Robotized task time scheduling and optimization based on Genetic Algorithms for non redundant industrial manipulators

Industrial robot manipulators must work as fast as possible in order to increase the productivity. This goal could be achieved by increasing robots speed or/and optimizing the trajectories followed by robots while performing assembly, welding or similar tasks. In our contribution, we focus on the second aspect and we target the shortening of paths between task-points. In other words, the goal is to find the shorter traveled distance between different configurations in the coordinate space. In addition to the short distance goal, we aim as well to impose both IKM (Inverse Kinematic Model) and the relative position and orientation of the manipulator regarding the task-points. To this end, we propose an optimization method based on Genetics Algorithms. The method is validated via numerical and graphical simulation, where, results show that the total cycle time required to perform a spot-welding task of an industrial car-body by a 6-DOFs (Degree Of Freedoms) industrial manipulator was drastically reduced.