Evolutionary Programming-Based Uni-vector Field Method for Fast Mobile Robot Navigation

Abstract

A novel obstacle avoidance and a final position and orientation acquiring methods are developed and implemented for fast moving mobile robots. Most of the obstacle avoidance techniques do not consider the robot orientation or its final angle at the target position. These techniques deal with the robot position only and are independent of its orientation and velocity. To solve these problems we propose a novel uni-vector field method, which introduces a normalized two-dimensional vector field for navigation. To obtain the optimal vector field, a function approximator is used, and is trained by evolutionary programming. Two kinds of vector fields are trained, one for the final posture acquisition, and the other for obstacle avoidance. Computer simulations and real experiments are carried out to demonstrate the effectiveness of the proposed scheme.