Search and Tracking of a Moving Target Using Heterogeneous USVs Swarm

This research investigates the performance and efficiency of Unmanned Surface Vehicles (USVs) in multi-target tracking scenarios using the Adaptive Particle Swarm Optimization with k-Nearest Neighbors (APSO-kNN) algorithm. The study explores various search patterns, including random walk, spiral search, lawnmower pattern, and cluster search, to determine their effectiveness in different dynamic environments. Through extensive simulations, we examine the impact of varying the number of targets and USVs' sensing capabilities on tracking performance. Our findings demonstrate that systematic search patterns like spiral and lawnmower achieve superior coverage and tracking accuracy, making them ideal for thorough area exploration and effective target tracking. The random walk pattern, despite its high adaptability, showed lower accuracy due to its non-deterministic nature. Cluster search-maintained group cohesion but depended heavily on the relative positions of the targets and the cluster center. This study provides valuable insights into the selection of appropriate search strategies and the optimization of sensing configurations for USVs. The conclusions drawn from this research can inform the deployment of USV swarms in real-world applications, such as surveillance, search and rescue, and environmental monitoring, ultimately enhancing their operational efficiency and success.