Efficient exploration and learning of whole body kinematics

摘要

We present a neural network approach to early motor learning. The goal is to explore the needs for boot-strapping the control of hand movements in a biologically plausible learning scenario. The model is applied to the control of hand postures of the humanoid robot ASIMO by means of full upper body movements. For training, we use an efficient online scheme for recurrent reservoir networks consisting of supervised backpropagation-decorrelation output adaptation and an unsupervised intrinsic plasticity reservoir optimization. We demonstrate that the network can acquire accurate inverse models for the highly redundant ASIMO, applying bi-manual target motions and exploiting all upper body degrees of freedom. We show that very few, but highly symmetric training data is sufficient to generate excellent generalization capabilities to untrained target motions. We also succeed in reproducing real motion recorded from a human demonstrator, massively differing from the training data in range and dynamics. The demonstrated generalization capabilities provide a fundamental prerequisite for an autonomous and incremental motor learning in an developmentally plausible way. Our exploration process - though not yet fully autonomous - clearly shows that goal-directed exploration can, in contrast to ldquobabblingrdquo of joints angles, be done very efficiently even for many degrees of freedom and non-linear kinematic configurations as ASIMOs.