Time scheduling and optimization of industrial robotized tasks based on genetic algorithms

Today's industrial manipulators are more and more demanding in terms of productivity. This goal could be achieved by increasing speed of the robot manipulator and/or by optimizing the trajectories followed by manipulators while performing manufacturing, assembling, welding or similar tasks. Focusing on the second aspect, this research proposes a method based on genetic algorithms by exploiting CAD (computer aided design) capabilities to optimize and simulate cycle time in performing classical manufacturing tasks. The goal is to determine the shortest distance traveled by the robot manipulator in the coordinate space for every pair of successive points. In addition, our optimization procedure considers supplementary factors such as inverse kinematic model (IKM) and relative position/orientation of the manipulator w.r.t task points. All these factors were statistically assessed to determine both individual and cross influences in finding the optimal solution. The proposed approach has been validated on a real life setup, involving a 6-DOFs (degrees of freedom) industrial robot manipulator when performing a spot welding task on a car body. The obtained results are promising and show the effectiveness of the proposed strategy. HighlightsThis paper proposes a strategy for planning and scheduling of the industrial robotic manipulators.The multi-objective optimization strategy is based on Genetic Algorithms (GAs).A statistical study to investigate influence of various factors on optimization is detailed.The proposed strategy is validated by considering an industrial task of spot welding on a car body.The obtained results are promising and show the efficacy of the proposed strategy.