An efficient coverage path planning method for UAV in complex concave regions.

Area of Science:

• Robotics and Automation
• Geospatial Analysis
• Optimization Algorithms

Background:

• Unmanned Aerial Vehicles (UAVs) are crucial for land assessment and disaster relief.
• Path planning for comprehensive coverage in complex terrains (TSP-CPP problem) is a significant challenge.
• Existing methods struggle with intricate concave areas, limiting UAV operational efficiency.

Purpose of the Study:

• To develop an innovative and efficient path planning method for UAVs in complex environments.
• To address the combined challenges of the Traveling Salesman Problem (TSP) and Coverage Path Planning (CPP).
• To enhance autonomous UAV reconnaissance capabilities.

Main Methods:

• Utilized Particle Swarm Optimization (PSO) to decompose complex areas into convex subregions.
• Proposed a novel Ant Colony Optimization (ACO) algorithm, FA3ACO, integrating fractional-order strategies, adaptive pheromone evaporation, and 3-opt strategies.
• Reformulated the area coverage problem as a TSP for efficient pathfinding.

Main Results:

• The FA3ACO algorithm demonstrated strong performance on benchmark functions, consistently finding optimal solutions.
• The PSO-FA3ACO framework achieved maximum coverage with optimized path lengths in simulated complex terrains.
• Effectiveness confirmed through simulations, minimizing invalid paths and enhancing operational efficiency.

Conclusions:

• The PSO-FA3ACO framework provides a robust solution for autonomous UAV path planning.
• This research offers significant theoretical insights and technical advancements for UAV applications.
• The method enhances operational efficiency for tasks like reconnaissance and disaster relief.