Key points are not available for this paper at this time.
Urban environments impose complex challenges for the navigation of unmanned aerial vehicles (UAVs), including dense obstacles, no-fly zones, energy constraints, and regulatory restrictions. Addressing these challenges requires efficient and robust optimization techniques. This study introduces the Improved Roosters Algorithm (IRA), a novel metaheuristic inspired by the natural dominance behavior of roosters, tailored for constrained 3D UAV path planning in urban scenarios. Unlike existing metaheuristics, IRA introduces a spiral dancing operator, adaptive constraint handling, and a hierarchical population structure. These innovations directly target the lack of adaptive mechanisms in constraint-rich urban environments, enabling more reliable and realistic UAV path planning. The performance of IRA is benchmarked against Particle Swarm Optimization (PSO), Standard Genetic Algorithm (SGA), Differential Evolution (DE), Grey Wolf Optimizer (GWO) and the original Roosters Algorithm (RA) across three increasingly complex simulation scenarios. Experimental results demonstrate that IRA consistently outperforms the baseline methods in terms of feasibility and optimality, validating its potential as a competitive tool for UAV mission planning in realistic urban environments.
Gençal et al. (Thu,) studied this question.