Cautious NMPC with Gaussian Process Dynamics for Autonomous Miniature Race Cars

TL;DR

This paper introduces a cautious NMPC approach utilizing Gaussian Processes to adaptively learn and improve the dynamics model of autonomous miniature race cars, enhancing performance while ensuring safety.

Contribution

It proposes a real-time implementable cautious NMPC method that learns dynamics from data using sparse Gaussian Processes with dynamic inducing inputs.

Findings

Significant lap time reduction in simulations.

Improved constraint satisfaction.

Effective real-time dynamics learning.

Abstract

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.