Transactions of the Institute of Systems, Control and Information Engineers
Online ISSN : 2185-811X
Print ISSN : 1342-5668
A Learning Optimal Trajectory Planning of Robotic Manipulators
A Decreasing Method of Computing Iteration Number in Optimal Trajectory Search
Kazumasa OHSAKAToshiro ONO
Author information

1989 Volume 2 Issue 1 Pages 17-22


A number of trajectory planning algorithms exist for calculating the joint positions, velocities, and torques which will drive a robotic manipulator along a given geometric path. This paper presents a learning method for optimal trajectory planning of robotic manipulators of which all joints are rotational. When the start and end points of end effector are given in the Cartesian coordinates, the Fourier coefficients representing each joint velocity and interval of motion which specify the optimal trajectory in joint coordinates are searched by using the method of steepest descent. In the searching process, a learning algorithm based on the idea of linear approximation and utilization of the information on the known optimal trajectories is introduced. As numerical examples, the trajectories of two-link manipulator are simulated and the learning effect is confirmed.

Information related to the author
© The Institute of Systems, Control and Information Engineers
Previous article Next article