Wendi Chen
Wendi Chen is a computer science Ph.D. student at Shanghai Jiao Tong University and the Shanghai Innovation Institute, where she is a member of the Machine Vision and Intelligence Group supervised by Professor Cewu Lu. Her research focuses on embodied AI and robotic manipulation, with particular emphasis on contact-rich interactions, deformable object manipulation, and force-aware policies. She is a co-author of ImplicitRDP, an end-to-end visual-force diffusion policy, and RoboPocket, a system for robot-free policy iteration using smartphones, as well as Reactive Diffusion Policy, which was a Best Student Paper Finalist at RSS 2025.
“FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich Manipulation”
Source→“Our hardware setup uses a Flexiv Rizon 4R leader arm for teleoperation and a Rizon 4s follower arm for task execution”
Source→“capture visual observations with a wrist-mounted iPhone fisheye camera”
Source→“standard diffusion policies use a fixed inference frequency and sampling steps throughout the episode, forcing a fundamental compromise: low-frequency, multi-step sampling better preserves pre-contact multimodality but responds slowly to force feedback, whereas high-frequency sampling improves reactivity but tends to collapse distinct pre-contact modes.”
Source→“Lifeng Zhuo and Wendi Chen: Equal contribution first authors who developed the core FA-RDP architecture and experiments.”
Source→“Wendi Chen — Shanghai Jiao Tong University / Shanghai Innovation Institute. Co-first author and project lead. Also an author on ImplicitRDP and RoboPocket, indicating sustained work on force-aware policies and online post-training infrastructure.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.