A UAV Path Planning Approach Based on Improved Artificial Lemming Algorithm in Urban Low Altitude Environments

With the rapid development of low-altitude economy, the complex low altitude environment requires more efficient and accurate path planning algorithms for unmanned aerial vehicles (UAVs). The artificial lemming algorithm (ALA), as an emerging bionic meta-heuristic optimization algorithm, has advantages in adaptability and search ability in path planning problems. However, it suffers from slow convergence, easy entrapment in local optima, and poor robustness in complex 3D spaces. To address these issues, this paper proposes an improved artificial lemming algorithm (IALA) for UAV path planning, which mainly incorporates three improved strategies. Firstly, the Gaussian wandering strategy is introduced to enhance the pertinence of the migration direction. Secondly, the search range is expanded through Cauchy's inverse cumulative distribution variation. Thirdly, periodic variation is considered to prevent the attenuation of search kinetic energy. The simulation results show that compared with other comparative algorithms, IALA shortens path length by 8%-30%, reduces turns by 10%-16%, and lowers risk by 31%-44%. The proposed IALA can successfully balance path efficiency, smoothness, and safety, making it more suitable for practical operation in urban low altitude environments.