Using Adaptive Genetic Algorithm to the Placement of Serial Robot Manipulator

Abstract

This paper presents mathematical methods for the placement of serial robot manipulators with respect to pre-defined target points in arc welding applications where robot is mounted on a gantry or a multi-freedom crossbeam and manual programming of the robot system is rather difficult to complete. The robot placement problem is a nonlinear optimization problem, the traditional optimization methods can not solve it satisfactorily. In this paper the adaptive genetic algorithm (ASAGA) is adopted and introduced which can dynamically modify the parameters of genetic algorithms in terms of simulated annealing mechanism. Multiple kinematics criteria is presented and the objective function is constructed. The joint angles of the arm were generated by the inverse kinematics. The result shows that the ASAGA is successful in solving the robot placement problem