The present paper deals with the issues related to collision-free, time-optimal navigation of an autonomous car-like robot, in the presence of some moving obstacles. Two different approaches are developed for this purpose. In the first ap-proach, the motion planner is developed by using a conventional potential field method and a fuzzy logic-based navigator is proposed in Approach 2. In the present work, an attempt is made to develop a good knowledge base (KB) of an FLC auto-matically, by using a genetic algorithm (GA). During training, an optimal rule base of the FLC is determined by considering the importance of each rule. The effectiveness and computational complexity of both the approaches are compared through computer simulations.
CITATION STYLE
Hui, N. B., & Pratihar, D. K. (2006). Mobile robot navigation: Potential field approach vs. genetic-fuzzy system. In Advances in Soft Computing (Vol. 36, pp. 67–76). https://doi.org/10.1007/978-3-540-36266-1_7
Mendeley helps you to discover research relevant for your work.