Título: Autonomous Control Using Soft Computing Paradigms
Autores: Oliveira, M. de; Figueiredo, M.; Gomide, F.; Romero, L.
Resumo: In this paper a genetic algorithm has been used to design of neurofuzzy systems as an alternative to traditional nonsupervised learning methods for neural networks. Fuzzy systems and neural networks also get improved behaviour with their symbioses. Here, we have integrated neural networks, fuzzy systems and evolutionary computing techniques to developed a control system for an automatically guided vehicle (AGV). The network learns to guide AGV to given goals without collisions. The Knowledge learned by the network can be extracted as if-then fuzzy rules and the number of rules, number of partitions and the shape and position of membership functions are easily determined.
Código DOI: 10.21528/CBRN1994-041
Artigo em PDF: CBRN1994-paper41.pdf
Arquivo BibTex: CBRN1994-paper41.bib