Please use this identifier to cite or link to this item:
http://repositorio.unitau.br/jspui/handle/20.500.11874/1775
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Gonçalves, João Bosco | pt_BR |
dc.contributor.author | Zampieri, Douglas Eduardo | pt_BR |
dc.date.accessioned | 2019-09-12T16:25:56Z | - |
dc.date.available | 2019-09-12T16:25:56Z | - |
dc.date.issued | 2003 | - |
dc.citation.volume | 25 | pt_BR |
dc.citation.issue | 1 | pt_BR |
dc.citation.spage | 69 | - |
dc.citation.epage | 78 | - |
dc.identifier.doi | 10.1590/S1678-58782003000100010 | pt_BR |
dc.identifier.issn | 16785878 | - |
dc.identifier.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-0037765530&doi=10.1590%2fS1678-58782003000100010&partnerID=40&md5=264f2141b69198b07bb946fba8a90b4a | - |
dc.identifier.uri | http://repositorio.unitau.br/jspui/handle/20.500.11874/1775 | - |
dc.description.abstract | The main objective of this paper is to use a recurrent neural network (RNN) to determine the trunk motion for a biped-walking machine, based on the zero-moment point (ZMP) criterion. ZMP criterion can be used to plan a stable gait for a biped-walking machine that has a trunk (inverted pendulum). So, a RNN is trained to determine a compensative trunk motion that makes the actual ZMP get closer to the planned ZMP. In this context, an identification scheme is presented to obtain the vector of parameters of the RNN. A first order standard back-propagation with momentum (BPM) is used to adjust free parameters for the network. Artificial neural network brings up important features for function approximation. This was the main reason to use an RNN to determine the trunk motion. The proposed scheme is simulated on a 10-degree-of-freedom biped robot. The results confirm the convergence of the proposed scheme, proving this is a new way to solve this classical problem in the biped-walking machine area. | en |
dc.description.provenance | Made available in DSpace on 2019-09-12T16:25:56Z (GMT). No. of bitstreams: 0 Previous issue date: 2003 | en |
dc.language | Inglês | pt_BR |
dc.publisher | Brazilian Society of Mechanical Sciences and Engineering | - |
dc.relation.ispartof | Journal of the Brazilian Society of Mechanical Sciences and Engineering | - |
dc.rights | Acesso Aberto | pt_BR |
dc.rights.uri | https://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.source | Scopus | pt_BR |
dc.subject.other | Artificial neural network | en |
dc.subject.other | Gait synthesis | en |
dc.subject.other | Postural stability | en |
dc.subject.other | Robot biped | en |
dc.subject.other | Zero moment point | en |
dc.subject.other | Backpropagation | en |
dc.subject.other | Gait analysis | en |
dc.subject.other | Robots | en |
dc.subject.other | Vectors | en |
dc.subject.other | Zero moment point (ZMP) | en |
dc.subject.other | Recurrent neural networks | en |
dc.title | Recurrent neural network approaches for biped walking robot based on zero-moment point criterion | en |
dc.type | Artigo de Periódico | pt_BR |
dc.description.affiliation | Gonçalves, J.B., Dept. of Elec. Engineering (DEE), Univ. of Taubaté (UNITAU), Rua Daniel Danelli, s/n, 12060-440 Taubaté, SP, Brazil | - |
dc.description.affiliation | Zampieri, D.E., School of Mechanical Engineering, Dept. of Compl. Mechanics (DMC), Stt. Univ. of Campinas (UNICAMP), Postal Number 6122, 13083-970 Campinas, SP, Brazil | - |
dc.identifier.scopus | 2-s2.0-0037765530 | - |
dc.contributor.scopus | 16030826000 | pt_BR |
dc.contributor.scopus | 6602840741 | pt_BR |
Appears in Collections: | Artigos de Periódicos |
Files in This Item:
There are no files associated with this item.
This item is licensed under a Creative Commons License