Design and programming of a robotic puppetry robot based on natural learner unit pattern generators neural networks

The purpose of this study is to design and construct a novel interactive game. This game is a robotic learning and imitation task. It is based on visual interaction of the player. The cornerstone technique used in this game is natural learner unit pattern generator neural networks (NLUPGNN), which is able to generate required motion trajectories based on imitation learning. The systematic design of these neural networks is the main problem solved in this paper. The unit pattern generators can be divided into two subsystems, a rhythmic system and a discrete system. A special learning algorithm is designed to use these unit pattern generators. The unit pattern generators are connected and coupled to each other to form a network, and their unknown parameters are found by a natural policy gradient learning algorithm. The motion sequences train some nonlinear oscillators, then they reproduce motions for a humanoid robot. As a result, the joints of the humanoid body imitate the movements of the teacher in real time. The main contribution of this work is the development of this learning algorithm, which is able to search the weights and topology of the network simultaneously. The algorithm synchronizes the learning steps by coupling the neurons in the last step.