Learning robot reaching motions by demonstration using nonlinear autoregressive models

Página do item simplificado
dc.creatorRafael Francisco dos Santos
dc.creatorGuilherme Pereira
dc.creatorLuis Antonio Aguirre
dc.date.accessioned2025-04-22T13:59:53Z
dc.date.accessioned2025-09-08T23:25:53Z
dc.date.available2025-04-22T13:59:53Z
dc.date.issued2018
dc.identifier.doihttps://doi.org/10.1016/j.robot.2018.06.006
dc.identifier.issn0921-8890
dc.identifier.urihttps://hdl.handle.net/1843/81729
dc.languageeng
dc.publisherUniversidade Federal de Minas Gerais
dc.relation.ispartofRobotics and autonomous systems
dc.rightsAcesso Restrito
dc.subjectSistemas dinâmicos
dc.subjectSistemas de controle
dc.subject.otherA new method for learning robot reaching motions from demonstrations, Dynamic system identified using Nonlinear Autoregressive (NAR) models, Good learning performance with low control efforts, Evaluated with mobile and manipulator robots
dc.subject.otherLearning by demonstration
dc.subject.otherNonlinear autoregressive models
dc.subject.otherDynamical systems
dc.subject.otherFixed poin
dc.titleLearning robot reaching motions by demonstration using nonlinear autoregressive models
dc.typeArtigo de periódico
local.citation.epage195
local.citation.spage182
local.citation.volume107
local.description.resumoThis paper presents NAR-RM, a method for learning robot reaching motions from a set of demonstrations using Nonlinear AutoRegressive (NAR) polynomial models. Reaching motions are modeled as solutions to autonomous discrete-time nonlinear dynamical systems, so that the movements started near the data of the demonstrations follow the trained trajectories and always reach and stop at the target. Since NAR models obtained using standard system identification techniques do not always adequately model the reaching motions, in this paper we present a method that uses a least-squares estimator with constraints to impose the location of fixed points in the model. With the imposition of new fixed points it is possible to change the location of the original fixed points of the model, thus allowing the learning of stable reaching motions. We evaluate our method using a library of human handwriting motions, a mobile robot and an industrial manipulator.
local.publisher.countryBrasil
local.publisher.departmentENG - DEPARTAMENTO DE ENGENHARIA ELÉTRICA
local.publisher.departmentENG - DEPARTAMENTO DE ENGENHARIA ELETRÔNICA
local.publisher.initialsUFMG
local.url.externahttps://www.sciencedirect.com/science/article/pii/S092188901730814X

Arquivos

Licença do pacote

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
License.txt
Tamanho:
1.99 KB
Formato:
Plain Text
Descrição:
Baixar

Coleções

Artigo de Periódico

Logo UFMG