Cooperative Coevolution Applied to Dual-arm Robot Motion Planning

This paper presents a cooperative coevolutionary approach to path planning for two robotic arms sharing common workspace. Each arm is considered an agent, required to find transition strategy from given initial to final configuration in the work space. Since the robots share workspace, they present dynamic obstacle to each other. To solve the problem of path planning in optimized fashion, we formulated it to multi-objective optimization domain and implemented co-evolutionary algorithm to simultaneously optimize four conflicting objectives. End-effector trajectory length, end-effector velocity distribution, total rotate angle and number of collisions are the objectives to be optimized. Simulation results for two 2-R type robots are presented. Experimental verification is conducted on two FANUC Lr Mate 200iC robots.