An adaptive fuzzy approach to obstacle avoidance

Abstract

Reinforcement learning based on a new training method previously reported guarantees convergence and an almost complete set of rules. However, there are two shortcomings remained: 1) the membership functions of the input sensor readings are determined manually and take the same form; and 2) there are still a small number of blank rules needed to be manually inserted. To address these two issues, this paper proposes an adaptive fuzzy approach using a supervised learning method based on backpropagation to determine the parameters for the membership functions for each sensor reading. By having different input fuzzy sets, each sensor reading contributes differently in avoiding obstacles. Our simulations show that the proposed system converges rapidly to a complete set of rules, and if there are no conflicting input-output data pairs in the training sets, the proposed system performs collision-free obstacle avoidance.