Learning human arm movements by imitation: Evaluation of a biologically-inspired connectionist architecture
Aude Billard and Maja J Mataric
This paper is concerned with the evaluation of a model of human imitation of arm movements. The model consists of a hierarchy of artificial neural networks, which are abstractions of brain regions involved in visuo-motor control. These are the spinal cord, the primary and pre-motor cortexes (M1 \& PM), the cerebellum, and the temporal cortex. A biomechanical simulation is developed which models the muscles and the complete dynamics of a 37 degree of freedom humanoid. Input to the model are data from human arm movements recorded using video and marker-based tracking systems. The model's performance is evaluated for reproducing reaching movements and oscillatory movements of the two arms. Results show a high qualitative and quantitative agreement with human data. In particular, the model reproduces the well known features of reaching movements in humans, namely the bell-shaped curves for the velocity and quasi-linear hand trajectories. Finally, the model's performance is compared to that of humans performing the same imitation task. It is shown that the model's reproduction is better or comparable to that of humans.