Khalil Alipour - Department of Mechanical Engineering K. N. Toosi Univ. of Technology, Tehran, Iran
Hossein Sadati - Department of Mechanical Engineering K. N. Toosi Univ. of Technology, Tehran, Iran
Mohammad Behruzi - Department of Mechanical Engineering K. N. Toosi Univ. of Technology, Tehran, Iran

Mobile Manipulators which consist of one or more manipulators mounted on a mobile base absorbed much of interest because they have locomotion. Optimal-energy motion planning is one of the most vital problems associated with these systems, especially the ones that travel in an unknown environment such as Mars rovers. Since an open loop optimal control may suffer from the lack of robustness, and plus the fact that the two-point-boundary-value problem that it leads to may not quite be as simple to solve, we have introduced the use of Artificial Neural Networks to close the control loop, hence guaranteeing sufficient robustness for the robot system in use. The conventional numerical methods for functional optimization have some drawbacks in optimization. Hence, as a motive, and in order to avoid such difficulties, the Ritz method as a direct approach in the calculus of variations is proposed to train the neural network, thus introducing a robust closed-loop control.

Mobile Manipulators- Motion Planning-Optimal Planning-Voronoi Diagram, Ritz Method