A time-optimal trajectory planning algorithm based on hybrid strategy mountain gazelle optimization (HMGO) is proposed to improve the operation efficiency and stability of the robotic manipulator under complex obstacle constraints. Initially, the collision detection model of obstacles and the robotic manipulator is formulated, and the quintic B-spline curve is utilized to generate the trajectory of the manipulator. Then, in the proposed HMGO, the population division strategy and population competition method are integrated to balance between exploitation and exploration, while the SPM chaotic mapping and reverse learning strategy are introduced for population initialization. Finally, the HMGO is compared with the five state-of-the-art metaheuristic algorithms on the CEC 2017 test suite. Experimental results demonstrate that HMGO exhibits significant advantages in obtaining optimal solutions. Furthermore, the HMGO is applied to solve the time-optimal trajectory planning problem for an AUBO-i5 manipulator. The experimental results demonstrate that, under kinematic constraints and obstacle avoidance requirements, HMGO is capable of generating safe and smooth time-optimal trajectories with a minimum 16.10% reduction in execution time compared with the five other state-of-the-art metaheuristic algorithms.
Tang et al. (Thu,) studied this question.