Sensitivity analysis of a crawl gait multi-objective optimization system

• Autor(es): Oliveira, Miguel ; Silva, Pedro ; Santos, Cristina ; Costa, L.
• Data: 2013
• Identificador Persistente: http://hdl.handle.net/1822/26781
• Origem: RepositóriUM - Universidade do Minho
• Assunto(s): Evolutionary robotics; Multi-objective optimization; Genetic
• Tipo de Documento: Documento de conferência
• Idioma: Inglês

Descrição

This paper describes the analysis of a crawl gait multi-objective optimization system that combines bio-inspired Central Patterns Generators (CPGs) and a multi-objective evolutionary algorithm. In order to optimize the crawl gait, a multiobjective problem, an optimization system based on NSGAII allows to find a set of non-dominated solutions that correspond to different motor solutions The experimental results highlight the effectiveness of this multi-objective approach.