Near-Minimum-Time Motion Planning of Manipulators along Specified Path

The large amount of computation necessary for obtaining time optimal solution for moving a manipulator on specified path has made it impossible to introduce an on line time optimal control algorithm. Most of this computational burden is due to calculation of switching points. In this paper a learning algorithm is proposed for finding the switching points. The method, which can be used for both serial and parallel manipulators, is based on a two-switch algorithm with three segments of moving with maximum acceleration, constant velocity and maximum deceleration along the path. The learning algorithm is aimed at decreasing the length of constant velocity segment in each step of learning process. The algorithm is applied to find the near minimum time solution of a parallel manipulator along a specified path. The results prove versatility of the algorithm both in tracking accuracy and short training process.