Behavior Control for a Mobile Robot by Dual-Hierarchical Neural Network

Abstract

A mobile robot which behavior is controlled by a structured neural network and its learning algorithm are presented. The robot has 4 wheels and travels with 2 motors. Twelve sensors are used for detecting internal conditions and environmental changes. These sensor signals are input to the input layer of the network, and the network outputs motor control signals. The network model is divided into two sub-networks connected each other with short term memotys to process a series of behavior pattems. The robot can learn various habits by changing the patterns to be taught. For one example, we made our robot playcops-and-robbers game. Through training, the robots learned habits such as capture and escape.