Genetic Algorithms in Computer-aided Design of Robotic Manufacturing Cells

Computer-aided design of modern robotic manufacturing cells involves solution of a number of complicated optimization problems that are related to equipment selection, scheduling, routing and path planning. The paper deals with three of them: optimal selection of robotic tools, optimal clustering of welding dots among robots, and optimal layout design. A number of efficient genetic algorithms are proposed for these specific integer optimization problems. They have been incorporated in commercial software package ROBOMAX that is widely used in Russian automotive industry. The efficiency of the proposed algorithms is carefully investigated via computer simulation; computational results indicate that the algorithms are effective in solving problems of practical size.