Back-propagation learning of autonomous behavior: A mobile robot Khepera took a lesson from the future consequences

A modified back-propagation (BP) algorithm for the development of autonomous robots was proposed, and applied to a real mobile robot Khepera. Coefficients of a multi-layered neural network (NN), that determined the sensor-motor reflex of the robot, were first set randomly, and the robot was allowed to behave in an environment for some time. Sets of the sensor-motor values were continuously sampled during the free-moving period, and each set was evaluated by the behavior that occurred after the sampling by using an evaluation function. The set obtained the highest score was selected for each sensor pattern, and used to train the NN with BP. By repeating the above procedures, the robot obtained the adaptive behavior for the given environment in accordance with the evaluation function. The time needed for Khepera to acquire the ability of navigation was approximately one tenth of the conventional genetic evolution.