Physics simulation environments and sim-to-real transfer techniques.
Yufei Jia, Zhanxiang Cao, Mingrui Yu et al. · arXiv preprint · May 2026
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
Christen Millerdurai, Shaoxiang Wang, Yaxu Xie et al. · SIGGRAPH 2026 · May 2026
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...
Chi Zhang, Penglin Cai, Ziheng Xi et al. · arXiv preprint · Jul 2026
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...
Zhihao Cao, Qi Shao, Shuhao Zhai et al. · arXiv · May 2026
Multi-agent simultaneous localization and mapping (SLAM) enables collaborative 3D reconstruction. This paper introduces ...
Marco Coscoy, Zewei Zhou, Seth Z. Zhao et al. · arXiv · May 2026
Multi-agent autonomous driving systems require coordination among vehicles to navigate complex traffic scenarios safely ...
Video
Jiye Lee, Yonghun Choi, Jungdam Won · SIGGRAPH 2026 (Journal Track) · Jun 2026
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.
Jiaxu Wang, Junhao He, Jingkai Sun et al. · arXiv preprint · May 2026
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.
Chengyue Huang, Khang Vo Huynh, Sebastian Elbaum et al. · arXiv · May 2026
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...
Zachary Kousik, Shanpu Fang, Rohan Thakker et al. · arXiv · 2024
An open-source 3D-printed humanoid robot platform designed for reinforcement-learning based locomotion research with affordable hardware.
Wang J., Xiao B., Wang J., Heider P., Li H., Zhang Y. · arXiv · 2024
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.
Nikita Rudin, David Hoeller, Philipp Reist et al. · RSS 2022 Workshop / arXiv 2109.11978 · Jun 2022
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.
Nikita Rudin, David Hoeller, Marco Hutter · Open Source Library · Jun 2022
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.
Viktor Makoviychuk, Lukasz Wawrzyniak, Yunrong Guo et al. · NeurIPS 2021 Datasets and Benchmarks Track · Dec 2021
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.
Josh Tobin, Rachel Fong, Alex Ray et al. · IROS · Sep 2017
Introduced domain randomization for vision-based manipulation: randomize simulation textures, lighting, and camera parameters so that the real world looks like just another variation.
Read these papers in order to build expertise in Simulation.
Yufei Jia, Zhanxiang Cao et al. · 2026
Christen Millerdurai, Shaoxiang Wang et al. · 2026
Chi Zhang, Penglin Cai et al. · 2026
Zhihao Cao, Qi Shao et al. · 2026
Marco Coscoy, Zewei Zhou et al. · 2026
Jiye Lee, Yonghun Choi et al. · 2026
…and 8 more papers.
