An ACO-Based Path Planning Algorithm for UAV in Urban Airspace

Navigating Unmanned Aerial Vehicles (UAVs) in urban airspace poses significant challenges for fast and efficient path planning due to the environment's complexity and dynamism. However, the existing research on UAV path planning has ignored the speed of algorithmic convergence and the smoothness of the generated path, which are critical for adapting to the dynamic changing of the urban airspace as well as for the safety of ground personnel, and the UAV itself. In this study, we propose an enhanced Ant Colony Optimization (ACO) algorithm that incorporates two heuristic functions: the compass heuristic and the inertia heuristic. These functions guide the ant agents in their movement towards the destination, aiming for faster convergence and smoother trajectories. The algorithm is evaluated using a gray-scale lattice map generated from ground personnel risk data in Suzhou City. The results indicate that the improved ACO path planning algorithm demonstrates both efficiency and quality, converging faster than traditional ACO methods in a gray-scale lattice map and producing smoother paths for UAV navigation.