Scholar
Yuanpei Chen
Google Scholar ID: LR4CHSkAAAAJ
South China University of Technology
Citations & Impact
Citations
741
H-index
11
i10-index
13
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- Representative Publications:
- 1. Object-Centric Dexterous Manipulation from Human Motion Data - CoRL 2024
- 2. Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation - CoRL 2023
- 3. Dynamic Handover: Throw and Catch with Bimanual Hands - CoRL 2023
- 4. Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning - T-PAMI 2023, NeurIPS 2022
- Collaborative Publications:
- 1. DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping
- 2. Retrieval Dexterity: Efficient Object Retrieval in Clutters with Dexterous Hand
- 3. Dexterous Non-Prehensile Manipulation for Ungraspable Object via Extrinsic Dexterity
- 4. SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Safe Reinforcement Learning
- 5. Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning - CoRL 2024
Research Experience
- Co-founder of PsiBot; worked with Prof. Yaodong Yang at Peking University; closely collaborated with Prof. Xiaolong Wang (UCSD), Prof. Chenguang Yang (SCUT), and Prof. Hao Dong (Peking University); served as a visiting researcher at Stanford University in 2023.
Education
- Peking University (Advisor: Prof. Yaodong Yang), Visiting Researcher at Stanford University (Advisors: Prof. Karen Liu and Prof. Fei-Fei Li)
Background
- Research Interests: Robotics, dexterous manipulation, reinforcement learning, and sim-to-real transfer. Goal is to let the robot perform various cool behaviors in the real world as in the simulation.