Abstract
This paper presents a trajectory planning for a flexible Cartesian robot manipulator in a point-to-point motion. In order to obtain a mathematical model properly, the parameters of the equation of motion are determined from an identification experiment. Neural networks are employed to generate the desired base position, and then a particle swarm optimization (PSO) is used for the learning algorithm, in which the sum of the displacement of the manipulator is adopted as the objective function. We show that the residual vibrations of the manipulator can be suppressed as a result of the minimum displacement requirement. The effectiveness of the proposed approach is verified by a comparison of numerical results and experimental ones.
