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
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.
Complete list of metadatas
Contributor : Edouard Leurent <>
Submitted on : Thursday, February 28, 2019 - 8:17:16 PM
Last modification on : Friday, March 22, 2019 - 1:37:16 AM
Long-term archiving on : Wednesday, May 29, 2019 - 5:45:44 PM


Files produced by the author(s)


  • HAL Id : hal-01931744, version 2
  • ARXIV : 1903.00220



Edouard Leurent, Yann Blanco, Denis Efimov, Odalric-Ambrym Maillard. Approximate Robust Control of Uncertain Dynamical Systems. NeurIPS 2018 - 32nd Conference on Neural Information Processing Systems, Dec 2018, Montréal, Canada. ⟨hal-01931744v2⟩



Record views


Files downloads