Crow Search Algorithm for Energy-Efficient UAV Path Planning in Large-Scale Aerial Surveys

UAVs have been extremely influential for applications such as remote/sensing, disaster response, surveillance, and infrastructure monitoring. They are valuable in modern-day operations because they can conduct high-precision aerial surveys autonomously. Most of the existing trajectory planning approaches are based on metaheuristic algorithms of Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Ant Colony Optimization (ACO), which are capable of providing satisfactory results. Still, they are computationally expensive with slow convergence and sensitive to local optima. In this paper, the challenges raised above are addressed by an Optimized Trajectory Planning Framework based on the Crow Search Algorithm (CSA). It is based on a nature-inspired optimization technique that mimics the intelligent foraging behavior of crows. The proposed approach dynamically adjusts the UAV flight path by balancing the exploration and exploitation, to compute the optimal trajectory quickly and meanwhile to save energy and avoid the obstacle. Unlike other metaheuristic methods, the Crow Search Algorithm does not confront the premature convergence problem and can guarantee adaptive path optimization even under uncertain environmental conditions. Results show that the energy efficiency performance of the Crow Search Algorithm is 15 percent better, the performance in terms of coverage is 20 percent improved, and the speed of convergence is 30 percent faster compared to various state-of-the-art methods. These experimental findings demonstrate that integrating CSA into UAV trajectory planning offers high computational efficiency, obstacle avoidance, and mission endurance, rendering it a superior UAV trajectory planning algorithm for real-time aerial navigation and autonomous surveillance applications.