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

Most of the obstacle avoidance techniques do not consider the robot orientation or its nal 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 eld method as a obstacle avoidance and a nal position and orientation acquiring method, which introduces a normalized two-dimensional vector eld for navigation. To obtain the optimal vector eld, a function approximator is used, and is trained by evolutionary programming. Two kinds of vector elds are trained, one for the nal posture acquisition, and the other for obstacle avoidance. Computer simulations and real experiments are carried out for a fast moving mobile robot to demonstrate the e ectiveness of the proposed scheme.

• Type: Conference
• Year: 1998
• Where: SEAL
• Authors: Yong-Jae Kim, Dong-Han Kim, Jong-Hwan Kim
• Keywords: Machine Learning, Obstacle Avoidance, Obstacle Avoidance Techniques, SEAL 1998, Vector Elds