OBSTACLE AVOIDANCE TRAVEL CONTROL OF ROBOT VEHICLE USING NEURAL-NETWORK

This paper describes an intelligent travel control algorithm for a mob ile robot vehicle using neural networks, and proposes a method that re alizes path planning and generation of motion commands simultaneously. Smooth moving trajectories are controlled by the outputs of cascaded identification modules that have learned the dynamic characteristics o f a mobile robot vehicle with strong nonlinearities of both driving fo rce and steering angle. A system is adopted that mutually transforms t he absolute coordinate and dynamic coordinate. Because a consequence o f the coordinate transformation in this system is that the dynamic pos ition values are normally zero, it is possible to reduce greatly the n umber of training patterns and, at the same time, to be able to constr uct an environment similar to that in which a human being drives a veh icle. A travel control system, by which a mobile robot vehicle can mov e on a smooth traveling path and avoid obstacles, is created by introd ucing a danger function as an expression of static and dynamic obstacl es in an unstructured environment. Finally, the validity of the propos ed travel control system is confirmed by computer simulations.