Hide metadata

dc.date.accessioned2020-04-22T19:39:03Z
dc.date.available2020-04-22T19:39:03Z
dc.date.created2019-07-24T12:44:39Z
dc.date.issued2019
dc.identifier.citationNygaard, Tønnes Frostad Martin, Charles Patrick Torresen, Jim Glette, Kyrre . Evolving Robots on Easy Mode: Towards a Variable Complexity Controller for Quadrupeds. Lecture Notes in Computer Science. 2019, 11454 LNCS, 616-632
dc.identifier.urihttp://hdl.handle.net/10852/74773
dc.description.abstractThe complexity of a legged robot’s environment or task can inform how specialised its gait must be to ensure success. Evolving specialised robotic gaits demands many evaluations—acceptable for computer simulations, but not for physical robots. For some tasks, a more general gait, with lower optimization costs, could be satisfactory. In this paper, we introduce a new type of gait controller where complexity can be set by a single parameter, using a dynamic genotype-phenotype mapping. Low controller complexity leads to conservative gaits, while higher complexity allows more sophistication and high performance for demanding tasks, at the cost of optimization effort. We investigate the new controller on a virtual robot in simulations and do preliminary testing on a real-world robot. We show that having variable complexity allows us to adapt to different optimization budgets. With a high evaluation budget in simulation, a complex controller performs best. Moreover, real-world evolution with a limited evaluation budget indicates that a lower gait complexity is preferable for a relatively simple environment.
dc.languageEN
dc.titleEvolving Robots on Easy Mode: Towards a Variable Complexity Controller for Quadrupeds
dc.typeJournal article
dc.creator.authorNygaard, Tønnes Frostad
dc.creator.authorMartin, Charles Patrick
dc.creator.authorTorresen, Jim
dc.creator.authorGlette, Kyrre
cristin.unitcode185,15,5,42
cristin.unitnameForskningsgruppe for robotikk og intelligente systemer
cristin.ispublishedtrue
cristin.qualitycode1
dc.identifier.cristin1712583
dc.identifier.bibliographiccitationinfo:ofi/fmt:kev:mtx:ctx&ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Lecture Notes in Computer Science&rft.volume=11454 LNCS&rft.spage=616&rft.date=2019
dc.identifier.jtitleLecture Notes in Computer Science
dc.identifier.volume11454 LNCS
dc.identifier.startpage616
dc.identifier.endpage632
dc.identifier.doihttps://doi.org/10.1007/978-3-030-16692-2_41
dc.identifier.urnURN:NBN:no-77881
dc.type.documentTidsskriftartikkel
dc.type.peerreviewedPeer reviewed
dc.source.issn0302-9743
dc.identifier.fulltextFulltext https://www.duo.uio.no/bitstream/handle/10852/74773/2/nygaard-evoapplications2019.pdf
dc.type.versionAcceptedVersion
dc.relation.projectNFR/240862


Files in this item

Appears in the following Collection

Hide metadata