Air-ground collaborative perception is essential for airport foreign object debris (FOD) detection, key-area patrol, emergency response, and battlefield operational assistance. However, existing systems often remain limited to isolated platforms, linear data processing, or single-algorithm optimization, and therefore struggle with blind-zone compensation, cross-platform confirmation, and degraded operation. This paper proposes an air-ground collaborative intelligent perception system integrating UAV clusters, UGV groups, fixed monitoring stations, edge computing nodes, and a command center. A dual-closed-loop architecture with six functional layers and two support pillars is designed: the data loop supports sensing, registration, fusion, and situation construction, while the control loop supports priority assessment, joint scheduling, route re-planning, and feedback re-sensing. A heterogeneous observation model, a quality-aware fusion model, a coverage utility model, and a joint task-allocation optimization model are established. A discrete-event simulation with 120 Monte Carlo runs, 36 random target events per run, and four baseline schemes is constructed in a 2 km × 2 km area. Under the stated assumptions, the proposed scheme achieves a 94.4% confirmation rate, reduces the mean confirmation delay from 42.02 s to 32.46 s compared with non-adaptive heterogeneous patrol, and increases timely confirmation within 60 s from 66.8% to 78.7%. The results indicate that the value of the architecture lies not only in adding platforms, but also in transforming heterogeneous resources into a closed-loop, reconfigurable, and engineering-deployable perception capability.

Hongxin Tan, Yuejian Xu. Architecture Design and Cooperative Mechanism of an Air-Ground Intelligent Perception System. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 8: 21-27. https://doi.org/10.25236/AJCIS.2026.090803.

[1] Grocholsky B, Keller J, Kumar V, et al. Cooperative air and ground surveillance. IEEE Robotics & Automation Magazine, 2006, 13(3): 16-25. 

[2] Lacroix S, Le Besnerais G. Issues in cooperative air/ground robotic systems. Robotics Research: The 13th International Symposium ISRR, Springer Tracts in Advanced Robotics, 2010: 421-432. 

[3] Tokekar P, Vander Hook J, Mulla D, et al. Sensor planning for a symbiotic UAV and UGV system for precision agriculture. IEEE Transactions on Robotics, 2016, 32(6): 1498-1511. 

[4] Li J, Sun T, Huang X, et al. A memetic path planning algorithm for unmanned air/ground vehicle cooperative detection systems. IEEE Transactions on Automation Science and Engineering, 2022, 19(4): 2724-2737. 

[5] Liu D, Bao W, Zhu X, et al. Vision-aware air-ground cooperative target localization for UAV and UGV. Aerospace Science and Technology, 2022, 124: 107525. 

[6] Cao Z, Kooistra L, Wang W, et al. Real-time object detection based on UAV remote sensing: A systematic literature review. Drones, 2023, 7(10): 620. 

[7] Cheng Q, Wang H, Zhu B, et al. A real-time UAV target detection algorithm based on edge computing. Drones, 2023, 7(2): 95.

[8] Noroozi M, Shah A. Towards optimal foreign object debris detection in an airport environment. Expert Systems with Applications, 2023, 213: 118829. 

[9] Niu Z, Zhang J, Li Z, et al. Automatic detection and predictive geolocation of foreign object debris on airport runway. IEEE Access, 2024, 12: 133748-133763.

[10] Cadena C, Carlone L, Carrillo H, et al. Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Transactions on Robotics, 2016, 32(6): 1309-1332.