Design of a genetic-fuzzy system for planning optimal path and gait simultaneously of a six-legged robot

Abstract

This paper describes a genetic-fuzzy system used for generating optimal path and gait simultaneously of a six-legged robot. No single traditional approach is found to be successful in handling this complicated task. Moreover, the conventional methods are computationally expensive and the generated path and gaits may not be optimal in any sense. Thus, there is still a need for the development of an efficient and computationally faster algorithm for solving this problem. In the proposed algorithm, optimal path and gaits are generated by fuzzy logic controllers (FLCs) and optimized FLCs are found by genetic algorithms (GAs). Design of an optimized FLC (only rule base optimization) involves the problem of dealing with discrete variables and GA is an efficient tool for this purpose. The actual optimization is done off-line and the hexapod can use these GA-tuned FLCs to navigate in real-world scenarios, in an optimal sense.