Profit-Driven Adaptive Moving Targets Search with UAV Swarms

Area of Science:

• Robotics
• Artificial Intelligence
• Distributed Systems

Background:

• Cooperative search operations are crucial for various applications.
• Existing methods often struggle with dynamic environments and target movement.
• Unmanned Aerial Vehicles (UAVs) offer a flexible platform for search missions.

Purpose of the Study:

• To develop a novel distributed algorithm for cooperative UAVs searching for moving targets.
• To enhance the average observation rate of UAV swarms.
• To create an adaptive search strategy that considers both target and UAV dynamics.

Main Methods:

• A unified metric, 'observation profit', is introduced to quantify the impact of moving targets and collaborating UAVs.
• A profit-driven adaptive algorithm is developed for UAV swarm decision-making.
• Simulations are used to evaluate the proposed framework.

Main Results:

• The proposed algorithm effectively increases the average observation rate of UAVs.
• The framework demonstrates significant adaptiveness in dynamic search scenarios.
• Simulation results validate the superiority of the unified metric approach.

Conclusions:

• The novel distributed algorithm provides an effective solution for moving target search using cooperative UAVs.
• The 'observation profit' metric enables adaptive and efficient swarm behavior.
• This framework enhances the overall performance of UAV-based search operations.