Optimal Two-Step Collision-Free Trajectory Planning for Cylindrical Robot using Particle Swarm Optimization

Among the works related to the planning of trajectories of manipulator robots, a subject that has been approached by different authors is the study associated to the manipulator's movement, without considering the variable "time" involved in these tasks. These studies involve the robot's kinematic constraints (path geometry, obstacles and the characteristics of the effector). This paper proposes an optimization technique for planning the trajectory of a cylindrical manipulator robot with 5 degrees of freedom. The technique considers two crucial factors: obstacle deviation and the kinematic characteristics of the manipulator. In the first step, an algorithm is employed to generate intermediate points along the trajectory. This algorithm optimizes the intermediate points to minimize the distance between them and the final destination. In the second step, the proposed method utilizes b-spline functions of the 5th degree to generate smooth and efficient trajectories with minimal joint movement. Joint space restrictions are proposed to ensure that the trajectory obtained does not cause collisions and it is applied within the operational limits of the robot. The proposed steps have been implemented using the Particle Swarm Optimization (PSO). The results of the study indicate that the proposed method is highly suitable for cylindrical robots operating in the presence of obstacles. The computational analyses conducted during the study clearly demonstrate that both the intermediate points and the trajectory within the joint space of the robot under investigation remained well within the designated collision-free zone.