Behavior control for a mobile robot by dual-hierarchical neural network.

概要

論文の詳細を見る
We are researching ways to use neurocomputers that have highly parallel data processing and learning functions for robot control. There are three requirements for the robots: The robot must be easy to control, but the neural network must be sophisticated enough to handle multiple sensor input. Second, the robot must be able to learn easily. Third, the robot must be able to adjust its own actions. We developed a new mobile mechanism, created a network model, and increased the network learning speed. Sensor signals from the robot are input to the neural network. The network outputs a certain reaction pattern in response to the sensor input. Then the reaction is refined to an ideal one using training patterns. A robot can change its reaction pattern by changing the training pattern. We created two robots with different action patterns: one chases other robots, the other runs away from other robots. We confirmed that a neurocomputer can effectively control robot actions.