Fuzzy logic and the Pittsburgh classifier system for mobile robot control

We report on experiments designed to highlight the strengths and weaknesses of an autonomous rule acquisition algorithm for the fuzzy controller of a simulated mobile robot. The algorithm is a Pittsburghstyle Fuzzy Classifier System. The highly cross-coupled and co-operative nature of fuzzy inference systems makes autonomous creation of an optimal rule-base a tough proposition. However, our results show that this architecture can regularly find highperformance solutions that eluded the designers of a hand-coded fuzzy controller.

• Type: Conference
• Year: 2003
• Where: EUSFLAT
• Authors: Anthony G. Pipe, Brian Carse
• Keywords: EUSFLAT 2003, EUSFLAT 2007, Fuzzy Controller, Hand-coded Fuzzy Controller, Pittsburghstyle Fuzzy Classifier