Safe learning in nonlinear model predictive control

Conference item

A robust Model Predictive Control algorithm is proposed for learning-based control with model represented by an affine combination of basis functions. The online optimization is formulated as a sequence of convex programming problems derived by linearizing concave components of the dynamic model. A tube-based approach ensures satisfaction of constraints on control variables and model states while avoiding conservative bounds on linearization errors. The linear dependence of the model on unknown parameters is exploited to allow safe online parameter adaptation. The resulting algorithm is recursively feasible and provides closed loop stability and performance guarantees. Numerical examples are provided to illustrate the approach.

Authors: Buerger, J; Cannon, M; Doff-Sotta, M

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: PMLR
• Host title: Proceedings of the 6th Annual Learning for Dynamics & Control Conference
• Pages: 603-614
• Series: Proceedings of Machine Learning Research
• Series number: 242
• Publication date: 2024-10-01
• Acceptance date: 2024-04-23
• Event title: 6th Annual Learning for Dynamics & Control Conference (L4DC 2024)
• Event location: University of Oxford, Oxford, UK
• Event website: https://l4dc.web.ox.ac.uk/home
• Event start date: 2024-07-15
• Event end date: 2024-07-17
• EISSN: 2640-3498
• Language: English