Show simple item record

dc.contributor.authorCao, Gen_NZ
dc.contributor.authorLai, Een_NZ
dc.contributor.authorAlam, Fen_NZ
dc.date.accessioned2017-02-13T01:59:46Z
dc.date.available2017-02-13T01:59:46Z
dc.date.copyright2017-01-04en_NZ
dc.identifier.citationIET Control Theory & Applications. doi: 10.1049/iet-cta.2016.1061
dc.identifier.issn1751-8644en_NZ
dc.identifier.issn1751-8652en_NZ
dc.identifier.urihttp://hdl.handle.net/10292/10321
dc.description.abstractModel predictive control (MPC) of an unknown system that is modelled by Gaussian process (GP) techniques is studied. Using GP, the variances computed during the modelling and inference processes allow us to take model uncertainty into account. The main issue in using MPC to control systems modelled by GP is the propagation of such uncertainties within the control horizon. In this study, two approaches to solve this problem, called GPMPC1 and GPMPC2, are proposed. With GPMPC1, the original stochastic model predictive control (SMPC) problem is relaxed to a deterministic non-linear MPC based on a basic linearised GP local model. The resulting optimisation problem, though non-convex, can be solved by the sequential quadratic programming. By incorporating the model variance into the state vector, an extended local model is derived. This model allows us to relax the non-convex MPC problem to a convex one which can be solved by an active-set method efficiently. The performance of both approaches is demonstrated by applying them to two trajectory tracking problems. Results show that both GPMPC1 and GPMPC2 produce effective controls but GPMPC2 is much more efficient computationally.
dc.publisherThe Institution of Engineering and Technology (IET)
dc.relation.urihttp://dx.doi.org/10.1049/iet-cta.2016.1061
dc.rightsThis paper is a postprint of a paper submitted to and accepted for publication in IET Control Theory & Applications and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library.
dc.titleGaussian Process Model Predictive Control of Unknown Nonlinear Systemsen_NZ
dc.typeJournal Article
dc.rights.accessrightsOpenAccessen_NZ
dc.identifier.doi10.1049/iet-cta.2016.1061en_NZ
pubs.elements-id219373
aut.relation.journalIET Control Theory & Applicationsen_NZ


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record