Generation of rhythmic hand movements in humanoid robots by a neural imitation learning architecture

This paper presents a two layer system for imitation learning in humanoid robots. The first layer of this system records complicated and rhythmic movement of the trainer using a motion capture device. It solves an inverse kinematic problem with the help of an adaptive Neuro-Fuzzy Inference system. Then it can achieve angles records of any joints involved in the desired motion. The trajectory is given as input to the systems second layer. The layer deals with extracting optimal parameters of the trajectories obtained from the first layer using a network of oscillator neurons and Particle Swarm Optimization algorithm. This system is capable to obtain any complex motion and rhythmic trajectory via first layer and learns rhythmic trajectories in the second layer then converge towards all these movements. Moreover, this two layer system is able to provide various features of a learner model, for instance resistance against perturbations, modulation of trajectories amplitude and frequency. The simulation results of the learning system is performed in the robot simulator WEBOTS linked with MATLAB software. Practical implementation on an NAO robot demonstrate that the robot has learned desired motion with high accuracy. These results show that proposed system in this paper produces high convergence rate and low test error.