Research on a New Path Planning Method for Mobile Robot

Abstract

Aim at the path planning problem of a mobile vehicle in an unknown environment, a new hybrid learning method is proposed, which is based on the fuzzy inference system and assisted by the combination of supervised learning and bionic automata, the bionic learning endows the robot the capabilities of self-learning and self-organization, the supervised learning is used to tune the input membership function of the fuzzy inference system, that avoid the expert knowledge's disadvantage of inaccurate estimation to the actual model. The simulation results show that the robot has learned the ability of obstacle avoidance and goal seeking and performs a better robustness in overcoming the local minima.