Show simple item record

dc.contributor.authorKormushev, P.
dc.contributor.authorUğurlu, Regaip Barkan
dc.contributor.authorCaldwell, D. G.
dc.contributor.authorTsagarakis, N. G.
dc.date.accessioned2020-09-02T06:19:27Z
dc.date.available2020-09-02T06:19:27Z
dc.date.issued2019-01
dc.identifier.issn0929-5593en_US
dc.identifier.urihttp://hdl.handle.net/10679/6874
dc.identifier.urihttps://link.springer.com/article/10.1007/s10514-018-9697-6
dc.description.abstractModern humanoid robots include not only active compliance but also passive compliance. Apart from improved safety and dependability, availability of passive elements, such as springs, opens up new possibilities for improving the energy efficiency. With this in mind, this paper addresses the challenging open problem of exploiting the passive compliance for the purpose of energy efficient humanoid walking. To this end, we develop a method comprising two parts: an optimization part that finds an optimal vertical center-of-mass trajectory, and a walking pattern generator part that uses this trajectory to produce a dynamically-balanced gait. For the optimization part, we propose a reinforcement learning approach that dynamically evolves the policy parametrization during the learning process. By gradually increasing the representational power of the policy parametrization, it manages to find better policies in a faster and computationally efficient way. For the walking generator part, we develop a variable-center-of-mass-height ZMP-based bipedal walking pattern generator. The method is tested in real-world experiments with the bipedal robot COMAN and achieves a significant 18% reduction in the electric energy consumption by learning to efficiently use the passive compliance of the robot.en_US
dc.description.sponsorshipEU project AMARSi
dc.language.isoengen_US
dc.publisherSpringer Natureen_US
dc.relation.ispartofAutonomous Robots
dc.rightsopenAccess
dc.titleLearning to exploit passive compliance for energy-efficient gait generation on a compliant humanoiden_US
dc.typeArticleen_US
dc.description.versionPublisher version
dc.peerreviewedyesen_US
dc.publicationstatusPublisheden_US
dc.contributor.departmentÖzyeğin University
dc.contributor.authorID(ORCID 0000-0002-9124-7441 & YÖK ID 241209) Uğurlu, Barkan
dc.contributor.ozuauthorUğurlu, Regaip Barkan
dc.identifier.volume43en_US
dc.identifier.issue1en_US
dc.identifier.startpage79en_US
dc.identifier.endpage95en_US
dc.identifier.wosWOS:000456142200005
dc.identifier.doi10.1007/s10514-018-9697-6en_US
dc.subject.keywordsBipedal walkingen_US
dc.subject.keywordsEnergy efficiencyen_US
dc.subject.keywordsReinforcement learningen_US
dc.subject.keywordsPassive complianceen_US
dc.identifier.scopusSCOPUS:2-s2.0-85041920871
dc.contributor.authorMale1
dc.relation.publicationcategoryArticle - International Refereed Journal - Institution Academic


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record


Share this page