Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs

Leurent, Edouard; Efimov, Denis; Maillard, Odalric-Ambrym

Document type :

Communication dans un congrès avec actes

Title :

Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs

Author(s) :

Leurent, Edouard [Auteur]
RENAULT
Finite-time control and estimation for distributed systems [VALSE]
Sequential Learning [SEQUEL]
Efimov, Denis [Auteur]

Finite-time control and estimation for distributed systems [VALSE]
Maillard, Odalric-Ambrym [Auteur]

Scool [Scool]
Sequential Learning [SEQUEL]

Conference title :

NeurIPS 2020 - 34th Conference on Neural Information Processing Systems

City :

Vancouver / Virtual

Country :

Canada

Start date of the conference :

2020-12-06

HAL domain(s) :

Informatique [cs]/Apprentissage [cs.LG]
Informatique [cs]/Automatique

English abstract : [en]

We consider the problem of robust and adaptive model predictive control (MPC) of a linear system, with unknown parameters that are learned along the way (adaptive), in a critical setting where failures must be prevented ...
Show more >We consider the problem of robust and adaptive model predictive control (MPC) of a linear system, with unknown parameters that are learned along the way (adaptive), in a critical setting where failures must be prevented (robust). This problem has been studied from different perspectives by different communities. However, the existing theory deals only with the case of quadratic costs (the LQ problem), which limits applications to stabilisation and tracking tasks only. In order to handle more general (non-convex) costs that naturally arise in many practical problems, we carefully select and bring together several tools from different communities, namely non-asymptotic linear regression, recent results in interval prediction, and tree-based planning. Combining and adapting the theoretical guarantees at each layer is non trivial, and we provide the first end-to-end suboptimality analysis for this setting. Interestingly, our analysis naturally adapts to handle many models and combines with a data-driven robust model selection strategy, which enables to relax the modelling assumptions. Last, we strive to preserve tractability at any stage of the method, that we illustrate on two challenging simulated environments.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Files

https://hal.inria.fr/hal-03004060/document
Open access
Access the document

http://arxiv.org/pdf/2002.10816
Open access
Access the document

https://hal.inria.fr/hal-03004060/document
Open access
Access the document

https://hal.inria.fr/hal-03004060/document
Open access
Access the document

Robust-Adaptive Control of Linear Systems: ... BibTeX CSV Excel RIS

Files

Robust-Adaptive Control of Linear Systems: ...

BibTeX

CSV

Excel

RIS