Learning Model Predictive Control with Error Dynamics Regression for Autonomous Racing

TL;DR

This paper introduces a novel Learning Model Predictive Control approach that combines a physics-based model with data-driven error dynamics learning, enabling autonomous race cars to improve handling and robustness at high speeds through iterative learning and exploration.

Contribution

It proposes a new LMPC method that integrates a global nonlinear physics model with local linear error learning, enhancing high-speed autonomous racing performance.

Findings

Improved robustness to parameter tuning and data scarcity.

Successful deployment on a full-scale race car in real-world conditions.

Demonstrated safety-aware exploration and iterative learning at the handling limit.

Abstract

This work presents a novel Learning Model Predictive Control (LMPC) strategy for autonomous racing at the handling limit that can iteratively explore and learn unknown dynamics in high-speed operational domains. We start from existing LMPC formulations and modify the system dynamics learning method. In particular, our approach uses a nominal, global, nonlinear, physics-based model with a local, linear, data-driven learning of the error dynamics. We conducted experiments in simulation and on 1/10th scale hardware, and deployed the proposed LMPC on a full-scale autonomous race car used in the Indy Autonomous Challenge (IAC) with closed loop experiments at the Putnam Park Road Course in Indiana, USA. The results show that the proposed control policy exhibits improved robustness to parameter tuning and data scarcity. Incremental and safety-aware exploration toward the limit of handling and iterative learning of the vehicle dynamics in high-speed domains is observed both in simulations and experiments.