Multi-UAV Cooperative Coverage Search for Various Regions Based on Differential Evolution Algorithm.

Area of Science:

• Robotics
• Artificial Intelligence
• Optimization Algorithms

Background:

• Unmanned Aerial Vehicles (UAVs) offer advantages for search missions but face limitations in range and endurance.
• Cooperative multi-UAV systems are crucial for effective coverage in complex environments.
• Existing methods struggle with efficient path planning and energy management for single UAVs.

Purpose of the Study:

• To propose a novel multi-UAV cooperative coverage algorithm (DECSMU) for efficient search missions.
• To enhance coverage rate and minimize energy consumption in complex terrains.
• To ensure collision avoidance and demonstrate algorithm stability and generality.

Main Methods:

• A differential evolution (DE) based algorithm (DECSMU) divides coverage into stages.
• Each UAV dynamically plans flight paths using DE with a reward function for coverage and energy.
• Distributed model predictive control facilitates collaborative coverage and information interaction.

Main Results:

• The DECSMU algorithm achieved high coverage rates and low energy consumption.
• Collision avoidance was maintained throughout the search missions.
• Experimental results demonstrated the algorithm's stability and generality across different regions.

Conclusions:

• The proposed DECSMU algorithm effectively addresses limitations of single UAVs in coverage search.
• DECSMU offers a stable and generalizable solution for multi-UAV cooperative missions.
• The dynamic reward function and distributed control contribute to efficient and safe operations.