Articulated Robot Path Planning Based on Hybridization of Adaptive Dimensionality Algorithm and Grey Wolf Optimizer in Dynamic Environments

A new method was developed to plan a path for a robotic articulated vehicle using the Grey Wolf Optimizer (GWO) ‎and Adaptive ‎Dimensionality (AD)‎. Existing studies in robotics path planning ignore the differences between robots in terms of size and flexibility and allocate a single cell to the robot regardless of the mentioned factors. Since the articulated robotic vehicle is longer than obstacles moving in the environment, this study takes into account vehicle size and flexibility in path planning by adapting the number of cells allocated to the robotic vehicle to contain the vehicle parts while performing different movements. Considering the number of fixed ‎obstacles during the environmental analysis improves safety and reduces dangerous turns. In the moving stage, the sensing area is reduced by AD based on steering angle range, and connectivity. The GWO leaders form the local path followed by the vehicle. Simulation results showed that the proposed ‎method finds ‎an optimal, ‎collision-free, and safer path. Compared to most related studies, the average path cost and the number of iterations increased by ‎‎(47.88%) and (59.15%) ‎compared to the GSO-AD, because increasing safety ‎in the proposed method guided the vehicle through a higher-cost path and imposed more iterations. These metrics decreased by (12.83%) and (50.14%) respectively compared to the Max-Min Ant because the latter uses complex calculations to lead the robot through large free spaces. The average time of the proposed method decreased by (17.57%) and (72.94%) compared to these methods which indicates the efficiency of the proposed method.‎