Approximate Robust Control of Uncertain Dynamical Systems

Edouard Leurent 1, 2, 3 Yann Blanco 3 Denis Efimov 2 Odalric-Ambrym Maillard 1
1 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
2 NON-A - Non-Asymptotic estimation for online systems
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : This work studies the design of safe control policies for large-scale non-linear systems operating in uncertain environments. In such a case, the robust control framework is a principled approach to safety that aims to maximize the worst-case performance of a system. However, the resulting optimization problem is generally intractable for non-linear systems with continuous states. To overcome this issue, we introduce two tractable methods that are based either on sampling or on a conservative approximation of the robust objective. The proposed approaches are applied to the problem of autonomous driving.
Type de document :
Communication dans un congrès
32nd Conference on Neural Information Processing Systems (NeurIPS 2018) Workshop, Dec 2018, Montréal, Canada
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01931744
Contributeur : Edouard Leurent <>
Soumis le : jeudi 22 novembre 2018 - 22:56:33
Dernière modification le : samedi 24 novembre 2018 - 01:23:42

Fichier

robust_control.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01931744, version 1

Collections

Citation

Edouard Leurent, Yann Blanco, Denis Efimov, Odalric-Ambrym Maillard. Approximate Robust Control of Uncertain Dynamical Systems. 32nd Conference on Neural Information Processing Systems (NeurIPS 2018) Workshop, Dec 2018, Montréal, Canada. 〈hal-01931744〉

Partager

Métriques

Consultations de la notice

66

Téléchargements de fichiers

47