Cristin-resultat-ID: 1936452
Sist endret: 5. oktober 2021, 10:45
NVI-rapporteringsår: 2021
Resultat
Vitenskapelig artikkel
2021

Safe Learning for Control using Control Lyapunov Functions and Control Barrier Functions: A Review

Bidragsytere:
  • Akhil Sadanandan Anand
  • Katrine Seel
  • Vilde Benoni Gjærum
  • Anne Håkansson
  • Haakon Robinson og
  • Aya Saad

Tidsskrift

Procedia Computer Science
ISSN 1877-0509
e-ISSN 1877-0509
NVI-nivå 1

Om resultatet

Vitenskapelig artikkel
Publiseringsår: 2021
Publisert online: 2021
Trykket: 2021
Volum: 192
Sider: 3987 - 3997
Open Access

Klassifisering

Vitenskapsdisipliner

Informasjons- og kommunikasjonsteknologi

Emneord

Control Barrier Functions • Safe learning • Robust AI • Control Lyapunov Functions

Beskrivelse Beskrivelse

Tittel

Safe Learning for Control using Control Lyapunov Functions and Control Barrier Functions: A Review

Sammendrag

Real-world autonomous systems are often controlled using conventional model-based control methods. But if accurate models of a system are not available, these methods may be unsuitable. For many safety-critical systems, such as robotic systems, a model of the system and a control strategy may be learned using data. When applying learning to safety-critical systems, guaranteeing safety during learning as well as testing/deployment is paramount. A variety of different approaches for ensuring safety exists, but the published works are cluttered and there are few reviews that compare the latest approaches. This paper reviews two promising approaches on guaranteeing safety for learning-based robust control of uncertain dynamical systems, which are based on control barrier functions and control Lyapunov functions. While control barrier functions provide an option to incorporate safety in terms of constraint satisfaction, control Lyapunov functions are used to define safety in terms of stability. This review categorises learning-based methods that use control barrier functions and control Lyapunov functions into three groups, namely reinforcement learning, online and offline supervised learning. Finally, the paper presents a discussion of the suitability of the different methods for different applications.

Bidragsytere

Akhil Sadanandan Anand

  • Tilknyttet:
    Forfatter
    ved Institutt for teknisk kybernetikk ved Norges teknisk-naturvitenskapelige universitet

Katrine Seel

  • Tilknyttet:
    Forfatter
    ved Institutt for teknisk kybernetikk ved Norges teknisk-naturvitenskapelige universitet

Vilde Benoni Gjærum

  • Tilknyttet:
    Forfatter
    ved Institutt for teknisk kybernetikk ved Norges teknisk-naturvitenskapelige universitet

Anne Håkansson

  • Tilknyttet:
    Forfatter
    ved Institutt for informatikk ved UiT Norges arktiske universitet

Haakon Robinson

  • Tilknyttet:
    Forfatter
    ved Institutt for teknisk kybernetikk ved Norges teknisk-naturvitenskapelige universitet
1 - 5 av 6 | Neste | Siste »