Fuzzy navigation for robotic manipulators

Abstract

This paper describes a novel navigation and obstacle avoidance system for robotic manipulators. The system is divided into separate fuzzy units which individually control the links of a manipulator. The rule base of each unit combines the repelling influence of obstacles with the attracting influence of the target position in a fuzzy way to generate actuating commands for the link. Owing to its simplicity and hence its short response time, the fuzzy navigator is especially suitable in on-line applications with strong real-time requirements. Furthermore, this approach allows obstacle avoidance in dynamic environments. The functioning of the fuzzy navigator with respect to robotic manipulators and results of real-world experiments are presented.