Vis enkel innførsel

dc.contributor.authorSadanandan Anand, Akhil
dc.contributor.authorSeel, Katrine
dc.contributor.authorGjærum, Vilde Benoni
dc.contributor.authorHåkansson, Anne
dc.contributor.authorRobinson, Haakon
dc.contributor.authorSaad, Aya
dc.date.accessioned2022-01-03T12:43:11Z
dc.date.available2022-01-03T12:43:11Z
dc.date.issued2021-10-01
dc.description.abstractReal-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.en_US
dc.identifier.citationSadanandan Anand A, Seel K, Gjærum V, Håkansson A, Robinson H, Saad A. Safe Learning for Control using Control Lyapunov Functions and Control Barrier Functions: A Review. Procedia Computer Science. 2021;192:3987-3997en_US
dc.identifier.cristinIDFRIDAID 1936452
dc.identifier.doi10.1016/j.procs.2021.09.173
dc.identifier.issn1877-0509
dc.identifier.urihttps://hdl.handle.net/10037/23579
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.relation.journalProcedia Computer Science
dc.relation.projectIDNorges forskningsråd: 295920en_US
dc.relation.projectIDinfo:eu-repo/grantAgreement/RCN/BALANSE/295920/Norway/IDUN - fra PhD til Professor Kjønnsbalanse i toppstillinger og forskningsledelse på Fakultet for Informasjonsteknologi og Elektroteknikk//en_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2021 The Author(s)en_US
dc.subjectVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550en_US
dc.subjectVDP::Technology: 500::Information and communication technology: 550en_US
dc.subjectControl Barrier Functions / Control Barrier Functionsen_US
dc.subjectControl Lyapunov Functions / Control Lyapunov Functionsen_US
dc.subjectRobust AI / Robust AIen_US
dc.subjectSafe learning / Safe learningen_US
dc.titleSafe Learning for Control using Control Lyapunov Functions and Control Barrier Functions: A Reviewen_US
dc.type.versionpublishedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel