CKSRI Seminar Series 2023 "Aggressive Maneuver of an Autonomous Driving Car"
Abstract: Conventional planning and control of autonomous vehicle adopts a kinematic model of the car. Although this model is sufficient for regular driving conditions, it does not consider the slip between the tires and the road, and hence cannot be applied to low friction cases, such as driving on ice or other slippery surfaces, or when driving the car close to or beyond its friction limit. In this talk we consider the problem of planning and control for an autonomous vehicle to perform an aggressive maneuver called drifting, which is characterized by a large side slip angle. We first propose an adaptive controller to control a circular drift motion, that can tolerate the change of the friction coefficient. For more complex motions, a high-level MPC-inspired reinforcement learning based planner, together with a low-level INDI (incremental nonlinear dynamic inversion) controller is proposed. Simulation and real world experiment on a 1:10 vehicle are provided to demonstrate the effectiveness of the proposed strategy.
Short Biography: Yilin Mo is an Associate Professor in the Department of Automation, Tsinghua University. He received his Ph.D. In Electrical and Computer Engineering from Carnegie Mellon University in 2012 and his Bachelor of Engineering degree from Department of Automation, Tsinghua University in 2007. Prior to his current position, he was a postdoctoral scholar at Carnegie Mellon University in 2013 and California Institute of Technology from 2013 to 2015. He held an assistant professor position in the School of Electrical and Electronic Engineering at Nanyang Technological University from 2015 to 2018 before joining Tsinghua. He serves as the Chair for IFAC Technical committee on Stochastic systems and as an associate editor for Automatica and IEEE Trans on Control of Network Systems. His research on networked control systems and cyber-physical systems have been well-received, with over 8000 google scholar citations and he has been selected by Elsevier as a highly cited Chinese scholar in 2021 and 2022.