A neuromorphic controller for a three-link biped robot

Summary form only given, as follows. A neural network architecture is developed for the control of a three-link biped walking robot. The proposed neuromorphic controller, based on a hierarchical structure of artificial neural networks, is trained by supervised learning. The training model is derived by applying nonlinear feedback decoupling and an optimal tracking strategy. The neurocontroller utilizes several useful computational features of neural networks-generalization, parameter adaptivity, and robustness. Based on a comparison of the system performance between the optimal control law and that based on the neurocontroller, the authors conclude that the neurocontroller provides superior performance in the presence of large disturbances.<>