Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adaptive USVs Swarm Optimization for Target Tracking in Dynamic Environments

Oren Gal

TL;DR

This work addresses multi-target tracking by USV swarms in dynamic maritime environments using APSO-kNN, a decentralized method that blends adaptive inertia PSO with kNN-based neighbor influence to balance exploration and exploitation. It systematically compares search patterns—Random Walk, Spiral, Lawnmower, Cluster—and investigates a mixed strategy, incorporating a Pursuit-Evasion model to simulate evasive targets and assessing the impact of sensing radius. The key findings show that systematic patterns like Spiral and Lawnmower deliver high coverage and tracking accuracy, while Random Walk offers adaptability and Cluster maintains cohesion; the mixed pattern provides robustness across varied scenarios. The results offer practical guidelines for deploying USV swarms in surveillance, search and rescue, and environmental monitoring, highlighting the value of adaptive inertia and sensing configuration in dynamic environments.

Abstract

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-Random Walk, Spiral, Lawnmower, and Cluster Search to assess their effectiveness in dynamic environments. Through extensive simulations, we evaluate the impact of different search strategies, varying the number of targets and USVs' sensing capabilities, and integrating a Pursuit-Evasion model to test adaptability. Our findings demonstrate that systematic search patterns like Spiral and Lawnmower provide superior coverage and tracking accuracy, making them ideal for thorough area exploration. In contrast, the Random Walk pattern, while highly adaptable, shows lower accuracy due to its non-deterministic nature, and Cluster Search maintains group cohesion but is heavily dependent on target distribution. The mixed strategy, combining multiple patterns, offers robust performance across varied scenarios, while APSO-kNN effectively balances exploration and exploitation, making it a promising approach for real-world applications such as surveillance, search and rescue, and environmental monitoring. This study provides valuable insights into optimizing search strategies and sensing configurations for USV swarms, ultimately enhancing their operational efficiency and success in complex environments.

Adaptive USVs Swarm Optimization for Target Tracking in Dynamic Environments

TL;DR

This work addresses multi-target tracking by USV swarms in dynamic maritime environments using APSO-kNN, a decentralized method that blends adaptive inertia PSO with kNN-based neighbor influence to balance exploration and exploitation. It systematically compares search patterns—Random Walk, Spiral, Lawnmower, Cluster—and investigates a mixed strategy, incorporating a Pursuit-Evasion model to simulate evasive targets and assessing the impact of sensing radius. The key findings show that systematic patterns like Spiral and Lawnmower deliver high coverage and tracking accuracy, while Random Walk offers adaptability and Cluster maintains cohesion; the mixed pattern provides robustness across varied scenarios. The results offer practical guidelines for deploying USV swarms in surveillance, search and rescue, and environmental monitoring, highlighting the value of adaptive inertia and sensing configuration in dynamic environments.

Abstract

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-Random Walk, Spiral, Lawnmower, and Cluster Search to assess their effectiveness in dynamic environments. Through extensive simulations, we evaluate the impact of different search strategies, varying the number of targets and USVs' sensing capabilities, and integrating a Pursuit-Evasion model to test adaptability. Our findings demonstrate that systematic search patterns like Spiral and Lawnmower provide superior coverage and tracking accuracy, making them ideal for thorough area exploration. In contrast, the Random Walk pattern, while highly adaptable, shows lower accuracy due to its non-deterministic nature, and Cluster Search maintains group cohesion but is heavily dependent on target distribution. The mixed strategy, combining multiple patterns, offers robust performance across varied scenarios, while APSO-kNN effectively balances exploration and exploitation, making it a promising approach for real-world applications such as surveillance, search and rescue, and environmental monitoring. This study provides valuable insights into optimizing search strategies and sensing configurations for USV swarms, ultimately enhancing their operational efficiency and success in complex environments.
Paper Structure (13 sections, 9 equations, 10 figures)

This paper contains 13 sections, 9 equations, 10 figures.

Table of Contents

  1. Introduction and Related Work
  2. The APSO-kNN Method
  3. Problem Formulation
  4. Particle Swarm Optimization (PSO) Framework
  5. k-Nearest Neighbors (kNN) Integration
  6. Fitness Function and Convergence
  7. Pursuit-Evasion Target Behavior Model
  8. Simulations
  9. APSO-kNN with With USVs Search Patterns
  10. APSO-kNN with Pursuit-Evasion Target Model
  11. Discussion and Analysis
  12. APSO-kNN with Pursuit-Evasion Target Model
  13. Conclusions

Figures (10)

  • Figure 1: The simulation results for five targets show the positions of the Unmanned Surface Vehicles (USVs) and the targets at different iterations. The blue circles around each USV illustrate their varying sensing radii, indicating the area each USV can perceive.
  • Figure 2: The simulation results for ten targets show the positions of the Unmanned Surface Vehicles (USVs) and the targets at different iterations. The blue circles around each USV illustrate their varying sensing radii, indicating the area each USV can perceive.
  • Figure 3: The simulation results for twenty targets show the positions of the Unmanned Surface Vehicles (USVs) and the targets at different iterations. The blue circles around each USV illustrate their varying sensing radii, indicating the area each USV can perceive.
  • Figure 4: The simulation results for ten targets show the positions of the Unmanned Surface Vehicles (USVs) and the targets at different iterations with Pursuit-Evasion behavior of the targets.
  • Figure 5: Simulation results and effectiveness of different search patterns.
  • ...and 5 more figures