INVERSE DYNAMIC MODEL IDENTIFICATION OF A BIPEDAL ROBOT USING ARTIFICIAL NEURAL NETWORKS

Abstract

The principal aim is to contribute to the identification of the inverse dynamics of the bipedal robot by training several Artificial Neural Network (ANN) models. These include Feedfor- ward Neural Networks (FFNN), Long Short-Term Memory(LSTM), and Recurrent Neural Networks (RNN). The project will compare these models to determine the best performer in terms of learning the inverse dynamics of the bipedal robot, considering both performance and computational complexity. The main tools for the achievement of the task are CoppeliaSim simulation and Python programming language