A Cluster-Based Hierarchical-Approach for the Path Planning of Swarm

Abstract

This paper addresses the path planning and control of multiple colonies/clusters that have unmanned aerial vehicles (UAV) which make a network in a hazardous environment. To solve the aforementioned issue, we design a new and novel hybrid algorithm. As seen in the mission requirement, to combine the Maximum-Minimum ant colony optimization (ACO) with Vicsek based multi-agent system (MAS) to make an Artificially Intelligent (AI) scheme. In order to control and manage the different colonies, UAVs make a form of a network. The designed method overcomes the deficiencies of existing algorithms related to controlling and synchronizing the information globally. Furthermore, our designed architecture bounds, lemmatizes the pheromone, and finds the best ants which then make the most optimized path. The key contribution of this study is to merge two unique algorithms into a hybrid algorithm that has superior performance than both algorithms operating separately. Another contribution of the designed method is the ability to increase the number of individual agents inside the colony or the number of colonies with a good convergence rate. Lastly, we also compared the simulation results with the non-dominated sorting genetic algorithm II (NSGA-II) in order to prove the designed algorithm has a better convergence rate.

Keywords

• bio-inspired algorithm
• computer simulations
• Max-Min ant colony optimization (MMACO)
• multi-agent systems (MAS)