Backpropagation learning in real autonomous mobile robot using proximal and distal evaluation of behaviour
暂无分享,去创建一个
Murase et al. (1998) have previously proposed a backpropagation algorithm for the development of behaviour based autonomous robots. Although the method was proved applicable to a real mobile robot, there existed some problems such as the convergence to the local minimum and the variability among trials. In order to improve the performance, we introduce a new criterion for selecting the training data set. Coefficients of a multilayer neural network, that determined the sensor-motor reflex of the robot, were first set randomly, and the robot was allowed to behave in 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 behaviour that occurred after the sampling by using an evaluation function. The behaviour was evaluated by both immediate response to near-by obstacles and long-range navigation capability. The new criterion provided a much faster and stable convergence than the previous one, and far better than the conventional genetic algorithm.
[1] Kazuyuki Murase,et al. Back-Propagation Learning of Autonomous Behaviour: A Mobile Robot Khepera Took a Lesson from the Future Consequences , 1998, ICES.
[2] Francesco Mondada,et al. Evolution of homing navigation in a real mobile robot , 1996, IEEE Trans. Syst. Man Cybern. Part B.
[3] Geoffrey E. Hinton,et al. Learning representations by back-propagating errors , 1986, Nature.
[4] John R. Koza,et al. Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.