Abstract
To enhance the working efficiency of a wafer-handling robotic arm and simultaneously alleviate the impact and vibration during the motion process, a trajectory planning approach based on an improved snake optimization (ISO) algorithm is proposed. The following improvements have been made to the snake optimization (SO) algorithm: the introduction of a Chaotic Tent Map for initializing the swarm, the use of randomly perturbed dynamic learning factors to replace fixed values, the application of a cosine annealing learning rate for self-adaptively updating individual positions, and the incorporation of Bayesian optimization for parameterization and fine-tuning of the system's selection process. Furthermore, the ISO algorithm is applied in the Cartesian space of the robotic arm to effectively address the trajectory planning challenge of the single-segment start-stop S-shaped speed curve with arc transitions. The simulation results indicate that the improved S-shaped speed curve has increased by 24.1% compared with the original plan, and the mean and variance rankings of ISO algorithm have, respectively, improved by 60.8% and 63.4%, compared with the SO algorithm. Meanwhile, this study has successfully achieved the Pareto optimal solution with time and impact as the targets based on the established MATLAB experimental simulation platform.