Robotics Research Hub

3D Euler-Angle Orientation Control for Two-Ray Fading Mitigation in Maritime Air-to-Sea Communications

Fri, 11 Sep 2026 00:00:00 GMT

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. This paper treats the full three...

3DThinkVLA: Endowing Vision-Language-Action Models with Latent 3D Priors via 3D-Thinking-Guided Co-training

Sun, 07 Jun 2026 00:00:00 GMT

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. Our core insight is that 3D geometry perception and 3D spatial reasoning are distinct capabilities that can be disentangled and ...

A Browser-Native Digital Test Range for Benchmarking 4D Ocean-Glider Planning Algorithms

Sun, 16 Aug 2026 00:00:00 GMT

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. We present a guided, installation-free browser-native digital test range that transforms a selected regi...

A Confidence-Aware Multimodal Fusion Framework for Industrial Human-Robot Collaboration

Thu, 10 Sep 2026 00:00:00 GMT

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. It embeds a conf...

A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms

Thu, 28 May 2026 00:00:00 GMT

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

A Low-Cost, Open Platform for End-to-End Autonomous Driving on a Miniature Ackermann Vehicle

Sun, 06 Sep 2026 00:00:00 GMT

This paper presents a low-cost, open experimental platform for research in end-to-end autonomous driving with miniature Ackermann vehicles. The platform combines a physical vehicle, a printed urban track, data collection tools, trajectory registration, and a Webots digital twin, enabling controll...

A Master-Salve Robot Manipulator for Needle-Based Teleoperation in MRI Chamber

Sun, 09 Aug 2026 00:00:00 GMT

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. Jointly, a digital master controller provides multimodal co...

A New Human-Likeness and Comfort Index for Robot Movements Along Prescribed Paths

Sun, 12 Jul 2026 00:00:00 GMT

As human-robot interaction rapidly spreads in numerous fields, the subject of robot acceptance gains increasing importance. Visual similarity to the human body, as occurs for humanoids, is generally not enough to ensure acceptance in physical interaction, as acceptance directly links to comfort a...

Scalable Behavior Cloning with Open Data, Training, and Evaluation

Thu, 25 Jun 2026 00:00:00 GMT

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. Furthermore, we open-source o...

Accelerating and Scaling MPC-Guided Reinforcement Learning for Humanoid Locomotion and Manipulation

Wed, 10 Jun 2026 00:00:00 GMT

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.

ACT: Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

Sat, 09 May 2026 00:00:00 GMT

ACT employs a transformer-based action chunking policy and temporal ensembling to perform precise bimanual manipulation on a $5k ALOHA robot setup.

Actuator Reality Shaping for Zero-Shot Sim-to-Real Robot Learning

Sun, 05 Jul 2026 00:00:00 GMT

Sim-to-real transfer in robot learning is often limited by discrepancies between the ideal actuator dynamics assumed during policy training and the nonlinear, hardware-dependent be...

Adaptation Needs in Robotic Systems: Assessing Behavior Trees and Their Enhancement

Tue, 08 Sep 2026 00:00:00 GMT

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. Behavior Trees (BTs) are widely used in robotic control architectures due to their ...

Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis

Sun, 06 Sep 2026 00:00:00 GMT

This paper proposes AdaRoboVLG, a task-adaptive Vision-Language-Grasp (VLG) framework that supports generalizable grasp synthesis across different robotic hands. Unlike existing VLG methods that tightly couple foundation models with end-to-end grasp policies, AdaRoboVLG learns an efficient genera...

Learning Agile Flight in the Wild

Sat, 09 May 2026 00:00:00 GMT

An end-to-end neural drone controller trained entirely in simulation flies acrobatic maneuvers in the real world with zero real-world fine-tuning, enabled by domain randomization and reinforcement learning.

AHEAD: Anticipatory Hand-Driven Teleoperation via Human Intent Prediction

Sun, 19 Jul 2026 00:00:00 GMT

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. For repetitive pick-and-place tasks, ...

AIR-VLA+: Decoupling Movement and Manipulation via Cascaded Dual-Action Decoders with Asymmetric MoE for Aerial Robots

Sun, 14 Jun 2026 00:00:00 GMT

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. In this paper, we propose AIR-VL...

ALAM: Algebraically Consistent Latent Transitions for Vision-Language-Action Models

Tue, 12 May 2026 00:00:00 GMT

Vision-Language-Action (VLA) models map visual observations and language instructions to robot actions through learned l...

ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

Sun, 12 Jul 2026 00:00:00 GMT

Generating realistic 3D human motions in real-time within interactive applications is key for animation, simulation, and humanoid robotics. While recent offline motion generation approaches offer precise control via text and kinematic constraints, they lack the inference speed required for intera...

Assessing Physical Frailty and Fall-Risk Indicators with Social Robots: An in situ Evaluation with Older Adults

Sun, 19 Jul 2026 00:00:00 GMT

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 indica...

Attention from Action, for Action: Emergent Visual Bottlenecks for Policy Learning

Sun, 16 Aug 2026 00:00:00 GMT

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. Label-free alternativ...

AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation

Sun, 24 May 2026 00:00:00 GMT

AwareVLN introduces selective self-aware reasoning for VLN agents, triggering explicit spatial and progress analysis only at uncertain waypoints to improve robustness and explainability.

AXIS: A Growable Community-Driven Data Engine for Scalable Robot Manipulation

Sun, 26 Jul 2026 00:00:00 GMT

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. We present AXIS, a growable community-driven data engine a...

BadWAM: When World-Action Models Dream Right but Act Wrong

Sun, 19 Jul 2026 00:00:00 GMT

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. This coupling is often viewed as a source of robustness, interpretability, and safet...

Berkeley Humanoid: A Low-Cost 3D-Printed Humanoid for Research

Sat, 09 May 2026 00:00:00 GMT

An open-source 3D-printed humanoid robot platform designed for reinforcement-learning based locomotion research with affordable hardware.

Beyond Binary: Sim-to-Real Dexterous Manipulation with Physics-Grounded Contact Representation

Wed, 27 May 2026 00:00:00 GMT

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

Beyond Episodic Evaluation: Memory Architectural Bottlenecks in Sequential Embodied Question Answering

Sun, 26 Jul 2026 00:00:00 GMT

Embodied question answering (EQA) is traditionally evaluated under an episodic formulation, where agents solve each task independently and reset internal state between episodes. However, real-world robots operate continuously and must accumulate, retain, and selectively reuse information acquired...

BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models

Thu, 28 May 2026 00:00:00 GMT

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

Bridging Performance and Generalization in Reinforcement Learning for Agile Flight

Thu, 25 Jun 2026 00:00:00 GMT

Autonomous drone racing is a fundamentally challenging regime for autonomous aerial robots, requiring time-optimal control while operating under persistent actuation saturation. While reinforcement learning (RL) has achieved human-level performance in this domain, current meth...

Can People Distinguish Human and AI Agency in Humanoid Teleoperation? A Preliminary Study of Agency Perception

Wed, 09 Sep 2026 00:00:00 GMT

Can people distinguish between human and AI agency in humanoid teleoperation? To explore this question, we developed \textit{Ghost-in-the-Loop}, a teleoperation framework that supports both human-operated and AI-generated control of a robot's voice, facial expressions, and gestures while maintain...

CAP: Continuously Adaptive Perception-Blind Humanoid Locomotion via Learned Denoising

Fri, 11 Sep 2026 00:00:00 GMT

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. Existing perceptive policies often assume that depth observations remain clean and in-distributio...

CARLAverse: A Highly Modular, Distributed, and Multimodal Framework for Human-in-the-Loop Simulation

Fri, 11 Sep 2026 00:00:00 GMT

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. While human-in-the-loop (HITL) simulators enable safe investigation of t...

Catalogue Photography as a Cold Start: Toward Deployable Carbide Burr Recognition

Sun, 06 Sep 2026 00:00:00 GMT

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. Automating this process with computer vision faces a critical cold-start constraint since no labelled imagery is availab...

Catch, Throw, Repeat: Planning for Human-Robot Partner Juggling

Sun, 19 Jul 2026 00:00:00 GMT

Dynamic object exchange between humans and robots remains a challenging problem due to uncertainty in perception, timing, and contact-rich interaction. Human-robot juggling represents a particularly demanding instance of this problem, requiring precise real-time coordination, predictive motion pl...

CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators

Sun, 30 Aug 2026 00:00:00 GMT

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. To bridge this gap, we introduce CLAP, a framework for...

CLIPort: What and Where Pathways for Robotic Manipulation

Sat, 09 May 2026 00:00:00 GMT

CLIPort fuses CLIP's semantic understanding with Transporter Networks' spatial precision to perform language-conditioned manipulation tasks like 'stack the red block on the blue block' with 2D pick-and-place affordances.

Co-VLA: Coordination-Aware Structured Action Modeling for Dual-Arm Vision-Language-Action Systems

Sun, 21 Jun 2026 00:00:00 GMT

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...

Co-VLA: Coordination-Aware Structured Action Modeling for Dual-Arm Vision-Language-Action Systems

Sun, 21 Jun 2026 00:00:00 GMT

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...

Collision Snapshot Guided Time-Reversed Safety-Critical Scenario Generation

Wed, 09 Sep 2026 00:00:00 GMT

The generation of safety-critical traffic scenarios is essential for training and evaluating autonomous vehicles. Prior approaches typically perturb the trajectories of existing agents in a traffic scenario using simplified adversarial objectives to induce safety-critical interactions, which can ...

Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections

Sun, 26 Jul 2026 00:00:00 GMT

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. We propose Master-Agent Proto-p...

ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models

Sun, 16 Aug 2026 00:00:00 GMT

Contact-rich manipulation failures are often detected only after the robot has committed to contact. This is especially limiting in wrist-camera setups: close gripper--object views help observe contact, but a poor approach may already push, miss, slip, or disturb the object before conventional de...

ContactMimic: Humanoid Object Interaction via Contact Control

Sun, 12 Jul 2026 00:00:00 GMT

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. We present CONTACTMIMIC, a learning framework that tracks e...

Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous Driving

Sun, 06 Sep 2026 00:00:00 GMT

Bridging the gap between the discrete reasoning of Vision-Language Models and the continuous, physics-constrained nature of autonomous driving remains a significant challenge. In this work, we introduce LaPla, a unified Vision-Language-Action (VLA) framework featuring latent-aligned planning to s...

Control-Informed Constraint Adaptation in Minimum-Time Trajectory Planning for Autonomous Racing

Mon, 17 Aug 2026 00:00:00 GMT

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. To guarantee safety, trajectory planners therefore restrict the...

CORAL: Curriculum-Optimized Reward Adaptation for LiDAR-Based Goal-Directed Urban Driving

Mon, 17 Aug 2026 00:00:00 GMT

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 t...

CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement Learning

Sun, 05 Jul 2026 00:00:00 GMT

Reward design remains a central challenge in reinforcement learning (RL). Hand-crafted rewards are often difficult to specify and may lead to suboptimal policies, while learned rew...

Corner Cases: Headland Coverage Path Planning for Autonomous Driving in Arable Farming

Sun, 06 Sep 2026 00:00:00 GMT

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. In the new method, the polygon c...

CougarTail & CUB: A General-Purpose Mast and Central Utility Board for Cylindrical Underwater Enclosures

Thu, 10 Sep 2026 00:00:00 GMT

Cylindrical watertight enclosures are widely used across various underwater systems, from unmanned underwater vehicles (UUVs), to remotely operated vehicles (ROVs), to various sensor platforms. However, electronics are typically built on rectangular PCBs arranged in horizontal stacks, which ineff...

Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation

Sun, 14 Jun 2026 00:00:00 GMT

Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy. A natural design choice is whether to use a single (unified) critic that estimates the combined value of all objectives, or separate (dual) critics with disjoint reward sign...

CrossDepth: Geometry-Constrained Attention for Generalizable Multi-View Surround Depth Estimation

Tue, 08 Sep 2026 00:00:00 GMT

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. Consequently, the depth of most pixels must be inferred from mon...

CUBic: Coordinated Unified Bimanual Perception and Control Framework

Sun, 17 May 2026 00:00:00 GMT

Recent advances in visuomotor policy learning have enabled robots to perform control directly from visual inputs. Yet, extending such end-to-end learning from single-arm to bimanual manipulation remains challenging due to the need for both independent perception and coordinated interaction between a...

DART-S: Reachability-Audited Active-Suspension Preconditioning for Off-Road Vehicle Jumps

Sun, 23 Aug 2026 00:00:00 GMT

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. To predi...

Decoding Task Progress from VLA Representations

Sun, 16 Aug 2026 00:00:00 GMT

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. Leveraging ideas from mechanistic interpretability, we...

DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation

Sun, 23 Aug 2026 00:00:00 GMT

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. Here we introduce DECOW...

Deformable Object Manipulation under Partial Observability via Real-Time Full-Shape Estimation

Thu, 10 Sep 2026 00:00:00 GMT

Manipulating deformable objects (DOs) is challenging due to their high-dimensional state space, underactuated dynamics, and partial observability. In this paper, we propose cRVAE, a lightweight conditional recurrent variational autoencoder that estimates the full DO state from only partial corner...

Deliberate Practice: Learning Robot Skills under a Budget

Sun, 16 Aug 2026 00:00:00 GMT

We consider the problem of autonomously learning robot skills under a limited practice budget for sequential tasks. We propose an active skill learning algorithm, \emph{Deliberate Practice (DP)}, that computes a provably \emph{budget-optimal} allocation---practicing skills that maximize expected ...

Design and Evaluation of a Touchscreen-Based Teleoperation Interface for Robotic Manipulators

Sun, 09 Aug 2026 00:00:00 GMT

Intuitive teleoperation interfaces are crucial for the safe and effective operation of robotic manipulators in challenging environments. In the nuclear industry, surface contact tasks such as swab sampling require precise path and force tracking, obstacle avoidance, and sustained operator attenti...

Development of a Humanoid Robot Prototype for Multimodal Human-Robot Interaction

Tue, 08 Sep 2026 00:00:00 GMT

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. The...

DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation

Sun, 12 Jul 2026 00:00:00 GMT

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. However, existing benchmarks remain limited in task and data diversity, embod...

Diffusion Policy: Visuomotor Policy Learning via Action Diffusion

Sat, 09 May 2026 00:00:00 GMT

A behavior cloning approach that models robot policies as conditional diffusion processes, enabling multimodal action distributions and smooth action sequences.

DIGIT: A Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation

Sat, 09 May 2026 00:00:00 GMT

An affordable, compact, high-resolution vision-based tactile sensor optimized for in-hand manipulation with real-time fingertip deformation sensing.

Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World

Sat, 09 May 2026 00:00:00 GMT

Introduced domain randomization for vision-based manipulation: randomize simulation textures, lighting, and camera parameters so that the real world looks like just another variation.

DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation

Sun, 16 Aug 2026 00:00:00 GMT

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. Yet realism al...

DROID: A Large-Scale In-the-Wild Robot Manipulation Dataset

Sat, 09 May 2026 00:00:00 GMT

A 350-hour dataset of diverse real-world robot manipulation across 22 robots in 71 scenes, designed to train scalable and generalist imitation learning policies.

Dual Advantage Fields

Sun, 07 Jun 2026 00:00:00 GMT

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. We...

DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation

Thu, 28 May 2026 00:00:00 GMT

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

Dynamic System Emulation: Fixed Wing Dynamics on a Multicopter

Wed, 09 Sep 2026 00:00:00 GMT

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. The goal is to provide an operationally simple platform for training and simulation that avoids the aerodynamic constraints of fixed-wing vehi...

DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation

Sun, 09 Aug 2026 00:00:00 GMT

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. First, they underuse dynamics priors shared across diverse v...

E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation

Thu, 25 Jun 2026 00:00:00 GMT

Recently, a few works have made early attempts to study test-time scaling for embodied tasks. However, two major challenges remain unsolved: (1) reasoning can effectively improve the performance of the policy, but its scaling mechanism has seldom been studied; (2) historical i...

Effect of Twisted-Yarn Architecture on Pressure and Proximity Sensing Characteristics of Textile Capacitive Sensors for Robotic Skin

Mon, 17 Aug 2026 00:00:00 GMT

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. This work presents a textile c...

EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera

Tue, 12 May 2026 00:00:00 GMT

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...

Embodied Scene Rearrangement Planning

Sun, 30 Aug 2026 00:00:00 GMT

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. Unlike prior rearrangement tasks, ESRP precludes global s...

Energy-Efficient Quadruped Locomotion with Compliant Feet

Sun, 17 May 2026 00:00:00 GMT

Quadruped robots are often designed with rigid feet to simplify control and maintain stable contact during locomotion. While this approach is straightforward, it limits the ability of the legs to absorb impact forces and reuse stored elastic energy, leading to higher energy expenditure during locomo...

Ensuring Safe Physical AI in Urban Mobility via Hazard-Informed Synthesized Envelopes

Mon, 17 Aug 2026 00:00:00 GMT

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. Rather ...

ErgoSurf: Ergodic Control for the Coverage of Unknown Surfaces

Sun, 09 Aug 2026 00:00:00 GMT

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. Ergodic control generates trajectories that spend time at a location proportional to a desired, task-specific spat...

Eureka: Human-Level Reward Design via Coding Large Language Models

Sat, 09 May 2026 00:00:00 GMT

Eureka uses GPT-4 to write reward functions for RL environments, achieving human-level reward design on 29 tasks and enabling zero-shot sim-to-real transfer on Shadow Hand dexterous manipulation.

Evidence-Gated Task and Motion Planning with Vision-Language Models

Sun, 23 Aug 2026 00:00:00 GMT

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. In such cases, approaches that combine Vi...

EVPeriscope: Extended Perception across Aerial and Ground Vehicles with Event-based Propeller Tracking

Sat, 12 Sep 2026 00:00:00 GMT

Reliable relative localization between aerial and ground robots is a key requirement for tightly coordinated heterogeneous teams. This can be difficult to do using conventional frame-based cameras and fiducial markers because they are sensitive to motion blur, lighting variations, and payload con...

Expected Free Energy-based Informative Path Planning for Robotic Mars Exploration

Mon, 17 Aug 2026 00:00:00 GMT

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 measure...

FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich Manipulation

Sun, 02 Aug 2026 00:00:00 GMT

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. After contact, geometric constraints and force limits narrow the sol...

FabriVLA: A Lightweight Vision-Language-Action Model for Precise Multi-Task Manipulation

Sun, 12 Jul 2026 00:00:00 GMT

We present FabriVLA, a lightweight Vision-Language-Action model for Precise Multi-Task Manipulation. FabriVLA combines an InternVL3.5 vision-language backbone with a flow-matching action head featuring gated self-attention across action tokens and shallow VLM layer fusion for enriched spatial con...

FARM: Reading Failure Signals from the Internal Predictive States of a Frozen Robotic World Model

Fri, 11 Sep 2026 00:00:00 GMT

Reliable robot deployment requires online failure monitoring, yet existing monitors mainly derive risk from proxy signals or train dedicated monitoring components. We ask whether the internal predictive states of a frozen pretrained robotic world model already contain directly decodable failure i...

FAST-LIO2: Fast Direct LiDAR-Inertial Odometry

Sat, 09 May 2026 00:00:00 GMT

A tightly-coupled LiDAR-inertial odometry system with incremental kd-tree mapping, enabling real-time state estimation for UAVs and mobile robots.

FasTac: A Curved Multispectral Vision-Based Tactile Sensor for High-Speed High-Precision 3D Shape and Force Perception

Sun, 02 Aug 2026 00:00:00 GMT

Curved tactile fingertips for dexterous manipulation must resolve fine contact geometry, distinguish normal and tangential loads, and capture transient signals. Existing curved vision-based tactile sensors struggle to combine accurate 3D reconstruction, three-axis force estimation, and high-speed...

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

Sun, 21 Jun 2026 00:00:00 GMT

Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose pro...

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

Sun, 21 Jun 2026 00:00:00 GMT

Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose pro...

FIRE-LIVWO: Robust LiDAR-Inertial-Visual-Wheel Odometry via Failure-Immune mmWave Radar Enhancement

Tue, 08 Sep 2026 00:00:00 GMT

Achieving robust SLAM in large-scale underground coal mines with complex structures and severe degeneracies remains highly challenging. Dense smoke and dust cause substantial loss of visual information and degrade LiDAR point-cloud features, while long, self-similar corridors induce geometric deg...

Flash-WAM: Modality-Aware Distillation for World Action Models

Sun, 07 Jun 2026 00:00:00 GMT

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. Step distillation has emerged as the natural remedy, but off...

FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference

Sun, 30 Aug 2026 00:00:00 GMT

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. This challenge is particularly pronounced in flow-matching-based VLA models, where action de...

Aligning Flow Map Policies with Optimal Q-Guidance

Tue, 12 May 2026 00:00:00 GMT

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. Their expressivity, however, comes at a significant inference cost:...

FolDeX: A Physical-World Benchmark for Long-Horizon Robotic Manipulation of Deformable Objects

Thu, 10 Sep 2026 00:00:00 GMT

Embodied AI, including vision-language-action and world-action models, must operate reliably in the physical world. Yet methods that perform well in simulation can degrade substantially on real robots, especially in long-horizon deformable-object manipulation, where policies must track changing s...

Formation Matrix and Energy-based Control of Multi-Agent Systems

Sun, 06 Sep 2026 00:00:00 GMT

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. Th...

Frame-Coded Legged Locomotion over Noisy Terrain

Thu, 10 Sep 2026 00:00:00 GMT

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. Tha...

Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation

Sun, 21 Jun 2026 00:00:00 GMT

Flow matching has emerged as a standard paradigm for robotic manipulation owing to its strong expressive power for modelling complex, multimodal action distributions, alongside sim...

Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation

Sun, 21 Jun 2026 00:00:00 GMT

Flow matching has emerged as a standard paradigm for robotic manipulation owing to its strong expressive power for modelling complex, multimodal action distributions, alongside sim...

FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model

Sun, 05 Jul 2026 00:00:00 GMT

Current work on robot furniture assembly mostly focuses on toy-scale settings or single-arm manipulation. We introduce FurnitureVLA, the first systematic study of real-scale bimanu...

Generalization of World Models under Environmental Variability for Vision-based Quadrotor Navigation

Sun, 07 Jun 2026 00:00:00 GMT

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. To address this, we conduct a systematic study using vision-based quadrot...

GenHOI: Contact-Aware Humanoid-Object Interaction by Imitating Generated Videos without Task-Specific Training

Sun, 14 Jun 2026 00:00:00 GMT

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. Existing methods often require time-consuming task-specific policy training or rely on rigid tr...

GeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual Actions

Sun, 09 Aug 2026 00:00:00 GMT

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. Action-conditioned world models offer a promising alternative, b...

GesVLA: Gesture-Aware Vision-Language-Action Model

Sun, 24 May 2026 00:00:00 GMT

GesVLA augments standard VLA models with gesture awareness, enabling robots to interpret verbal instructions alongside human hand gestures for disambiguated manipulation.

GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic Manipulation

Sun, 06 Sep 2026 00:00:00 GMT

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. We call th...

GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition

Sun, 26 Jul 2026 00:00:00 GMT

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. To address this, we pr...

Goal-Oriented Semantic Communication for Distributed ISAC-Enabled Vehicle Coordination

Sun, 19 Jul 2026 00:00:00 GMT

Vehicle coordination at unsignalized intersections relies on accurate real-time vehicle state acquisition and reliable command-and-control (C&C) signal delivery. However, existing studies typically treat sensing, communication, and control separately, which may lead to redundant transmissions, ou...

GR00T N1: An Open Foundation Model for Generalist Humanoid Robots

Fri, 11 Sep 2026 00:00:00 GMT

General-purpose robots need a versatile body and an intelligent mind. Recent advancements in humanoid robots have shown great promise as a hardware platform for building generalist autonomy in the human world. A robot foundation model, trained on massive and diverse data sources, is essential for...

GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors

Sun, 07 Jun 2026 00:00:00 GMT

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. We p...

Grasp, Handover, Rotate: Bimanual Object Reorientation via Compositional Diffusion and Energy-Based Optimization

Sun, 26 Jul 2026 00:00:00 GMT

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. However, achieving this under ...

GS-Agent: Creating 4D Physical Worlds With Generative Simulation

Sun, 26 Jul 2026 00:00:00 GMT

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. Recent advances in gene...

Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models

Sun, 17 May 2026 00:00:00 GMT

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. Existing VLA models learn a direct "Sense-to-Act" mapping from multimod...

GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization

Tue, 12 May 2026 00:00:00 GMT

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...

GuideWalk: Learning Unified Autonomous Navigation and Locomotion for Humanoid Robots across Versatile Terrains

Sun, 14 Jun 2026 00:00:00 GMT

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. In this work, we present GuideWalk, a unified end-to-end framework that integrates traversa...

Gymnasium: A Standard Interface for Reinforcement Learning Environments

Sat, 09 May 2026 00:00:00 GMT

Gymnasium is the maintained successor to OpenAI Gym, providing a standardized API for RL environments with 100+ built-in tasks, vectorized parallel execution, and native support for physics engines like MuJoCo, PyBullet, and IsaacGym.

Hand-in-the-Loop: Improving Dexterous VLA via Seamless Interventional Correction

Sun, 17 May 2026 00:00:00 GMT

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. While Interactive Imitation Learning (IIL) can refine policies through human takeover data...

HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models

Tue, 12 May 2026 00:00:00 GMT

World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics. Current...

HaWMPO: Hallucination-Aware World Model-based Policy Optimization for Generalist Robot Policy

Fri, 11 Sep 2026 00:00:00 GMT

Generalist robot policies have demonstrated strong generalization across robotic manipulation tasks, yet their success rates remain limited in com- plex long-horizon scenarios. Recent methods improve Visual-Language-Action (VLA) policies through online reinforcement learning on real robots, but s...

Stretch: A Small, Capable, and Affordable Mobile Manipulator

Sat, 09 May 2026 00:00:00 GMT

A low-cost mobile manipulator designed for indoor home and office environments, with a large open-source ecosystem and teleoperation-based data collection.

Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation

Sun, 05 Jul 2026 00:00:00 GMT

As an essential modality for dexterous and contact-rich tasks, tactile sensing provides precise force feedback that cannot be reliably inferred from vision. However, limited by har...

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer

Sat, 09 May 2026 00:00:00 GMT

An Isaac-Gym-based training framework for humanoid locomotion that enables zero-shot sim-to-real transfer on XBot-L/XBot-S robots via domain randomization.

HumanoidUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation

Thu, 25 Jun 2026 00:00:00 GMT

High-quality demonstration data are essential for humanoid robot skill learning, especially for whole-body behaviors that require coordinated perception, locomotion, and manipulation. Existing data-collection methods largely rely on robot teleoperation, which is constrained by...

HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark

Sun, 16 Aug 2026 00:00:00 GMT

Humanoid motion tracking is central to teleoperation and whole-body imitation, yet evaluation often disagrees with what people perceive in videos. Kinematic errors average per-frame pose differences but miss the physical artifacts that matter most, particularly unstable support and incorrect cont...

iGibson: Interactive Gibson Benchmark for Real-World Navigation and Manipulation

Sat, 09 May 2026 00:00:00 GMT

iGibson is a photorealistic, physics-based indoor simulation platform with 15 interactive scenes, 500+ object categories, and GPU-accelerated rendering, enabling RL and VLA training for mobile manipulation and embodied AI.

Improving Robotic Generalist Policies via Flow Reversal Steering

Sun, 14 Jun 2026 00:00:00 GMT

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. We focus ...

IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation

Sun, 17 May 2026 00:00:00 GMT

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. Existing frame-conditioned VLA policies infer each chunk from the current o...

Invertible Neural Network Adapter for One-Step Flow Matching in Robot Manipulation

Sun, 21 Jun 2026 00:00:00 GMT

This paper presents an invertible neural network adapter for general robotic manipulation, designed to generate precise high-dimensional actions conditioned on multimodal observati...

Invertible Neural Network Adapter for One-Step Flow Matching in Robot Manipulation

Sun, 21 Jun 2026 00:00:00 GMT

This paper presents an invertible neural network adapter for general robotic manipulation, designed to generate precise high-dimensional actions conditioned on multimodal observati...

Isaac Gym: High Performance GPU-Based Physics Simulation for Robot Learning

Sat, 09 May 2026 00:00:00 GMT

A GPU-accelerated physics simulation framework that enables thousands of RL environments to run in parallel on a single GPU, eliminating CPU-GPU transfer bottlenecks.

JEPA Policy: Diffusion-Free Imitation Learning via Paired Action and Future Representation Prediction

Fri, 11 Sep 2026 00:00:00 GMT

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. Act...

Knowledge-Guided Hierarchical Policy Learning for High-Precision Cylindrical Assembly under Tight Tolerances

Wed, 09 Sep 2026 00:00:00 GMT

A hybrid hierarchical learning framework is proposed to achieve high-precision assembly of 170mm cylindrical components with tolerance of 0.1mm. The lower-level network integrates expert experience through Behavior Cloning (BC), giving the robot human-like intuition, and incorporates the Twin Del...

LA4VLA: Learning to Act without Seeing via Language-Action Pretraining

Thu, 25 Jun 2026 00:00:00 GMT

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. As a result, ...

LadderMan: Learning Humanoid Perceptive Ladder Climbing

Sun, 07 Jun 2026 00:00:00 GMT

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. We present extbf{LadderMan}, a un...

LANTERN: A Closed-Loop Benchmark for VLM-Based Cooperative Driving with Temporally Grounded Warnings

Wed, 09 Sep 2026 00:00:00 GMT

We present LANTERN, a closed-loop benchmark for temporally grounded cooperative warnings. LANTERN separates warning onset, hazard onset, warning termination, and post-hazard recovery, and evaluates each physical event under matched warning and no-warning executions so that the warning's contribut...

Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference

Sun, 12 Jul 2026 00:00:00 GMT

Human decision-making is highly flexible -- some actions are taken immediately; others require longer deliberation. Language models have exhibited a similar capacity for adaptive "reasoning." However, transferring this capability to continuous control policies has been challenging, as directly re...

Learning Adaptive Solvers for Distributed Factor Graph Optimization on Matrix Lie Groups

Sun, 12 Jul 2026 00:00:00 GMT

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. To address this, we present DeepCORD, ...

Learning Agent-based Model Predictive Control for Holistic Vehicle Performance

Sat, 12 Sep 2026 00:00:00 GMT

Agent-based model predictive control (AMPC) has recently been proposed as a distributed scheme that collaborates with all agents to achieve optimal holistic performance. However, its optimality highly depends on the prediction accuracy that requires all agents or their contributions to be known, ...

Learning Terrain-Adaptive Humanoid Locomotion on Granular Terrain

Thu, 10 Sep 2026 00:00:00 GMT

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....

Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)

Thu, 25 Jun 2026 00:00:00 GMT

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...

Legged Gym: A Framework for Massively Parallel Reinforcement Learning of Legged Locomotion

Sat, 09 May 2026 00:00:00 GMT

Legged Gym is an open-source training framework built on NVIDIA Isaac Gym that enables massively parallel deep RL for legged robot locomotion, achieving policy training times of minutes rather than days.

LeRobot: A Library for Real-World Robot Learning

Sat, 09 May 2026 00:00:00 GMT

Hugging Face's LeRobot is an open-source PyTorch framework providing pretrained models, datasets, and training scripts for imitation and reinforcement learning on real robots, lowering the entry barrier to robot learning.

M3imic: Learning a Versatile Whole-Body Controller for Multimodal Motion Mimicking

Sun, 07 Jun 2026 00:00:00 GMT

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. Different tasks rely on distinct motion reference modalities: locomotion primarily depends on...

Machines that know they are aging: a framework for hardware-aware autonomous intelligence

Sun, 02 Aug 2026 00:00:00 GMT

Autonomous systems inevitably age, yet their artificial intelligence typically assumes hardware remains in its original condition. Batteries degrade, sensors drift, processors accumulate timing errors, and memory reliability declines, creating a growing mismatch between assumed and actual capabil...

MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction

Tue, 12 May 2026 00:00:00 GMT

Multi-agent simultaneous localization and mapping (SLAM) enables collaborative 3D reconstruction. This paper introduces ...

ManiSkill: A Unified Benchmark for Generalizable Manipulation Skills

Sat, 09 May 2026 00:00:00 GMT

ManiSkill is a GPU-parallelized robotics simulation benchmark with 20+ manipulation tasks, PartNet-Mobility assets, and unified observation/action spaces, supporting RL, IL, and VLA training at millions of steps per hour.

Marine Autonomous Vehicle Fleet Scheduling to Maximise Scientific Impact

Sun, 30 Aug 2026 00:00:00 GMT

The marine science community increasingly relies on Marine Autonomous Vehicles (MAVs) to collect the critical environmental data required to understand global ocean systems. However, as these operations scale, manually routing and planning large autonomous fleets becomes exponentially complex and...

MDrive: Benchmarking Closed-Loop Cooperative Driving for End-to-End Multi-agent Systems

Tue, 12 May 2026 00:00:00 GMT

Multi-agent autonomous driving systems require coordination among vehicles to navigate complex traffic scenarios safely ...

Memory as Plans: World-Action Modeling with Memory-Grounded Planning

Fri, 11 Sep 2026 00:00:00 GMT

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. Existing memory mechanisms often rely on language summaries, growing visual windows, or their...

MemoryWAM: Efficient World Action Modeling with Persistent Memory

Sun, 21 Jun 2026 00:00:00 GMT

Robust robotic manipulation in the real world requires not only an understanding of the current observation, but also memory and dynamics modeling. World action models (WAMs) posse...

MemoryWAM: Efficient World Action Modeling with Persistent Memory

Sun, 21 Jun 2026 00:00:00 GMT

Robust robotic manipulation in the real world requires not only an understanding of the current observation, but also memory and dynamics modeling. World action models (WAMs) posse...

Mind the Context: Continual Learning of Socially Appropriate Robot Actions via Environmental-Social Disentanglement

Sun, 16 Aug 2026 00:00:00 GMT

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. Because such norms and environments cannot all be ...

MOCHI: Motion Enhancement of Collaborative Human-object Interactions

Wed, 05 Aug 2026 00:00:00 GMT

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.

From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation

Tue, 12 May 2026 00:00:00 GMT

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. Existing approaches...

MonoDuo: Using One Robot Arm to Learn Bimanual Policies

Thu, 28 May 2026 00:00:00 GMT

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,

MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics

Sun, 24 May 2026 00:00:00 GMT

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.

Native Video-Action Pretraining for Generalizable Robot Control

Sun, 12 Jul 2026 00:00:00 GMT

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. To bridge this gap, we present LingBot-VA 2.0, a video-action foun...

Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching

Sun, 05 Jul 2026 00:00:00 GMT

Vision-Language-Action (VLA) models have demonstrated promising generalization capabilities across robotic manipulation tasks, yet their real-world deployment remains limited by th...

Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement

Sun, 21 Jun 2026 00:00:00 GMT

Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-based policies remain brittle in precise physical interactions du...

Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement

Sun, 21 Jun 2026 00:00:00 GMT

Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-based policies remain brittle in precise physical interactions du...

Octo: An Open-Source Generalist Robot Policy

Sat, 09 May 2026 00:00:00 GMT

Octo is a large open-source transformer-based generalist robot policy trained on 800k trajectories, supporting language-conditioned and goal-image-conditioned control across 9 robotic platforms with efficient fine-tuning on consumer GPUs.

Odometer-Agnostic Drift Correction Using OpenStreetMap Lane Geometry

Thu, 10 Sep 2026 00:00:00 GMT

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. Existing map-assisted methods can reduce drift, but often depend on dense maps, sensor-specific processing, o...

OK-Robot: Open-Ended Object Manipulation with Pretrained Vision-Language Models

Sat, 09 May 2026 00:00:00 GMT

OK-Robot uses off-the-shelf VLMs (CLIP, OWL-ViT) and LLMs (GPT-4) to perform open-ended object manipulation in unseen homes without any training, achieving 58% success on real-world pick-and-place tasks.

OMG: Omni-Modal Motion Generation for Generalist Humanoid Control

Sun, 14 Jun 2026 00:00:00 GMT

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. We argue that the key to general-purpose humanoid control is...

Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy

Thu, 25 Jun 2026 00:00:00 GMT

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 ...

One Demonstration Is Enough for Real-World Robotic Reinforcement Learning

Sun, 05 Jul 2026 00:00:00 GMT

Learning effective robot control policies on physical hardware is challenging due to costly data collection and the difficulty of reward specification. Prior work has incorporated ...

One Future, Every Robot: Label-Efficient Collective-State Prediction with Decentralized JEPA

Sun, 02 Aug 2026 00:00:00 GMT

Can every robot in a swarm predict the same future collective state from only local observations and bandwidth-limited messages? We formulate this as decentralized shared-state prediction and introduce Collective-State JEPA (CS-JEPA), a recurrent joint-embedding predictive architecture whose outp...

OopsieVerse: A Safety Benchmark with Damage-Aware Simulation for Robot Manipulation

Sun, 05 Jul 2026 00:00:00 GMT

While robotic manipulation capabilities have advanced rapidly, physical safety remains a major barrier to deploying household robots: task success is insufficient if the robot dama...

Open X-Embodiment: Robotic Learning Datasets and RT-X Models

Sat, 09 May 2026 00:00:00 GMT

The largest collaborative robot learning dataset ever assembled, spanning 22 robots from 21 institutions, enabling training of generalist RT-X policies that exhibit positive cross-embodiment transfer.

π0: A Vision-Language-Action Flow Model for General Robot Control

Sat, 09 May 2026 00:00:00 GMT

π0 is a 3.5B-parameter VLA flow model from Physical Intelligence that achieves state-of-the-art general robot manipulation by mixing online RL with high-quality human demonstrations, available as an open-source PyTorch implementation.

OpenVLA: An Open-Source Vision-Language-Action Model

Sat, 09 May 2026 00:00:00 GMT

A 7B-parameter open-source Vision-Language-Action model pre-trained on 970k real-world robot demonstrations, achieving strong generalization across robots and tasks.

ORCH: Organizational Principles Enable Collective Intelligence in Embodied AI

Sat, 12 Sep 2026 00:00:00 GMT

Collective intelligence depends not only on the capabilities of individual members, but also on how those members are organized. Yet artificial multi-agent systems are typically assembled using fixed organizational structures, even when the physical tasks they perform impose fundamentally differe...

OVMAN: A Task and Benchmark for Open-Vocabulary Motion-Aware Navigation

Wed, 09 Sep 2026 00:00:00 GMT

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. None of them can express go to the chair that was moved or go to where the vase used t...

PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball

Sun, 02 Aug 2026 00:00:00 GMT

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. The deployed policy sees the ball only as segmentation-masked depth from a head-mounted camera, while training-time CBF guidance...

PhAIL: A Real-Robot VLA Benchmark and Distributional Methodology

Thu, 28 May 2026 00:00:00 GMT

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

Planning-Oriented End-to-End Autonomous Driving: Architectures, Evaluation, and Emerging Paradigms

Sun, 23 Aug 2026 00:00:00 GMT

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. This survey reviews this transition across behavior cloning, conditional imi...

Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation

Sun, 21 Jun 2026 00:00:00 GMT

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 ge...

Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation

Sun, 21 Jun 2026 00:00:00 GMT

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 ge...

Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts

Sun, 24 May 2026 00:00:00 GMT

A lightweight runtime verification layer that preemptively prunes unsafe VLA and world-model actions before they reach robot hardware, eliminating collision and droppage failures.

PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models

Tue, 12 May 2026 00:00:00 GMT

Vision-Language-Action (VLA) models have shown promise for generalizable robot control but struggle when adapting to new...

QQWorld: Quantile-Quantile Matching for World Model Regularization

Sun, 02 Aug 2026 00:00:00 GMT

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. LeWorldModel (LeWM) regularizes its latents toward an isotropic Gaussian using the Epps-Pulley (...

Quasi-static analysis of passive stability in a novel underactuated multi-finger hand

Fri, 11 Sep 2026 00:00:00 GMT

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. This paper introduces a quasi-static analytical approach to assess passive stability in underactua...

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Thu, 28 May 2026 00:00:00 GMT

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,

Rapid Learning of Dexterous In-Hand Pen Writing through Real-Time Jacobian Estimation

Sat, 12 Sep 2026 00:00:00 GMT

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. Mode...

Reflex: Enabling Fast and Predictive Vision-Language-Action Models for Reaction-Critical Manipulation

Mon, 17 Aug 2026 00:00:00 GMT

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. To address this gap, we present ReflexBench, a ben...

Reflex-Informed Neuromuscular Reinforcement Learning for Muscle-Driven Locomotion

Sat, 12 Sep 2026 00:00:00 GMT

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. To address this limitation...

RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark

Tue, 12 May 2026 00:00:00 GMT

Long-horizon robotic tasks require agents to remember and reason about past observations and actions. This paper present...

RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?

Tue, 08 Sep 2026 00:00:00 GMT

Vision-Language-Action (VLA) models have shown promising progress in language-conditioned robotic manipulation. However, existing datasets and benchmarks mainly evaluate task completion under predefined settings, offering limited insight into model reasoning under increasing spatial and procedura...

Robot Learning from Human Demonstrations: Handwritten Alphabet Trajectories and Human-Likeness Evaluation

Sun, 09 Aug 2026 00:00:00 GMT

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. The resulting human-like robot motion is recognised as a key factor ...

RoboTTT: Context Scaling for Robot Policies

Sun, 19 Jul 2026 00:00:00 GMT

Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-Training Robot Policies (RoboTTT), a robot model and training recipe that scale visuomotor context to 8K timesteps, three orders of magnitude beyond state-of-the-art policies, witho...

RotVLA: Rotational Latent Action for Vision-Language-Action Model

Sun, 17 May 2026 00:00:00 GMT

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. However, existing LAMs often rely on discrete quantization encode and decode pipelines, whi...

RSL-RL: A Fast and Flexible Reinforcement Learning Library for Legged Robots

Sat, 09 May 2026 00:00:00 GMT

RSL-RL is a lightweight, high-performance PyTorch library implementing PPO tailored for locomotion. Used as the default RL backend in Legged Gym, it enables training thousands of agents in parallel on GPU.

RT-1: Robotics Transformer for Real-World Control at Scale

Sat, 09 May 2026 00:00:00 GMT

RT-1 is a 35M-parameter transformer trained on 130K robot demonstrations that generalizes to new tasks, objects, and environments, forming the foundation for Google's RT-2 and RT-X line of VLA models.

RT-1: Robotics Transformer for Real-World Control at Scale

Sat, 09 May 2026 00:00:00 GMT

A large transformer model trained on 130k episodes of real robot manipulation to output discretized arm-and-gripper actions from RGB images and natural language instructions.

RT-2: Vision-Language-Action Models That Generalize to Novel Tasks

Sat, 09 May 2026 00:00:00 GMT

Google DeepMind's VLA model combining a vision-language foundation model with robot action outputs, showing emergent generalization to novel objects, backgrounds, and semantic instructions far beyond training data.

Safe Aerial 3D Path Planning for Autonomous UAVs using Magnetic Potential Fields

Tue, 12 May 2026 00:00:00 GMT

Safe autonomous navigation in three-dimensional environments remains a critical challenge for unmanned aerial vehicles (...

SafeManip: A Property-Driven Benchmark for Temporal Safety Evaluation in Robotic Manipulation

Tue, 12 May 2026 00:00:00 GMT

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...

Safety-aware Skill Adaptation for Reinforcement Learning in Dynamic Environments

Fri, 11 Sep 2026 00:00:00 GMT

Skill adaptation frameworks based on reinforcement learning often require restrictive assumptions to maintain stability, such as fixed observations or tightly controlled exploration schedules. In cluttered and dynamic environments, however, unrestricted exploration can lead to unsafe behaviour an...

Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models

Tue, 08 Sep 2026 00:00:00 GMT

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 proper...

Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance

Thu, 28 May 2026 00:00:00 GMT

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

Scale Up Strategically: Learning Compositional Generalization via Bias-Aware Evaluation and Data Collection for Robotic Manipulation

Sun, 26 Jul 2026 00:00:00 GMT

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. We introduce a diagnostic framework that localizes this failure to individual \textit{instruction...

Scaling Behavior Foundation Model for Humanoid Robots

Sun, 19 Jul 2026 00:00:00 GMT

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. Behavior Foundation Models (BFMs) have recently emerged as a promisin...

Scout-Assisted Planning for Heterogeneous Robot Teams under Partially Known Environments

Sun, 24 May 2026 00:00:00 GMT

SAP pairs aerial scouts with ground robots to gather environmental information ahead of time, reducing mission time by 40% through information-theoretic POMDP planning.

SEED-UMI: Sharing the Exoskeleton between human and robot for onE-to-one Dexterous demonstration

Sat, 12 Sep 2026 00:00:00 GMT

Imitation learning for dexterous hands is bottlenecked by the difficulty of collecting contact-rich demonstrations that transfer faithfully to the robot. Prior wearable-exoskeleton systems record only on the human side and retarget via open-loop mappings calibrated in free space, which degrade un...

SI-Diff: A Framework for Learning Search and High-Precision Insertion with a Force-Domain Diffusion Policy

Tue, 12 May 2026 00:00:00 GMT

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. Existing approaches typically address search and...

SimplerEnv: Simulated Manipulation Policy Evaluation with Real-World Video Prompts

Sat, 09 May 2026 00:00:00 GMT

A benchmark environment for evaluating real-world robot manipulation policies in simulation using real-world video prompts, enabling zero-shot sim-to-real transfer evaluation without physical hardware.

Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations

Sun, 17 May 2026 00:00:00 GMT

Predictive world models enable agents to model scene dynamics and reason about the consequences of their actions. Inspired by human perception, object-centric world models capture scene dynamics using object-level representations, which can be used for downstream applications such as action planning...

Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action

Sun, 24 May 2026 00:00:00 GMT

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.

Spatiotemporal Tube-Based Safety-Certificate for Autonomous Navigation of Articulated Vehicles

Mon, 17 Aug 2026 00:00:00 GMT

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. This paper presents a spatiotemporal tube-based appr...

STEP: State-Aware Task Estimation and Planning with Multi-Modal LLMs for Human-Robot Collaboration

Sun, 30 Aug 2026 00:00:00 GMT

Effective human-robot collaboration in industrial settings requires robots to understand human intentions and assist with task planning, reducing workload. Recent works have explored the use of Multi-modal Large Language Models (MM-LLMs) for task planning in such data-scarce scenarios, leveraging...

Stigmergic Graph Memory: An Environment-Aware Approach for Many-to-Many Multi-Agent Pickup and Delivery

Sun, 19 Jul 2026 00:00:00 GMT

Automated fulfillment warehouses must continuously assign and execute pickup-and-delivery work while avoiding congestion. In many-to-many Multi-Agent Pickup and Delivery (MAPD), a request specifies a stock-keeping unit rather than fixed endpoints, requiring the controller to select an agent, sour...

Stubborn: A Streamlined and Unified Reinforcement Learning Framework for Robust Motion Tracking and Fall Recovery for Humanoids

Sun, 14 Jun 2026 00:00:00 GMT

Recent reinforcement learning approaches have shown great promise in improving humanoid motion tracking performance and achieving fall recovery under disturbances. However, most existing works treat motion tracking and fall recovery as different tasks and require multi-stage training with specialize...

Subspace Inference Enables Efficient Active Reward Learning from Preferences

Sun, 06 Sep 2026 00:00:00 GMT

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. However, effective uncertainty quantification ...

Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning

Sun, 24 May 2026 00:00:00 GMT

The first demonstration of superhuman, safe, multi-agent drone racing using a MARL framework trained in simulation and transferred to real Crazyflie nano-drones.

SwingBot: Learning Whole-Body Brachiation for Humanoid Robots

Thu, 10 Sep 2026 00:00:00 GMT

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. Bringing this capabil?ity to high-DoF humanoid robots is difficult because the controller must disco...

Symmetries Here and There, Combined Everywhere: Cross-space Symmetry Compositions in Robotics

Sun, 24 May 2026 00:00:00 GMT

Formalizes cross-space symmetry compositions in robotics and derives equivariant network architectures that exploit multiple simultaneous symmetries for improved generalization.

Synthetic Data Generation and Vision-based Wrinkle and Keypoint Detection for Bimanual Cloth Manipulation

Sun, 07 Jun 2026 00:00:00 GMT

Robotic manipulation of textiles remains challenging because continuous deformation and self-occlusions hinder the robust visual perception required to estimate the cloth's state. To address the lack of annotated real-world data, we developed a Blender-based synthetic pipeline exporting auto-annotat...

TactSpace: Learning a Physics-enriched Shared Latent Space for Tactile Sim-to-Real Transfer

Sun, 21 Jun 2026 00:00:00 GMT

Tactile sensing provides direct measurements of contact interactions that are essential for robotic manipulation. However, current simulators lack the fidelity to faithfully model ...

TactSpace: Learning a Physics-enriched Shared Latent Space for Tactile Sim-to-Real Transfer

Sun, 21 Jun 2026 00:00:00 GMT

Tactile sensing provides direct measurements of contact interactions that are essential for robotic manipulation. However, current simulators lack the fidelity to faithfully model ...

TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection

Sun, 30 Aug 2026 00:00:00 GMT

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. We present a novel task-aware deformable prediction (TADP) method for single-stage 3D object ...

Task-space model-based control of pneumatic soft actuators

Sun, 30 Aug 2026 00:00:00 GMT

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. This paper presents a real-time dynamic-model-based task-space feedback and estimation framew...

TEA-AgriVLN: Traversability Estimation Alarm for Agricultural Vision-and-Language Navigation

Sun, 02 Aug 2026 00:00:00 GMT

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. The A2A benchmark and the AgriVLN method pioneeringly extended ...

Tensegrity Continuum Robots Enable Task-Adaptive Morphologies for Cooperative Behaviors

Sun, 30 Aug 2026 00:00:00 GMT

Robots that can change their morphologies and behaviors for different tasks and environments hold great promise for adaptable, multifunctional systems. Modular reconfigurable robots (MRRs) can achieve such functionalities by docking and rearranging individual units, but most rely on rigid modules...

\textbf{PLATO}: \emph{Preintegration Learning from Accurate Trajectory Observations} for Neural Inertial Odometry

Wed, 09 Sep 2026 00:00:00 GMT

Neural inertial odometry has demonstrated strong potential for motion estimation in challenging environments, yet inertial-only preintegration remains sensitive to IMU bias and uncertainty. To this end, this paper introduces \textbf{PLATO}:~\emph{Preintegration Learning from Accurate Trajectory O...

THRIVE: Therapeutic Humanoid Robot In Virtual Environment

Mon, 17 Aug 2026 00:00:00 GMT

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. The system is...

TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning

Tue, 12 May 2026 00:00:00 GMT

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...

Towards Neuro-Symbolic Procedural Reasoning for Long-Horizon Vision-Language-Action Manipulation

Tue, 08 Sep 2026 00:00:00 GMT

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. We investigate a neuro-symbolic framework that combines learned VLA ...

Towards Professional Tennis Styles for Humanoid Robots with Adaptive Motion Planning and Tracking

Sun, 23 Aug 2026 00:00:00 GMT

Humanoid robots have recently demonstrated promising capabilities in real-world ball sports. However, achieving professional motion styles while maintaining strong task performance remains challenging. In this work, we propose AdaPT, an Adaptive Motion Planning and Tracking framework that learns ...

Towards Surgical World-Action Modeling: A Preliminary Joint Visual-Trajectory Forecasting for Surgical Motion Planning

Sun, 23 Aug 2026 00:00:00 GMT

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. Scene...

Uncertainty Quantification for Flow-Based Vision-Language-Action Models

Wed, 05 Aug 2026 00:00:00 GMT

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).

Unified Noise Steering for Efficient Human-Guided VLA Adaptation

Tue, 12 May 2026 00:00:00 GMT

Adapting Vision-Language-Action (VLA) models to specific user preferences or task requirements typically requires expens...

UniMPA: A Unified Memory-Prediction-Action Model via Action-Grounded Transition Modeling

Sat, 12 Sep 2026 00:00:00 GMT

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. Visually similar current observation...

Unitree Go2: Learning Vision-Based Quadrupedal Locomotion End-to-End

Sat, 09 May 2026 00:00:00 GMT

Unitree Go2 uses cross-modal vision + proprioception transformers trained in Isaac Gym to achieve agile navigation over rough terrain with minimal sim-to-real gap.

Using Automated Vehicles Operational Data to Confirm Safety and Anticipate Threats

Fri, 11 Sep 2026 00:00:00 GMT

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. The framework is inspired by best practices developed at the United Nations Eco...

VibeAct: Vibration to Actions for Contact-Rich Reactive Robot Dexterity

Thu, 25 Jun 2026 00:00:00 GMT

Dexterous manipulation depends on contact events that are fast, local, and often visually occluded. Piezoelectric microphones offer a compact and high-bandwidth way to sense these interactions, but the resulting vibro-acoustic signals are difficult to simulate faithfully enoug...

Video2DoorTraversal: Push Door Traversal via Simulated Door Twins

Sun, 23 Aug 2026 00:00:00 GMT

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. Given one RGB video of a real door, Doo...

VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse Demonstrations

Sun, 09 Aug 2026 00:00:00 GMT

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. Variable impedance skills can be learned from demonstrations, avoiding com...

Visual-SLAM for the detection of hidden tomatoes in greenhouses by Hierarchical Localization and GLOMAPfor robotized harvesting

Sat, 12 Sep 2026 00:00:00 GMT

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. This work proposes a Visual-SLAM system usi...

VLA-Corrector: Stage-Aware Observable State Understanding for Prompt-Based Closed-Loop Recovery of Vision-Language-Action Policies

Wed, 09 Sep 2026 00:00:00 GMT

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. We introduce a st...

VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method

Sun, 26 Jul 2026 00:00:00 GMT

Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions. However, route-level instructions commonly encode spatial priors, such as orientation, distance, and layout, that are not explicitly available from onboard sensing at deployment in open, GPS-deni...

VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models

Sat, 09 May 2026 00:00:00 GMT

VoxPoser uses LLMs to compose 3D value maps from free-form language instructions, enabling zero-shot closed-loop manipulation planning with model-based trajectory synthesis over dynamic environments.

Wave-Based Bilateral Teleoperation between Nonlinear Manipulators with Direct Contact Force Feedback

Sun, 23 Aug 2026 00:00:00 GMT

We study bilateral teleoperation between nonlinear, multi-DOF robotic manipulators in the presence of constant communication delays. Unlike classical wave-transformation architectures that transmit a coordinating force, we consider the case where the environmental force is reflected to the master...

What Limits Vision-and-Language Navigation ?

Sun, 17 May 2026 00:00:00 GMT

Vision-and-Language Navigation (VLN) is a cornerstone of embodied intelligence. However, current agents often suffer from significant performance degradation when transitioning from simulation to real-world deployment, primarily due to perceptual instability (e.g., lighting variations and motion blu...

What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies

Tue, 08 Sep 2026 00:00:00 GMT

Visuomotor imitation policies can achieve high performance under in-distribution visual conditions yet fail when visually similar objects or receptacles are introduced. We study this behavior as a problem of conditional visual grounding: the visual target required for successful control changes w...

WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control

Fri, 11 Sep 2026 00:00:00 GMT

Humanoid robots require precise locomotion and dexterous manipulation to perform challenging loco-manipulation tasks. Yet existing approaches, modular or end-to-end, are deficient in manipulation-aware locomotion. This confines the robot to a limited workspace, preventing it from performing large...

WorldSample: Closed-loop Real-robot RL with World Modelling

Sun, 05 Jul 2026 00:00:00 GMT

Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction beyond t...

WT-UMI: Tactile-based Whole-Body Manipulation via Force-Supervised Contact-Aware Planning

Sun, 14 Jun 2026 00:00:00 GMT

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. On the other hand, different demonstration sources provide complementary modalities with...

X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction

Tue, 12 May 2026 00:00:00 GMT

Effectively handling the interplay between spatial perception and action generation remains a critical bottleneck in robotic manipulation. Existing methods typically treat spatial perception and action execution as decoupled or strictly...

X-NavDP: Generalizing Navigation Diffusion Policy to Novel Behavior and Embodiments with Group Q-score Reweighted Matching

Sun, 02 Aug 2026 00:00:00 GMT

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. This limits the policy's generalization to diverse embodiments and challenging scenarios (e.g., escaping dea...

$ω$-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation

Sun, 09 Aug 2026 00:00:00 GMT

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. Yet existing humanoid policies typically decompose locomotion and manipulation, while recent world-action mode...