Three-dimensional trajectory planning for unmanned aerial vehicles based on the starfish optimization algorithm (SFOA)

When solving the path planning problem for Unmanned Aerial Vehicle (UAV) in a three-dimensional complex environment, traditional algorithms often face issues like falling into local optimum easily, insufficient global search ability, poor efficiency and defective optimization result. To address these issues, a three-dimensional path planning method is proposed based on the Starfish Optimization Algorithm (SFOA). This algorithm, inspired by the exploration, preying, and regeneration behaviors of starfish, balances global search and local exploitation, enhancing UAV trajectory planning in complex environments. The study constructs a complex three-dimensional environment model and designs a comprehensive optimization objective by covering constraints like trajectory length, safety, flight height, and smoothness. The trajectory planning framework proposed in this study is designed for pre-mission planning, generating UAV paths offline based on known static terrain and threat information. Comparative experimental results with Ant Colony Optimization and Particle Swarm Optimization show that the SFOA-based UAV trajectory planning achieves significant improvements in comprehensive cost and convergence speed, demonstrating superior global optimization performance. This offers an innovative solution for UAV efficiently and safe trajectory planning in complex environments.