Haoyu Xiong

Hi! My name is Haoyu Xiong. I'm a full-time researcher at Shanghai Qizhi Institute advised by Cewu Lu. I'm also working with Animesh Garg at University of Toronto and Vector Institute, closely collaborating with Stanford Vision and Learning Lab. Previously, I spent a wonderful time at UC Berkeley.

I'm broadly interested in robot learning. Specifically, I'm focusing on visual imitation learning, representation learning for robotic manipulation.

Email  /  Scholar  /  Github  /  Twitter  /  Linkedin  /  Zhihu

profile photo

My research vision is to build robotic systems with a human-compatible ability to achieve generalizable autonomy in the real world. I believe understanding representations without the dependency of strong supervision plays a vital role in this goal.

LbW Learning by Watching:
Physical Imitation of Manipulation Skills from Human Videos
Haoyu Xiong, Quanzhou Li, Yun-Chun Chen, Homanga Bharadhwaj, Samrath Sinha, Animesh Garg
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
Spotlight Talk, RSS 2021 Workshop on Visual Learning and Reasoning for Robotics
We present an approach for physical imitation from human videos for robot manipulation tasks. The key idea of our method lies in explicitly exploiting the kinematics and motion information embedded in the video to learn structured representations that endow the robot with the ability to imagine how to perform manipulation tasks in its own context.
website / video / pdf