An effective robot trajectory planning method using a genetic algorithm

In this paper, we propose a novel trajectory planning method for a robot manipulator whose workspace includes several obstacles. To generate the robot’s trajectory we developed a genetic algorithm (GA) to search for valid and optimal solutions to the trajectory in task space. In this method, a polynomial based on Hermite cubic interpolation is applied to approximate the time histories of the trajectory in task space. The GA determines the parameters, which are the interior points to be interpolated to formulate the polynomial representing the trajectory, to minimize the fitness of the desired objective function. It does not need a special formulation and can evaluate the trajectory to an optimal one quickly. The effectiveness and capability of the proposed approach are demonstrated through simulation studies.