Approximate Robust Control of Uncertain ...
Document type :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
Title :
Approximate Robust Control of Uncertain Dynamical Systems
Author(s) :
Leurent, Edouard [Auteur]
Sequential Learning [SEQUEL]
Non-Asymptotic estimation for online systems [NON-A-POST]
RENAULT
Blanco, Yann [Auteur]
RENAULT
Efimov, Denis [Auteur]
Non-Asymptotic estimation for online systems [NON-A-POST]
Maillard, Odalric Ambrym [Auteur]
Sequential Learning [SEQUEL]
Sequential Learning [SEQUEL]
Non-Asymptotic estimation for online systems [NON-A-POST]
RENAULT
Blanco, Yann [Auteur]
RENAULT
Efimov, Denis [Auteur]

Non-Asymptotic estimation for online systems [NON-A-POST]
Maillard, Odalric Ambrym [Auteur]

Sequential Learning [SEQUEL]
Conference title :
Proc. MLITS Workshop at NeurIPS
City :
Montreal
Country :
Canada
Start date of the conference :
2018-12-07
HAL domain(s) :
Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Robotique [cs.RO]
Informatique [cs]/Robotique [cs.RO]
English abstract : [en]
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 ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.archives-ouvertes.fr/hal-01931744v2/document
- Open access
- Access the document
- http://arxiv.org/pdf/1903.00220
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-01931744v2/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-01931744v2/document
- Open access
- Access the document
- document
- Open access
- Access the document
- robust_control.pdf
- Open access
- Access the document
- 1903.00220
- Open access
- Access the document