Zero-order optimization for Gaussian process-based model predictive control

DOI10.1016/J.EJCON.2023.100862MaRDI QIDQ6092479zbMATH OpenFDO

Authors Amon Lahr, Andrea Zanelli, Andrea Carron, Melanie N. Zeilinger

Publication date 23 November 2023

Published in European Journal of Control (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2211.15522

zbMATH Keywords

inexact sequential quadratic programmingnonlinear optimizationreal-time model predictive control

Mathematics Subject Classification ID

Quadratic programming (90C20) Model predictive control (93B45)

Abstract: By enabling constraint-aware online model adaptation, model predictive control using Gaussian process (GP) regression has exhibited impressive performance in real-world applications and received considerable attention in the learning-based control community. Yet, solving the resulting optimal control problem in real-time generally remains a major challenge, due to i) the increased number of augmented states in the optimization problem, as well as ii) computationally expensive evaluations of the posterior mean and covariance and their respective derivatives. To tackle these challenges, we employ i) a tailored Jacobian approximation in a sequential quadratic programming (SQP) approach, and combine it with ii) a parallelizable GP inference and automatic differentiation framework. Reducing the numerical complexity with respect to the state dimension $n_x$ for each SQP iteration from $mathcalO(n_x^6)$ to $mathcalO(n_x^3)$, and accelerating GP evaluations on a graphical processing unit, the proposed algorithm computes suboptimal, yet feasible solutions at drastically reduced computation times and exhibits favorable local convergence properties. Numerical experiments verify the scaling properties and investigate the runtime distribution across different parts of the algorithm.

Recommendations

• Online learning‐based model predictive control with Gaussian process models and stability guarantees
• Hybrid Gaussian process modeling applied to economic stochastic model predictive control of batch processes
• Tracking control of uncertain nonlinear systems via adaptive Gaussian process prediction and real-time optimisation

Cites work

• \texttt{acados} -- a modular open-source framework for fast embedded optimal control
• CasADi: a software framework for nonlinear optimization and optimal control
• Constrained optimal feedback control of systems governed by large differential algebraic equations
• Gaussian processes for machine learning.
• scientific article; zbMATH DE number 780774 (Why is no real title available?)
• Implicit Functions and Solution Mappings
• Recent advances in quadratic programming algorithms for nonlinear model predictive control
• Strongly Regular Generalized Equations

This page was built for publication: Zero-order optimization for Gaussian process-based model predictive control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6092479)