Show simple item record

dc.contributor.authorCaldwell, Jack
dc.contributor.authorMarshall, Joshua A.
dc.date.accessioned2021-10-24T13:41:36Z
dc.date.available2021-10-24T13:41:36Z
dc.date.issued2021-09
dc.identifier.citationJ. Caldwell and J. A. Marshall. Towards efficient learning-based model predictive control via feedback linearization and Gaussian process regression. In Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic, September 27, 2021.en
dc.identifier.urihttp://hdl.handle.net/1974/29514
dc.description.abstractThis paper presents a learning-based Model Pre- dictive Control (MPC) methodology incorporating nonlinear predictions with robotics applications in mind. In particular, MPC is combined with feedback linearization for computational efficiency and Gaussian Process Regression (GPR) is used to model unknown system dynamics and nonlinearities. In this method, MPC predicts future states by leveraging a GPR model and optimizes a sequence of inputs over feedback linearized states. The controller was tested in simulation by using a two- link planar robot in the presence of model uncertainty. With respect to trajectory-tracking error, the proposed controller outperformed a conventional Proportional-Derivative Inverse Dynamics controller and a GPR-augmented version. Although a fully nonlinear MPC formulation achieved slightly better performance, the proposed controller had an average control calculation time that was 82× faster.en
dc.language.isoenen
dc.publisherIEEEen
dc.relationStrategic Partnership Grants for Networksen
dc.subjectcontrol systemsen
dc.subjectfeedback linearizationen
dc.subjectmodel predictive controlen
dc.subjectGaussian process regressionen
dc.subjectmachine learningen
dc.titleTowards efficient learning-based model predictive control via feedback linearization and Gaussian process regressionen
dc.typejournal articleen
dc.identifier.doi10.1109/IROS51168.2021.9636755
project.funder.identifierhttp://dx.doi.org/10.13039/501100000038en
project.funder.nameNatural Sciences and Engineering Research Council of Canadaen
oaire.awardNumberNETGP 508451-17en
oaire.awardURIhttps://ncrn-rcrc.mcgill.caen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record