Humanoid robot gait on sloping floors using reinforcement learning

dc.contributor.authorSILVA, I. J.
dc.contributor.authorPERICO, D. H.
dc.contributor.authorHOMEM, T. P. D.
dc.contributor.authorVILAO, C. O.
dc.contributor.authorReinaldo Bianchi
dc.contributor.authorFlavio Tonidandel
dc.contributor.authorOrcidhttps://orcid.org/0000-0001-9097-827X
dc.contributor.authorOrcidhttps://orcid.org/0000-0003-0345-668X
dc.date.accessioned2022-01-12T21:59:24Z
dc.date.available2022-01-12T21:59:24Z
dc.date.issued2016-01-05
dc.description.abstract© Springer International Publishing AG 2016.Climbing ramps is an important ability for humanoid robots: ramps exist everywhere in the world, such as in accessibility ramps and building entrances. This works proposes the use of Reinforcement Learning to learn the action policy that will make a robot walk in an upright position, in a lightly sloped terrain. The proposed architecture of our system is a two-layer combination of the traditional gait generation control loop with a reinforcement learning component. This allows the use of an accelerometer to generate a correction for the gait, when the slope of the floor where the robot is walking changes. Experiments performed on a real robot showed that the proposed architecture is a good solution for the stability problem.
dc.description.firstpage228
dc.description.lastpage246
dc.description.volume619
dc.identifier.citationSILVA, I. J.; PERICO, D. H.; HOMEM, T. P. D.; VILAO, C. O.; BIANCHI, R.; TONIDANDEL, F. Humanoid robot gait on sloping floors using reinforcement learning. Communications in Computer and Information Science, v. 619, p. 228-246, 2016.
dc.identifier.doi10.1007/978-3-319-47247-8_14
dc.identifier.issn1865-0929
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/3928
dc.relation.ispartofCommunications in Computer and Information Science
dc.rightsAcesso Restrito
dc.subject.otherlanguageGait pattern stabilization
dc.subject.otherlanguageHumanoid robots
dc.subject.otherlanguageReinforcement learning
dc.titleHumanoid robot gait on sloping floors using reinforcement learning
dc.typeArtigo de evento
fei.scopus.citations2
fei.scopus.eid2-s2.0-84992700501
fei.scopus.subjectAction policies
fei.scopus.subjectGait generation
fei.scopus.subjectGait pattern
fei.scopus.subjectHumanoid robot
fei.scopus.subjectProposed architectures
fei.scopus.subjectSloped terrains
fei.scopus.subjectStability problem
fei.scopus.subjectUpright position
fei.scopus.updated2024-07-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84992700501&origin=inward
Arquivos
Coleções