Modeling and Layout Optimization of Bio-Inspired Swarm Vigilance Tasks

This paper considers the swarm vigilance problem for multi-agent systems (MAS), where multiple agents are deployed within a rectangular region for perception-based vigilance. There are two main challenges, namely the task allocation for vigilance roles and the coverage planning of the perception ranges. Firstly, vigilance behavioral patterns and processes in animal populations within natural habitats are investigated. Inspired by these biological vigilance behaviors, an efficient vigilance task allocation model for MAS is proposed. Secondly, the subsequent optimization of task layouts can achieve efficient surveillance coverage with fewer agents, minimizing resource consumption. Thirdly, an improved particle swarm optimization (IPSO) algorithm is proposed, which incorporates fitness-driven adaptive inertia weight dynamics. According to simulation analysis and comparative studies, optimal parameter configurations for Genetic Algorithm (GA) and IPSO are determined. Finally, the results indicate the proposed IPSO's superior performance to both GA and standard particle swarm optimization (PSO) in vigilance task allocation optimization, with satisfying advantages in computational efficiency and solution quality.