Cristin-resultat-ID: 1645962
Sist endret: 2. januar 2019, 08:56
NVI-rapporteringsår: 2018
Resultat
Vitenskapelig artikkel
2018

Machine Learning in Control Systems An Overview of state of the art

Bidragsytere:
  • Signe Moe
  • Anne Marthine Rustad og
  • Kristian Gaustad Hanssen

Tidsskrift

Lecture Notes in Computer Science (LNCS)
ISSN 0302-9743
e-ISSN 1611-3349
NVI-nivå 1

Om resultatet

Vitenskapelig artikkel
Publiseringsår: 2018
Volum: 11311
Sider: 250 - 265

Importkilder

Scopus-ID: 2-s2.0-85058416238

Beskrivelse Beskrivelse

Tittel

Machine Learning in Control Systems An Overview of state of the art

Sammendrag

Control systems are in general based on the same structure, building blocks and physics-based models of the dynamic system regardless of application, and can be mathematically analyzed w.r.t. stability, robustness and so on given certain assumptions. Machine learning methods (ML), on the other hand, are highly flexible and adaptable methods but are not subject to physic-based models and therefore lack mathematical analysis. This paper presents state of the art results using ML in the control system. Furthermore, a case study is presented where a neural network is trained to mimic a feedback linearizing speed controller for an autonomous ship. The neural network outperforms the traditional controller in case of modeling errors and measurement noise.

Bidragsytere

Signe Moe

  • Tilknyttet:
    Forfatter
    ved Mathematics and Cybernetics ved SINTEF AS

Anne Marthine Rustad

  • Tilknyttet:
    Forfatter
    ved Mathematics and Cybernetics ved SINTEF AS

Kristian Gaustad Hanssen

Bidragsyterens navn vises på dette resultatet som Kristian Gaustad Hanssen
  • Tilknyttet:
    Forfatter
    ved Mathematics and Cybernetics ved SINTEF AS
1 - 3 av 3