MAP2: Model- and Acceleration-Based Pursuit with MPC and Gaussian Process Residual Learning for Autonomous Racing

2026-10-08

AI Summary

This study addresses the failure of geometric controllers and inaccurate dynamic response modeling in autonomous racing under limit-handling conditions by proposing a kinematic model predictive control (MPC) method integrated with sparse Gaussian process (SGP) residual learning. The approach leverages SGP to correct unmodeled dynamic errors online and employs a tire dynamics model to map kinematic outputs into physical steering commands, thereby overcoming the performance bottlenecks of conventional control frameworks. Real-vehicle experiments demonstrate that the proposed method reduces lateral tracking error by 37.99% compared to pure pursuit algorithms while improving lap times by at least 1.5%. These results validate its capability for high-precision trajectory tracking in extreme competitive racing scenarios.

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%.

Problem

• Autonomous Racing
• Trajectory Tracking
• Limit Handling
• Ackermann Steering Geometry
• Tire Dynamics

Innovation

• Model Predictive Control
• Sparse Gaussian Process
• Residual Learning
• Autonomous Racing
• Trajectory Tracking