KPC: Learning-Based Model Predictive Control with Deterministic Guarantees

No Thumbnail Available
Maddalena, Emilio T
Scharnhorst, Paul
Jiang, Yuning
Jones, Colin N
We propose Kernel Predictive Control (KPC), a learning-based predictive control strategy that enjoys deterministic guarantees of safety. Noise-corrupted samples of the unknown system dynamics are used to learn several models through the formalism of non-parametric kernel regression. By treating each prediction step individually, we dispense with the need of propagating sets through highly non-linear maps, a procedure that often involves multiple conservative approximation steps. Finite-sample error bounds are then used to enforce state-feasibility by employing an efficient robust formulation. We then present a relaxation strategy that exploits online data to weaken the optimization problem constraints while preserving safety. Two numerical examples are provided to illustrate the applicability of the proposed control method.
Publication Reference
Proceedings of the 3rd Conference on Learning for Dynamics and Control