Open access
Date
2020-11Type
- Journal Article
Abstract
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. 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 with fast sampling times of 20 ms, highlighting improvements with regard to both performance and safety over a nominal controller. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000389524Publication status
publishedExternal links
Journal / series
IEEE Transactions on Control Systems TechnologyVolume
Pages / Article No.
Publisher
IEEESubject
Model Predictive Control; Gaussian Processes; Learning-based Control; Model Learning; Autonomous RacingOrganisational unit
09563 - Zeilinger, Melanie / Zeilinger, Melanie
Funding
157601 - Safety and Performance for Human in the Loop Control (SNF)
More
Show all metadata