implicitly.
Yufei Jia, Zhanxiang Cao, Mingrui Yu et al.
Simulation-based RL for contemporary robot control is increasingly organized around GPU-resident simulation: physics, rollout collection, and learning are placed on a single GPU-centric execution path
Zuojin Tang, Haoyun Liu, Xinyuan Chang et al.
Vision-Language-Action (VLA) models map visual observations and language instructions to robot actions through learned latent representations.
Wenxuan Guo, Xiuwei Xu, Yichen Liu et al.
AwareVLN introduces selective self-aware reasoning for VLN agents, triggering explicit spatial and progress analysis only at uncertain waypoints to improve robustness and explainability.
Jiahe Pan, Stelian Coros, Jitendra Malik et al.
A primary bottleneck in contact-rich manipulation is the difficulty of collecting real-world data. Sim-to-real reinforcement learning offers a scalable alternative, but the simulation-reality gap prev
Zhongxi Chen, Yifan Han, Yanming Shao et al.
Vision-Language-Action (VLA) models have emerged as a promising paradigm for grounding visual-language understanding into real-world robotic manipulation. However, dexterous manipulation remains chall
Xingyu Wang, Pengxiang Ding, Jingkai Xu et al.
Recent advances in visuomotor policy learning have enabled robots to perform control directly from visual inputs.
Jusuk Lee, Seungjae Lee, Jonghun Shin et al.
Robot manipulation critically depends on perception that preserves the action-relevant aspects of a scene. Yet most robot learning pipelines are built upon visual encoders pre-trained for static recog
Christen Millerdurai, Shaoxiang Wang, Yaxu Xie et al.
Reconstructing the absolute 3D pose and shape of the hands from the user's viewpoint using a single head-mounted camera is crucial for practical egocentric interaction in AR/VR, telepresence, and hand-centric manipulation tasks, where sensing must remain compact and unobtrusive.
Pramod Pal, Shishir Kolathaya, Ashitava Ghosal
Quadruped robots are often designed with rigid feet to simplify control and maintain stable contact during locomotion.
Christos Ziakas, Alessandra Russo, Avishek Joey Bose
Generative policies based on expressive model classes, such as diffusion-models and flow matching, are well-suited to complex control problems with highly multimodal action distributions.
Wenxuan Guo, Ziyuan Li, Meng Zhang et al.
GesVLA augments standard VLA models with gesture awareness, enabling robots to interpret verbal instructions alongside human hand gestures for disambiguated manipulation.
Yiran Ling, Qing Lian, Jinghang Li et al.
In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied reasoning by allowing users to guide robot policies with explicit visual cues.
Xiaosong Jia, Bowen Yang, Zuhao Ge et al.
Vision-Language-Action (VLA) models aim for general robot learning by aligning action as a modality within powerful Vision-Language Models (VLMs). Existing VLAs rely on end-to-end supervision to implicitly enable the action decoding process to learn task-relevant features.
Zhuohang Li, Liqun Huang, Wei Xu et al.
Vision-Language-Action (VLA) models are prone to compounding errors in dexterous manipulation, where high-dimensional action spaces and contact-rich dynamics amplify small policy deviations over long horizons.
Qiuxuan Feng, Jiale Yu, Jiaming Liu et al.
World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics. Current WAMs generally follow two paradigms: generalizable but imprecise models learned from diverse data, or precise but specialized models fitted to specific tasks.
Shijie Lian, Bin Yu, Xiaopeng Lin et al.
Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators act with different short-horizon intents, task phases, or recent context.
Zhihao Cao, Qi Shao, Shuhao Zhai et al.
Collaborative photorealistic 3D reconstruction from multiple agents enables rapid large-scale scene capture for virtual production and cooperative multi-robot exploration.
Marco Coscoy, Zewei Zhou, Seth Z. Zhao et al.
Vehicle-to-Everything (V2X) communication has emerged as a promising paradigm for autonomous driving, enabling connected agents to share complementary perception information and negotiate with each other to benefit the final planning.
Yajie Li, Bozhou Zhang, Chun Gu et al.
Video foundation-models models offer a promising imagination mechanism for robot manipulation by predicting long-horizon future observations, but effectively exploiting these imagined futures for action execution remains challenging.
Sandeep Bajamahal, Lawrence Yunliang Chen, Toru Lin et al.
Bimanual coordination is essential for many real-world manipulation tasks, yet learning bimanual robot policies is limited by the scarcity of bimanual robots and datasets. Single-arm robots, however,
Jiaxu Wang, Junhao He, Jingkai Sun et al.
MoSA closes the real-to-sim gap for continuum robots by learning a residual stress field that captures anisotropic material behavior missed by standard simulators.
Sergey Arkhangelskiy
Real-world evaluation of vision-language-action (VLA) policies still rests on binary success rate at a fixed timeout with N <= 25 rollouts per condition, almost always without confidence intervals or
Zhen Sun, Yongjian Guo, Haoran Sun et al.
A lightweight runtime verification layer that preemptively prunes unsafe VLA and world-model actions before they reach robot hardware, eliminating collision and droppage failures.
Xinyu Guo, Bin Xie, Wei Chai et al.
Vision-Language-Action (VLA) models have shown promise for generalizable robot control but struggle when adapting to new domains while preserving prior capabilities.
Qiuyue Wang, Mingsheng Li, Jian Guan et al.
Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks,
Huashuo Lei, Wenxuan Song, Huarui Zhang et al.
Memory is a critical component of robotic intelligence, as robots must rely on past observations and actions to accomplish long-horizon tasks in partially observable environments.
Qiwei Li, Xicheng Gong, Xinghang Li et al.
Latent Action Models (LAMs) have emerged as an effective paradigm for handling heterogeneous datasets during Vision-Language-Action (VLA) model pretraining, offering a unified action space across embodiments.
Haechan Mark Bong, Giovanni Beltrame
Safe autonomous Uncrewed Aerial Vehicle (UAV) navigation in urban environments requires real-time path planning that avoids obstacles. MaxConvNet is a potential-field planner that leverages properties of Maxwell's equations to generate a path to the goal without local minima.
Chengyue Huang, Khang Vo Huynh, Sebastian Elbaum et al.
Robotic manipulation is typically evaluated by task success, but successful completion does not guarantee safe execution. Many rl failures are temporal: a robot may touch a clean surface after contamination or release an object before it is fully inside an enclosure.
Lee, Haegu, Kim, Yitaek, Sloth, Christoffer
Smoothed implicit contact dynamics enables gradient-based planning and control for contact-rich tasks without predefined mode sequences. However, safety-critical control remains challenging because implicit contact dynamics makes safety-filter design nontrivial.
Shutong Ding, Zejia Zhong, Zhongyi Wang et al.
Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion policies. Among these approaches, one representativ
Hoang-Dung Bui, Abhish Khanal, Raihan Islam Arnob et al.
SAP pairs aerial scouts with ground robots to gather environmental information ahead of time, reducing mission time by 40% through information-theoretic POMDP planning.
Yibo Liu, Stanko Oparnica, Simon Shewchun-Jakaitis et al.
Contact-rich manipulation is fundamental in robotics but poses significant challenges due to uncertainties in relative poses, such as misalignments and small clearances in peg-in-hole tasks.
Jonathan Spieler, Angel Villar-Corrales, Sven Behnke
Predictive world models enable agents to model scene dynamics and reason about the consequences of their actions.
Pengteng Li, Weiyu Guo, He Zhang et al.
SOMA introduces an explicit spatial memory framework that enables VLA models to track and manipulate objects even after they leave the camera's field of view.
Ismail Geles, Leonard Bauersfeld, Markus Wulfmeier et al.
The first demonstration of superhuman, safe, multi-agent drone racing using a MARL framework trained in simulation and transferred to real Crazyflie nano-drones.
Loizos Hadjiloizou, Rodrigo Pérez-Dattari, Noémie Jaquier
Formalizes cross-space symmetry compositions in robotics and derives equivariant network architectures that exploit multiple simultaneous symmetries for improved generalization.
Matthew M. Hong, Jesse Zhang, Anusha Nagabandi et al.
Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for downstream exploration.
Junjie Lu, Xinyao Qin, Yuhua Jiang et al.
Diffusion-based vision-language-action (VLA) models have emerged as strong priors for robotic manipulation, yet adapting them to real-world distributions remains challenging.
Yunheng Wang, Yuetong Fang, Taowen Wang et al.
Vision-and-Language Navigation (VLN) is a cornerstone of embodied intelligence.
Kai Xiong, Hongjie Fang, Lixin Yang et al.
Effectively handling the interplay between spatial perception and action generation remains a critical bottleneck in robotic manipulation.
