Vehicle Prediction Model for Enhanced MPC Path Tracking in Formula Student Driverless

2026-06-09

AI Summary

This study addresses the limitations of conventional model predictive control (MPC) in autonomous racing under extreme conditions, where path-tracking performance is hindered by insufficient accuracy of the underlying prediction models. To overcome this challenge, the authors propose a novel three-tier prediction architecture that synergistically integrates historical and real-time data. This framework uniquely combines offline Bayesian linear regression with online sparse Gaussian process regression, achieving high-fidelity predictions and rigorous uncertainty quantification while maintaining low computational overhead. An MPC controller built upon a kinematic bicycle model and the proposed predictor demonstrates up to a 57% improvement in path-tracking accuracy on narrow tracks. The efficacy of the approach is validated through experiments on a real-world Formula Student autonomous racing platform.

Abstract

Autonomous race cars, such as in Formula Student Driverless, operate close to their physical handling limits. The resulting highly nonlinear vehicle behavior increases the path tracking complexity, especially on narrow tracks. Model Predictive Control (MPC) is commonly used to address this issue, a method whose performance is closely tied to the accuracy of the underlying prediction model. This paper presents a novel, real-time capable prediction model for autonomous race cars that adjusts to changing conditions by combining information from past runs and the current driving situation. Our model is divided into three consecutive submodels: a nominal Kinematic Bicycle Model, an offline Bayesian Linear Regression (BLR) model, and an online Sparse Gaussian Process Regression (SGPR) model. The proposed approach enables efficient integration of all available data without significantly increasing computational cost, ensuring high prediction accuracy and a quantitative uncertainty assessment right from the start of the run. Compared to existing approaches, an improvement in prediction accuracy of up to 57% was achieved. Further, we successfully demonstrated the practical applicability of the model within an MPC-based path tracking controller on a real Formula Student race car.

Problem

• autonomous race cars
• path tracking
• nonlinear vehicle dynamics
• Formula Student Driverless
• handling limits

Innovation

• Model Predictive Control
• Sparse Gaussian Process Regression
• Bayesian Linear Regression
• Autonomous Race Car
• Real-time Prediction Model