Zeyuan Chen | 陈泽源

I am a second-year master's student at the Peking University. I'm also a research intern at Center on Frontiers of Computing Studies (CFCS) in the School of Computer Science at Peking University, advised by Prof. Hao Dong at PKU-Agibot Lab .

My research interests include Robotics and Dextereous Manipulation.

Email  /  Google Scholar  /  Github  /  WeChat

profile photo

Publications
ClutterDexGrasp: A Sim-to-Real System for General Dexterous Grasping in Cluttered Scenes

Zeyuan Chen*, Qiyang Yan*, Yuanpei Chen*, Tianhao Wu, Jiyao Zhang, Zihan Ding, Jinzhou Li, Yaodong Yang, Hao Dong
Preprint
arXiv / website

We propose the first close-loop sim-to-real system for general dexterous grasping in cluttered scenes.
CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes

Jiyao Zhang*, Zhiyuan Ma*, Tianhao Wu**, Zeyuan Chen**, Hao Dong
Preprint
website / code (coming soon)

We propose a contact- and collision-aware intermediate representation for general dexterous grasping in clutterred scenes.
Adaptive Visual-Tacile Fusion with Predictive Force Attention for Dexterous Manipulation

Jinzhou Li*, Tianhao Wu*, Jiyao Zhang**, Zeyuan Chen**, Haotian Jin, Mingdong Wu, Yujun Shen, Yaodong Yang, Hao Dong
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)
arXiv/ website

We propose a force diffusion & force-guided attention fusion module that adaptively adjusts the weights of visual and tactile features.

Projects
Dexterous Grasp Synthesis from Para-Gripper Grasps

Zeyuan Chen
Demo

We use AnyGrasp to generate para-gripper grasp candidates, mapped them to dexterous hand poses via hand-tuned transformations, and enabled table-clearing through motion planning and heuristic hand closing.
Teleoperation System for Dexterous Hand Retargeting

Zeyuan Chen
Demo

We developed a teleoperation system integrating HaMeR and Intel RealSense D415 for hand tracking, with Dexpilot for retargeting, deployed on Leap Hand for dexterous task data collection.

Borrowed from Jon Barron.