Self-learning neural control of a mobile robot
Bartosz Jerzy Janusz, Martin Riedmiller · 2002
Reinforcement learning is a promising paradigm for the training of intelligent controllers. The learning capabilities of a neural network based controller architecture are shown by its application to control a mobile robot in an unknown environment. Based on the multi-sensor information provided by four infrared sensors, the controller has to learn to avoid collisions, receiving only a final training signal of success or failure. The article further shows that simulation can be used to avoid the long real world training effort.