RECOGNITION OF MANIPULATED OBJECTS BY MOTOR LEARNING WITH MODULAR ARCHITECTURE NETWORKS

For recognition and control of multiple manipulated objects, we present two learning schemes for neural-network controllers based on feedback-error-learning and modular architecture. In both schemes, the network consists of a recognition network and modular control networks. In the first scheme, a Gating Network is trained to acquire object-specific representations for recognition of a number of objects (or sets of objects). In the second scheme, an Estimation Network is trained to acquire function-specific, rather than object-specific, representations which directly estimate physical parameters. Both recognition networks are trained to identify manipulated objects using somatic and/or visual information. After learning, appropriate motor commands for manipulation of each object are issued by the control networks which have a modular structure. By simulation of simple examples, the potential advantages and disadvantages of the two schemes are examined.