Motion Planning for a Robot Arm by Using Genetic Algorithm

This paper proposes genetic algorithm (GA) to optimize the point-to-point trajectory planning for a 3-link (redundant) robot arm. The objective function for the proposed GA is to minimizing traveling time and space, while not exceeding a maximum pre-defined torque, without collision with any obstacle in the robot workspace. Quadrinomial and quintic polynomials are used to describe the segments that connect initial, intermediate, and final point at joint-space. Direct kinematics has been used for avoiding the singular configurations of the robot arm.