Hierarchical Task Planning Method for Heterogeneous Unmanned Swarm Based on Adaptive Hybrid Ant Colony Algorithm

Crucial means and key supports for ensuring the safe and efficient execution of swarm cooperative inspection missions lie in path‑planning and multi‑constraint avoidance technologies for air‑ground heterogeneous unmanned swarms. Aiming at the deficiencies of conventional intelligent optimization algorithms, such as susceptibility to local optima, high path redundancy, unbalanced heterogeneous task allocation and poor adaptability to multiple constraints, an improved ant colony algorithm integrating hierarchical zoning strategy and multi‑constraint screening is proposed. First, mathematical models concerning motion constraints, endurance constraints and timing constraints of air‑ground heterogeneous platforms are established. Second, heuristic functions with heterogeneous energy‑consumption differences and adaptive pheromone update rules are introduced to optimize global exploration and local convergence capabilities. Finally, a multi‑constraint threshold screening mechanism is embedded to realize hierarchical cooperative planning featuring wide‑area traversal by unmanned aerial vehicles and refined inspection by ground platforms. Simulation results demonstrate that the proposed algorithm can effectively reduce path redundancy with zero constraint violations throughout the whole process. Compared with traditional ant colony algorithm and particle swarm optimization, the cluster operation energy consumption is averagely reduced by 14.72% and the operation time is shortened by 12.45%. Stable robustness is maintained under varying task scales and heterogeneous platform ratios, which can provide effective technical support for cooperative inspection mission planning of field heterogeneous unmanned swarms