Stable online neural control of hexapod joint trajectories

We describe our initial results from the first phase of an investigation into online adaptive neural control of hexapod walking robot´s leg trajectories. In this application very accurate trajectories and foot placement are required even in the presence of disturbances. Our first experiments are based on our existing experience in neural control of robot manipulators. The experiments described are dealt with the neural controller performance on intermittent end-effector force disturbances