Multi-objective Trajectory Planning Method based on the Improved Elitist Non-dominated Sorting Genetic Algorithm

Abstract Robot manipulators perform a point-point task under kinematic and dynamic constraints. Due to multi-degree-of-freedom coupling characteristics, it is difficult find better desired trajectory. In this paper, multi-objective trajectory planning approach based on an improved elitist non-dominated sorting genetic algorithm (INSGA-II) proposed. Trajectory function planned with new composite polynomial that by combining of quintic polynomials cubic Bezier curves. Then, INSGA-II, introducing three operators: ranking group selection (RGS), direction-based crossover (DBX) adaptive precision-controllable mutation (APCM), developed optimize travelling time torque fluctuation. Inverted generational distance, hypervolume optimizer overhead are selected evaluate the convergence, diversity computational effort algorithms. The optimal solution determined via fuzzy comprehensive evaluation obtain Taking serial-parallel hybrid manipulator as instance, velocity acceleration profiles obtained using compared those B-spline method. effectiveness practicability proposed method verified simulation results. This research proposes optimization which can offer efficiency stability for point-to-point robot manipulators.