Learning to avoid moving obstacles optimally for mobile robots using a genetic-fuzzy approach

Abstract

The task in a motion planning problem for a mobile robot is to find an obstacle-free path between a starting and a destination point, which will require the minimum possible time of travel. Although there exists many studies involving classical methods and using fuzzy logic controllers (FLCs), they are either computationally extensive or they do not attempt to find optimal controllers. The proposed genetic-fuzzy approach optimizes the travel time of a robot off-line by simultanously finding an optimal fuzzy rule base and optimal membership function distributions describing various values of condition and action variables of fuzzy rules. A mobile robot can then use this optimal FLC on-line to navigate in the presence of moving obstacles. The results of this study on a number of problems show that the proposed genetic-fuzzy approach can produce efficient rules and membership functions of an FLC for controlling the motion of a robot among moving obstacles.