Title: Reducing Wishful Assumptions for Increasing Robustness in Robot Manipulation
Abstract: Manipulation is an essential skill enabling robots to physically engage them in real-world tasks. Being a topic involving multiple sub-problems, including planning, control, learning, design, and estimation, robot manipulation still remains a highly challenging field after decades of extensive research. Among others, one major issue always associated with manipulation systems is that it is hard to transfer most of the "successful" solutions from labs to real-world applications, either they be learning-based or analytical approaches, due to physical and perception uncertainties etc. In other words, we have been making too many wishful assumptions in the development of robot systems, such as that we will have enough data for training, we will have good sensors, etc. In this talk, I will focus on the exploration of common wishful assumptions, their impacts, as well as how we can develop robots with less of such assumptions. Research topics including robot self-identification, interactive perception, manipulation funnels, caging-based manipulation, and end-effector design will be discussed.
Bio: Kaiyu Hang is an Assistant Professor of Computer Science at Rice University, where he leads the Robotics and Physical Interactions Lab. He is broadly interested in robotic systems that can physically interact with other robots, people, and the world. By developing algorithms in optimization, planning, learning, estimation, and control, his research is focused on efficient, robust, and generalizable manipulation systems, addressing problems that range from small scale grasping and in-hand manipulation, to large scale dual-arm manipulation, mobile manipulation, and multi-robot manipulation.
Meeting ID: 841 4970 8803
Password: 444347