Mobile robot obstacle avoidance using short memory: a dynamic recurrent neuro-fuzzy approach

Abstract

This paper presents a dynamic recurrent neuro-fuzzy system (DRNFS) with short memory for obstacle avoidance of mobile robots in unknown environments. The DRNFS is developed to avoid obstacles through supervised learning from a set of obstacle-avoidance trajectories provided by a human driver. The feedback connections added in the second layer of the DRNFS make the system cope with temporal problems, which allows the robot to memorize the previous environment information. The parameters and structure of the DRNFS can be automatically optimized through the learning process. The parameter optimization is realized by the ordered derivative algorithm, and the structure simplification is completed by the fuzzy rules similarity measure. Simulation results are presented to verify the feasibility of the proposed system.