Predictive Hebbian association of time-delayed inputs with actions in a developmental robot platform

Abstract

The work described here explores a neural network architecture that can be embedded directly in the realtime sensorimotor coordination loop of a developmental robot platform. We take inspiration from the way children are able to learn while interacting with a teacher, in particular the use of prediction of the teacher actions to improve own learning. The architecture is based on two neural networks that operate online, and in parallel, one for learning and one for prediction. A Hebbian learning rule is used to associate the high-dimensional afferent sensor input at different time-delays with the current efferent motor commands corresponding to the teacher demonstration. The predictions of future motor commands are used to limit the growth of the neural network weights, and to enable the robot to smoothly continue movements the teacher has begun. Results on a simulated iCub robot learning object interaction tasks are presented, including an analysis of the sensitivity to changes in the task setup. We also outline the first implementation on the real iCub platform.