Model-based control cuts errors and lap times in autonomous racing
MAP2: Model- and Acceleration-Based Pursuit with MPC and Gaussian Process Residual Learning for Autonomous Racing
Robotics
Summary
In fast self-driving car racing, cars need to follow tracks very precisely while turning close to their limits. The authors improve existing driving controllers by combining a look-ahead planning method with a smart way to fix leftover prediction errors using data. This new controller, called MAP2, helps cars steer more accurately even when turning very sharply and reduces errors by up to 45%. Tests on real cars showed the improved controller makes lap times faster by at least 1.5%.
What this means in practice
- •For autonomous vehicle developers: Improve real-time path tracking accuracy and reduce lap times in autonomous race cars using combined model predictive control and learned residual corrections.
- •For robotic control engineers: Incorporate Gaussian Process residual models with geometric control frameworks to handle complex vehicle dynamics near physical limits.
Authors
Weizhan Huang, Cheng Hu, Edoardo Ghignone, Nicolas Baumann, Yiqin Wang, Hongye Su, Lei Xie, Michele Magno
Abstract
Autonomous racing requires accurate trajectory tracking near the handling limits of a vehicle while maintaining low computational latency. Geometric controllers are computationally efficient, but the Ackermann steering geometry becomes invalid under limit-handling conditions. Model- and Acceleration-based Pursuit (MAP) preserves the simplicity of geometric approaches while leveraging tire dynamics. Yet MAP remains fundamentally a geometric controller that relies on Ackermann steering geometry, and its tire model may not fully capture the vehicle's actual dynamic response. This paper presents MAP2, a model-based pursuit controller that combines a curvature-based kinematic MPC and a Sparse Gaussian Process (SGP) residual correction. The proposed algorithm uses MPC to optimize kinematic control inputs over a prediction horizon and maps them to steering commands through a tire dynamics model augmented with SGP residual correction. Real-world vehicle experiments demonstrate substantial reductions in lateral tracking error and lap time. Compared with MAP and Pure Pursuit (PP), MAP2 reduces the average lateral tracking error by 37.99% and 44.65%, respectively, while reducing average lap time by at least 1.5%.