Cautious Model Predictive Control using Gaussian Process Regression
For control engineers and roboticists, this work provides a principled way to incorporate GP-based uncertainty into MPC for safer and more cautious control of nonlinear systems.
The paper presents a model predictive control approach that integrates a nominal system with a GP-modeled additive nonlinear part, using chance constraints to account for residual uncertainty. The method is demonstrated in simulation and on autonomous racing RC cars, showing improved performance and safety over a nominal controller.
Gaussian process (GP) regression has been widely used in supervised machine learning due to its flexibility and inherent ability to describe uncertainty in function estimation. In the context of control, it is seeing increasing use for modeling of nonlinear dynamical systems from data, as it allows the direct assessment of residual model uncertainty. We present a model predictive control (MPC) approach that integrates a nominal system with an additive nonlinear part of the dynamics modeled as a GP. Approximation techniques for propagating the state distribution are reviewed and we describe a principled way of formulating the chance constrained MPC problem, which takes into account residual uncertainties provided by the GP model to enable cautious control. Using additional approximations for efficient computation, we finally demonstrate the approach in a simulation example, as well as in a hardware implementation for autonomous racing of remote controlled race cars, highlighting improvements with regard to both performance and safety over a nominal controller.