Multi-objective Trajectory Optimization of 6-DOF Manipulator Based on Improved NSGA-II Algorithm

To reduce the time, energy consumption and pulsation during the operation of the 6-DOF manipulator, a multi-objective trajectory optimization method based on an improved NSGA-II algorithm is proposed. Firstly, for the 6-DOF manipulator operating along a known Cartesian path of end effector, joint space trajectory planning is performed using quintic B-spline curve interpolation. Secondly, aiming at the shortcomings of slow convergence speed, limited search range, and susceptibility to local optima in the traditional NSGA-II algorithm, the algorithm is improved by adopting a parent selection method based on linear ranking and an improved crossover and mutation operator. Comparative tests are conducted on test function and other multi-objective optimization algorithms to validate the better performance of the proposed algorithm. Then, the Pareto solution sets obtained using the improved NSGA-II algorithm and other multi-objective optimization algorithms are analyzed using evaluation functions. The results demonstrate that the proposed improved NSGA-II algorithm accelerates convergence speed, expands the search range, and achieves a better Pareto front. Finally, by employing an average fuzzy membership function, an optimal solution is obtained from the Pareto optimal solution set, thereby obtaining an optimal trajectory that comprehensively considers time, energy consumption, and pulsation.