ABSTRACT
Robot learning has witnessed significant progress in terms of generalization recently, with the help of datadriven learning and image/text foundation models. While these achievements are encouraging, most tasks conducted in this context are relatively simple (e.g., pickandplace with a parallel gripper). In this talk, I will talk about our recent efforts to learn generalizable skills focusing on tasks with rich physical contacts and geometric reasoning. Specifically, I will discuss our research on: (i) the use of a large number of lowcost, binary force sensors to enable Sim2Real manipulation; (ii) unifying 3D and semantic representation learning to generalize policy learning across diverse objects and scenes. I will showcase the realworld applications of our research, including dexterous manipulation, and legged locomotion control, and languagedriven mobile manipulation.


PRESENTER
Xiaolong Wang is an Assistant Professor in the ECE department at the University of California, San Diego. He received his Ph.D. in Robotics at Carnegie Mellon University. His postdoctoral training was at the University of California, Berkeley. His research focuses on the intersection between computer vision and robotics. His specific interest lies in learning 3D and dynamics representations from videos and physical robotic interaction data. These comprehensive representations are utilized to facilitate the learning of robot skills, with the goal of generalizing the robot to interact effectively with a wide range of objects and environments in the real physical world. He is the recipient of the NSF CAREER Award, Intel Rising Star Faculty Award, and multiple industrial Research Awards.