We propose an image-only robotic manipulation framework with ability to actively perceive object from multiple perspectives during the manipulation process.

We propose MultiGrasp, a two-stage framework for simultaneous multi-object grasping with multi-finger dexterous hands.

We present an environment suite called Safety-Gymnasium, which encompasses safety-critical tasks in both single and multi-agent scenarios and a library of algorithms named Safe Policy Optimization (SafePO).

OmniSafe is an infrastructural framework designed to accelerate safe reinforcement learning (RL) research.

We introduce ReDMan, an open-source simulation platform that provides a standardized implementation of safe RL algorithms for Reliable Dexterous Manipulation.

@article{geng2023partmanip,
 title={PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations},
 author={Geng, Haoran and Li, Ziming and Geng, Yiran and Chen, Jiayi and Dong, Hao and Wang, He},
 journal={arXiv preprint arXiv:2303.16958},
 year={2023}
}

We introduces Part-aware Affordance Learning methods. Our approach first learns a part prior, subsequently generating an affordance map. We further enhance precision by introducing a part-level scoring system, designed to identify the best part for manipulation.

This study is the first attempt to formulate the dynamic grasping problem as a “move-and-grasp” game and use adversarial RL to train the grasping policy and object moving strategies jointly.