Adaptive elite ant colony optimization for track planning in gravity-aided navigation with multi-feature fusion

Autonomous Underwater Vehicle track planning is critical for maritime defense missions, particularly in signal-denied and stealth-sensitive environments. Gravity-aided inertial navigation systems (GAINS), as a passive and emission-free approach, offer strong potential for such missions. However, track planning under gravity constraints remains underexplored. This paper proposes an Adaptive Elite Ant Colony Optimization (AEACO) algorithm to address this gap. AEACO integrates two key strategies: an elite reinforcement mechanism inspired by genetic algorithms and a dynamic parameter adjustment method for pheromone-related variables. A gravity adaptability model is first established using fuzzy statistics and entropy-weighted feature fusion to identify navigable regions. AEACO then reinforces elite path segments and self-adjusts its parameters in response to gravity field variations. Experiments across 22 real-world marine gravity scenarios show that AEACO consistently outperforms various classical methods. Specifically, it achieves up to 19% shorter paths, 40% fewer turns, and 95% faster convergence. Unlike other Ant Colony Optimization (ACO) variants, AEACO operates without fixed parameters or external tuning, making it scalable and adaptable for real-time defense operations in complex underwater environments.