Intelligent Control Concerning Obstacle Avoidance of Mobile Robot
Hideo Nagata*, and Takeshi Tsuchiya**
* Mitsubishi Electric Corporation, 2-2-3, Marunouchi, Chiyoda-ku, Tokyo, 100 Japan
** Faculty of Engineering, Hokkaido University, Nishi-8-chome, Kita-13-jo, Kita-ku, Sapporo, Hokkaido, 060 Japan
This paper describes a collision avoidance method for a mobile robot operated by the operational histories of human operators as well as by a computerized fuzzy controller. In order to cope with a changeable environment, a mobile robot has to provide higher planning which watches for the success or failure of a plan and provides feedback of perception. in this paper,a mobile robot makes a judgment based on relative positions and speeds between the robot and obstacles, and predicts a next environment to some extent. Moreover, the mobile robot tries to acquire skill-based intelligence through a layered neural network. Some results of computer simulations are shown to ascertain the effectiveness of this two-stage control. Finally, we propose layered pathplanning in terms of thinking levels which take into consideration the dynamics of a robot.