A Simple and Efficient Sampling-based Algorithm for General Reachability Analysis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

A Simple and Efficient Sampling-based Algorithm for General Reachability Analysis

Thomas Lew
  • Fonction : Auteur
  • PersonId : 1119432
Lucas Janson
  • Fonction : Auteur
Marco Pavone
  • Fonction : Auteur
  • PersonId : 1119402

Résumé

In this work, we analyze an efficient sampling-based algorithm for general-purpose reachability analysis, which remains a notoriously challenging problem with applications ranging from neural network verification to safety analysis of dynamical systems. By sampling inputs, evaluating their images in the true reachable set, and taking their-padded convex hull as a set estimator, this algorithm applies to general problem settings and is simple to implement. Our main contribution is the derivation of asymptotic and finite-sample accuracy guarantees using random set theory. This analysis informs algorithmic design to obtain an-close reachable set approximation with high probability, provides insights into which reachability problems are most challenging, and motivates safety-critical applications of the technique. On a neural network verification task, we show that this approach is more accurate and significantly faster than prior work. Informed by our analysis, we also design a robust model predictive controller that we demonstrate in hardware experiments.
Fichier principal
Vignette du fichier
lew22a.pdf (2.99 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04305268 , version 1 (24-11-2023)

Identifiants

Citer

Thomas Lew, Lucas Janson, Riccardo Bonalli, Marco Pavone. A Simple and Efficient Sampling-based Algorithm for General Reachability Analysis. Learning for Dynamics and Control Conference 2022, 2022, Stanford (CA), United States. ⟨hal-04305268⟩
13 Consultations
10 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More