Abstract
In this paper, we study an inverse kinematics problem in which optimum trajectories of walking robot toes are generated under the condition of minimum walking energy. It is important for the walking robot that the motions of legs are determined to achieve the desired body operation. A 4-legged walking robot with rinks and motors at joints of waist and knee is assumed. Mathematical optimization method is used for optimization of several parameters which describe the trajectory function of toe. We use neural networks to calculate optimum trajectory in real time. Neural network controllers are made up by using clustered data for several configurations of obstacles in walking environment and used by changing them.
