Intelligent control of humanoid robots using neural networks

This paper focusses on the application of connectionist (neural networks) control techniques and their hybrid forms (neuro-fuzzy networks and neuro-genetic algorithms) in the area of humanoid robotic systems. It represents an attempt to cover the basic principles and concepts of connectionist learning control in humanoid robotics, with an outline of a number of recent algorithms used in advanced control of humanoid robots. Overall, this survey covers a selection of examples that serve to demonstrate the advantages and disadvantages of the application of connectionist control techniques.