Implementação de controle servo visual e coordenação visuo-motora em robôs manipuladores

Detalhes bibliográficos
Ano de defesa: 2006
Autor(a) principal: Dâmaso, Renato de Sousa
Orientador(a): Não Informado pela instituição
Banca de defesa: Não Informado pela instituição
Tipo de documento: Tese
Tipo de acesso: Acesso aberto
Idioma: por
Instituição de defesa: Universidade Federal do Espírito Santo
BR
Doutorado em Engenharia Elétrica
Centro Tecnológico
UFES
Programa de Pós-Graduação em Engenharia Elétrica
Programa de Pós-Graduação: Não Informado pela instituição
Departamento: Não Informado pela instituição
País: Não Informado pela instituição
Palavras-chave em Português:
Link de acesso: http://repositorio.ufes.br/handle/10/4106
Resumo: This work investigates strategies for controlling a manipulator to approach and grasp an object in its working environment, using visual feedback. Strategies that do not depend on models relating the visual space and the motor space of the manipulator are searched for. Results of the experimental implementations accomplished with an industrial and a prototyped manipulators are presented and analyzed. The main contribution is the proposition of a strategy to experimentally and incrementally build a visuo-motor model to manipulators with binocular visual feedback. Some meaningful characteristics of such a model are the demand of just a few experiments to "learn" the model and the adoption of two data structures to store the estimated parameters, one addressed by the end effector of the manipulator and the other addressed by the position of the object. The model thus obtained can be used to coordinate the manipulator during the execution of the task of interest. Such a system is capable to adapt the visuo-motor model in order to compensate for changes in the manipulator or the visual system, as well as to "remember" information learnt in previous experiments. The method here proposed, the incremental building of the visuo-motor model, is compared to a method of iterative adaptation of Jacobean matrix, and some conclusions are highlighted. As part of such a comparison, results of the implementation of these two methods using the same experimental setup are presented.