Artificial neural networks for the emulation of human locomotion patterns

Abstract

Many neurophysiologists believe that one of the important circuits in the entire central nervous system (CNS) is the reverberating (oscillatory) circuit. Such positive feedback within the neuronal pool. One such circuit is a central pattern generator (CPG) which generates rhythmic motion actions such as locomotion and respiration. Here, the authors use a recurrent neural network (RNN) to model the CPG. By appropriately modifying the weights of the RNN using a learning algorithm, the RNN can be programmed to function as an adaptive oscillator which in turn models the CPG. The CPG model is potentially applicable for improved understanding of animal locomotion, and for its application in legged robots. Computer simulations are provided to demonstrate the efficacy of the proposed CPG model using the RNN.