Optimization of the cycle time in a robotic workcell using genetic algorithms

摘要

This paper presents a new method for solving the scheduling problem for a point-to-point robot motion. Given N functional points that the robot has to reach, where the order is not significant, it is required to plan its route in order to achieve the minimum cycle time. A Genetic Algorithm solving the classical TSP problem is adapted to a robot motion-scheduling problem. The travel distance is replaced by the time required to move from one point to another and the multiple solutions of the Inverse Kinematics problem are taken into account, in order to take an optimal solution. Finally, a validation for the proposed approach through experiments for the optimization of the cycle time of a PUMA-like robot is presented.