Lifeng Zhuo
Lifeng Zhuo is a researcher affiliated with Shanghai Jiao Tong University. He is known as a co-first author of FA-RDP, a frequency-adaptive reactive diffusion policy for contact-rich robotic manipulation. His work focuses on diffusion-based learning policies that balance multimodal trajectory prediction with reactive force-feedback control during contact-rich tasks.
“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→AI-extracted from podcast / newsletter / paper summaries. May contain errors.