Enhancing Individual UAV Path Planning With Parallel Multi-Swarm Treatment Coronavirus Herd Immunity Optimizer (PMST-CHIO) Algorithm

This paper introduces the PMST-CHIO, a novel variant of the Coronavirus Herd Immunity Optimizer (CHIO) algorithm, exclusively tailored for individual unmanned aerial vehicle (UAV) path planning in complex 3D environments. While acknowledging and building upon the foundational principles derived from UAV swarm path planning research, the PMST-CHIO distinctively focuses on optimizing the trajectory of single UAVs. It innovatively integrates a parallel multi-swarm treatment mechanism, enhancing the standard CHIO's exploration and exploitation capabilities significantly. This mechanism diverges from the swarm-based approaches by deploying multiple instances of the CHIO optimizer, each functioning autonomously within its sub-swarm, thereby facilitating independent path planning for individual UAVs. These multiple CHIO instances or CHIO candidates, operate in concert to determine the optimal and collision-free routes, taking into account the unique characteristics of individual UAVs and the intricacies of the service area. The algorithm incorporates two key mechanisms: 1) global exploitation, employing the best solution identified by the highest performing CHIO candidate across the swarms; and 2) strategic shift from parallel multi-swarm exploration to focused exploration by the top-performing CHIO candidate after a specific iteration threshold is reached. This adaptation significantly improves the algorithm's global search efficiency, convergence behavior, and navigational accuracy under challenging environments. Extensive simulations and comparative studies validate that the PMST-CHIO can effectively overcome the limitations of the standard CHIO algorithm, yielding safer, shorter, and more compliant flight paths for individual UAVs in intricate 3D landscapes.