dc.date.accessioned | 2018-08-12T09:42:24Z | |
dc.date.available | 2018-08-12T09:42:24Z | |
dc.date.created | 2017-09-07T17:33:08Z | |
dc.date.issued | 2017 | |
dc.identifier.citation | Nygaard, Tønnes Frostad Samuelsen, Eivind Glette, Kyrre . Overcoming initial convergence in multi-objective evolution of robot control and morphology using a two-phase approach. Lecture Notes in Computer Science. 2017, 10199 LNCS(Part I), 825-836 | |
dc.identifier.uri | http://hdl.handle.net/10852/62862 | |
dc.description.abstract | Co-evolution of robot morphologies and control systems is a new and interesting approach for robotic design. However, the increased size and ruggedness of the search space becomes a challenge, often leading to early convergence with sub-optimal morphology-controller combinations. Further, mutations in the robot morphologies tend to cause large perturbations in the search, effectively changing the environment, from the controller’s perspective. In this paper, we present a two-stage approach to tackle the early convergence in morphology-controller co-evolution. In the first phase, we allow free evolution of morphologies and controllers simultaneously, while in the second phase we re-evolve the controllers while locking the morphology. The feasibility of the approach is demonstrated in physics simulations, and later verified on three different real-world instances of the robot morphologies. The results demonstrate that by introducing the two-phase approach, the search produces solutions which outperform the single co-evolutionary run by over 10%.
© 2017 Springer Verlag | en_US |
dc.language | EN | |
dc.publisher | Springer Verlag | |
dc.title | Overcoming initial convergence in multi-objective evolution of robot control and morphology using a two-phase approach | en_US |
dc.type | Journal article | en_US |
dc.creator.author | Nygaard, Tønnes Frostad | |
dc.creator.author | Samuelsen, Eivind | |
dc.creator.author | Glette, Kyrre | |
cristin.unitcode | 185,15,5,42 | |
cristin.unitname | Forskningsgruppe for robotikk og intelligente systemer | |
cristin.ispublished | true | |
cristin.fulltext | postprint | |
cristin.qualitycode | 1 | |
dc.identifier.cristin | 1491902 | |
dc.identifier.bibliographiccitation | info: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=10199 LNCS&rft.spage=825&rft.date=2017 | |
dc.identifier.jtitle | Lecture Notes in Computer Science | |
dc.identifier.volume | 10199 LNCS | |
dc.identifier.issue | Part I | |
dc.identifier.startpage | 825 | |
dc.identifier.endpage | 836 | |
dc.identifier.doi | http://dx.doi.org/10.1007/978-3-319-55849-3_53 | |
dc.identifier.urn | URN:NBN:no-65453 | |
dc.type.document | Tidsskriftartikkel | en_US |
dc.type.peerreviewed | Peer reviewed | |
dc.source.issn | 0302-9743 | |
dc.identifier.fulltext | Fulltext https://www.duo.uio.no/bitstream/handle/10852/62862/2/nygaard-evorobot2017.pdf | |
dc.type.version | AcceptedVersion | |