Zhao, Kang (Xi'an Jiaotong University), Xue, Jianru (Xi'an Jiaotong University), Meng, Xiangning (Xi'an Jiaotong University), Li, Gengxin (Xi'an Jiaotong University), Wu, Mengsen (XJTU)

Learning Residual Model of Model Predictive Control Via Random Forests for Autonomous Driving

Scheduled for presentation during the Invited Session "Learning-empowered Intelligent Transportation Systems: Foundation Vehicles and Coordination Technique II" (WeBT1), Wednesday, September 25, 2024, 14:50−15:10, Salon 1

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 14, 2024

Abstract

One major issue in learning-based model predictive control (MPC) for autonomous driving is the contradiction between the system model's prediction accuracy and computation efficiency. The more situations a system model covers, the more complex it is, along with highly nonlinear and nonconvex properties. These issues make the optimization too complicated to solve and render real-time control impractical. The learned model consists of two levels. The low level uses linear regression to fit the residues, and the high level uses random forests to switch different linear models. Meanwhile, we adopt the linear dynamic bicycle model with error states as the nominal model. The switched linear regression model is added to the nominal model to form the system model. It reformulates the learning-based MPC as a quadratic program (QP) problem, and optimization solvers can effectively solve it. Experimental path tracking results show that the driving vehicle's prediction accuracy and tracking accuracy are significantly improved compared with the nominal MPC. Compared with the state-of-the-art Gaussian process-based nonlinear model predictive control (GP-NMPC), our method gets better performance on tracking accuracy while maintaining a lower computation consumption.