Cautious NMPC with Gaussian Process Dynamics for Autonomous Miniature Race Cars
This work addresses the challenge of high-performance control in autonomous racing, which is incremental as it builds on existing NMPC and GP methods for a specific domain.
The paper tackled the problem of modeling racing dynamics for autonomous miniature race cars by introducing a cautious nonlinear model predictive control method that learns from data, resulting in significant improvements in lap time and constraint satisfaction compared to a baseline without model learning.
This paper presents an adaptive high performance control method for autonomous miniature race cars. Racing dynamics are notoriously hard to model from first principles, which is addressed by means of a cautious nonlinear model predictive control (NMPC) approach that learns to improve its dynamics model from data and safely increases racing performance. The approach makes use of a Gaussian Process (GP) and takes residual model uncertainty into account through a chance constrained formulation. We present a sparse GP approximation with dynamically adjusting inducing inputs, enabling a real-time implementable controller. The formulation is demonstrated in simulations, which show significant improvement with respect to both lap time and constraint satisfaction compared to an NMPC without model learning.