A hierarchical path planning of manipulators using memetic algorithm

In this paper, a hierarchical memetic algorithm (MA) is proposed for the path planning of manipulators. The proposed algorithm consists of a global path planner (GPP) and a local motion planner (LMP). The global planner, a MAKLINK based approach, plans a trajectory which the end-effector of a manipulator should follows. A memetic algorithm with a non-random initial population plans a series of configurations along the path given by the former stage. The MA locally adjusts the robot configuration to search for minimum potential configurations using the repulsive force between manipulator and obstacles. Once the optimal configuration is obtained, the better chromosomes will be reserved as the initial population for next generation. Since the proposed MA is with non-random initial population and potential based local searching, it is more efficient and the planned path is smoother than traditional GA. The simulation result show that the proposed algorithm works well, specifically in terms of collision avoidance and computation efficiency.