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

In fields like land assessment and disaster relief, the use of unmanned aerial vehicles has become increasingly prevalent. Path planning remains a key challenge for achieving comprehensive coverage of complex areas, combining elements of the Traveling Salesman Problem (TSP) and Coverage Path Planning (CPP), referred to as the TSP-CPP problem. This study introduced an innovative method that employs Particle Swarm Optimization (PSO) to decompose the target area into convex subregions, simplifying intricate concave areas into manageable convex components, thus reformulating the issue as a TSP. We then proposed an enhanced Ant Colony Optimization (ACO) algorithm, termed FA3ACO, which integrates fractional-order strategies, adaptive pheromone evaporation mechanisms, and 3-opt strategies to address the reformulated TSP efficiently. Experimental results showed that the proposed FA3ACO algorithm performs well on standard benchmark functions, consistently finding optimal solutions. Two simulation experiments, conducted in environments with different terrain complexities, confirm the effectiveness of the PSO-FA3ACO framework, achieving maximum coverage with optimized path lengths and minimizing invalid paths. This research offers a robust solution for autonomous UAV-based reconnaissance, highlighting its potential to improve operational efficiency and offering theoretical insights and technical advancements for future applications in UAVs.