AMODERNAPPROACH IN MILITARYPLANNING FORUNMANNEDCOMBATAERIALVEHICLES BASEDONSWARMINTELLIGENCE

Abstract

In today’s world of rapidly shifting geopolitical scenarios, it is crucial to stay ahead of our adversaries, particularly in network-centric warfare. Unmanned Combat Aerial Vehicles (UCAVs), also known as drones, play a crucial role in intelligence gathering, surveillance, and the administration of military missions around the globe. Path planning for UCAVs is essential to ensure mission success with minimal collateral damage. This study suggests employing swarm intelligence algorithms for UCAV path planning in extreme, hazardous, and dynamic environments. In addition, the objective is to develop a path planning model that addresses the challenges posed by ambiguous environments and dynamic obstacles. The proposed path planning model takes into account the number of threats present and assigns three coordinate points to each threat, enabling UCAVs to effectively avoid or cir cumvent them. This method incorporates the advantages of swarm intelligence algorithms, viz. their ability to rapidly adapt to environmental changes and their distributed decision making capabilities. For this path planning problem, Particle Swarm Optimisation (PSO), Levy Flight Particle Swarm Optimisation (LFPSO), Grey Wolf Optimizer (GWO), and Mutation-driven Modified Grey Wolf optimizer (MDM-GWO) are employed. In addition, hybridised MDMGWO and LFPSO (MDMGWO-LFPSO) is used to conduct simulation experiments and determine the efficacy of this approach. Subsequently, its performance is compared with the performance of these existing algorithms. The proposed UCAV path planning model and MDMGWO-LFPSO have the potential to provide an optimal solution within the time and space constraints of a battlefield, making it a valuable instrument for modern military planning.