Finite-Sample-Based Reachability for Safe Control with Gaussian Process Dynamics

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Prajapat, Manish, Köhler, Johannes, Lahr, Amon, Krause, Andreas, Zeilinger, Melanie N.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910938603454464
author Prajapat, Manish
Köhler, Johannes
Lahr, Amon
Krause, Andreas
Zeilinger, Melanie N.
author_facet Prajapat, Manish
Köhler, Johannes
Lahr, Amon
Krause, Andreas
Zeilinger, Melanie N.
contents Gaussian Process (GP) regression is shown to be effective for learning unknown dynamics, enabling efficient and safety-aware control strategies across diverse applications. However, existing GP-based model predictive control (GP-MPC) methods either rely on approximations, thus lacking guarantees, or are overly conservative, which limits their practical utility. To close this gap, we present a sampling-based framework that efficiently propagates the model's epistemic uncertainty while avoiding conservatism. We establish a novel sample complexity result that enables the construction of a reachable set using a finite number of dynamics functions sampled from the GP posterior. Building on this, we design a sampling-based GP-MPC scheme that is recursively feasible and guarantees closed-loop safety and stability with high probability. Finally, we showcase the effectiveness of our method on two numerical examples, highlighting accurate reachable set over-approximation and safe closed-loop performance.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07594
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Finite-Sample-Based Reachability for Safe Control with Gaussian Process Dynamics
Prajapat, Manish
Köhler, Johannes
Lahr, Amon
Krause, Andreas
Zeilinger, Melanie N.
Systems and Control
Machine Learning
Optimization and Control
Gaussian Process (GP) regression is shown to be effective for learning unknown dynamics, enabling efficient and safety-aware control strategies across diverse applications. However, existing GP-based model predictive control (GP-MPC) methods either rely on approximations, thus lacking guarantees, or are overly conservative, which limits their practical utility. To close this gap, we present a sampling-based framework that efficiently propagates the model's epistemic uncertainty while avoiding conservatism. We establish a novel sample complexity result that enables the construction of a reachable set using a finite number of dynamics functions sampled from the GP posterior. Building on this, we design a sampling-based GP-MPC scheme that is recursively feasible and guarantees closed-loop safety and stability with high probability. Finally, we showcase the effectiveness of our method on two numerical examples, highlighting accurate reachable set over-approximation and safe closed-loop performance.
title Finite-Sample-Based Reachability for Safe Control with Gaussian Process Dynamics
topic Systems and Control
Machine Learning
Optimization and Control
url https://arxiv.org/abs/2505.07594