Motion Planning of Robot Manipulator Based on Improved NSGA-II

In this paper, the trajectory of a robot manipulator is planned using the non-dominated sorting genetic algorithm II (NSGA-II). Moreover, consumed time, Cartesian trajectory length, and smooth movement are used as the multi-objective to be optimized [1, 2]. The Pareto optimal solution set is obtained through NSGA-II, and simulation is used to obtain and verify the results. In an actual engineering case, the optimal solution of the Pareto solution set can be selected as the optimal path of a robot manipulator. Results show that the relationship between consumed time and joint jerk is a priority solution to practical engineering selection. Moreover, the spatial distribution of the optimal solution set is improved by enhancing the proposed crowding distance mechanism in the conventional NSGA-II algorithm.