Automatic Operation of a Mobile Robot Using an RCE Network
Hisato Kobayashi and Katsuhiko Inagaki
Dept. of Electrical Engineering, College of Engineering, Hosei University, 3-7-2, Kajino-cho, Koganei-shi, Tokyo 184, Japan
This article describes an example using a neural net as a method of mobile robot operation. The method eliminates the need for characteristic equations of a mobile robot, but requires an exercise to some extent using adequate “patterns.” For accumulating experience of this practice, an RCE (restricted coulomb energy) network, or a pattern recognition-use neural network, is used. A simulation is conducted by driving a car into a garage. A man drives a car into a garage to create pattern data, which an RCE net is made to learn. After learning to some extent, it is allowed to put a car into a garage from an arbitrary initial point. The following are the descriptions of the results.