I'm interested in robots 🦾 that assist human👫 in all sorts of ways. Currently, I'm focusing on designing algorithms that enable humanoid robots to adapt intelligently to uncertainties during loco-manipulation!
🎉2023.4: Finished SWheg series robots, marked a mile-stone for a 2-year long project!
🎉2022.5: Finished incredible time at MIT MechE as a special student.
🎉2022.2: Paper selected as Best Paper Finalist at ICARM 2022.
Research
*Equal Contribution, $Denotes core contributors
BFM-Zero: A Promptable Behavioral Foundation Model
for Humanoid Control Using Unsupervised
Reinforcement Learning
Yitang Li*, Zhengyi Luo*, Tonghe Zhang$, Cunxi Dai$, Andrea Tirinzoni, Anssi Kanervisto, Haoyang Weng, Kris Kitani, Mateusz Guzek, Ahmed Touati, Alessandro Lazaric, Matteo Pirotta, Guanya Shi
in-submmision, 2026
arXiv /
webpage
BFM-Zero is a behavioral foundation model that learns a shared latent space over motions, goals, and rewards via unsupervised RL, letting a single humanoid robot policy be prompted to perform diverse whole-body tasks in the real world.
A holistic framework for dynamic interactive navigation that leverages learned representations for rapid adaptation to object dynamics, and utilizes model-based prediction to inform decision-making.
Robust design of a wheel-leg transformable robot for high-payload context.
Human-Exoskeleton Misalignment Reduction on Knee Joint via an RPR Mechanism-Based Device
Cunxi Dai,
Peiwen Fu,
Bin Zhong,
Kaiqi Guo,
Mingming Zhang ICARM 2022
Best Paper Finalist, ICARM 2022 Paper
/
YouTube
Knee joint misalignment reduction with an RPR mechanism-based device.
Selected Projects
Power Management Module and Force-Sensing Tendon for 2-DoF Ankle-Foot Prosthesis
MIT Media Lab, Biomechatronics Lab, 2023
