Research Paper:
An Intent Recognition Method for Aerial Swarm Based on Attention Pooling Mechanism
Hui He*
, Zhihong Peng*,
, Peiqiao Shang*
, Wenjie Wang*
, and Xiaoshuai Pei**

*National Key Laboratory of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology
No.5 Zhongguancun South Street, Haidian District, Beijing 100081, China
Corresponding author
**Information Science Research Institute, China Electronics Technology Group Co., Ltd.
China Electronics Technology Intelligent Technology Park, Jinfu South Road, Shijingshan District, Beijing 100081, China
In the realm of unmanned aerial vehicle (UAV) swarm intent recognition, conventional approaches predominantly focus on the attributes derived from singular targets at discrete instances. This trend leads to a significant limitation: the inability to effectively harness and capture the collective feature information of the entire swarm over temporal sequences. To address this gap, this study introduces a comprehensive end-to-end UAV swarm intent recognition approach. Initially, this method utilizes the distance threat coefficient and angular threat coefficient between UAVs to construct the graphical structural representation of the UAV swarm. Subsequently, an innovative deep learning framework, designated as attention-pool based on graph attention network and long short-term memory, which integrates a graph attention network, a novel graph pooling strategy, and a long short-term memory, is developed. This architecture can process the graphically structured data derived from the swarm modeling and accurately deduce the collective intent. Through experimental validation and analyses against existing methodologies, as well as ablation studies, it is evidenced that the model outperforms state-of-the-art methods in terms of accuracy of intent recognition.
- [1] M. Lehto and W. Hutchinson, “Mini-drone swarms: Their issues and potential in conflict situations,” J. of Information Warfare, Vol.20, No.1, pp. 33-49, 2021.
- [2] J. Whelan, A. Almehmadi, and K. El-Khatib, “Artificial intelligence for intrusion detection systems in unmanned aerial vehicles,” Computers and Electrical Engineering, Vol.99, Article No.107784, 2022. https://doi.org/10.1016/j.compeleceng.2022.107784
- [3] H. Xu, J. Zhao, L. Chen, W. Tan, and H. Zhang, “A review of methods of battlefield target combat intention recognition,” Proc. of 2022 Int. Conf. on Autonomous Unmanned Systems, pp. 3686-3696, 2022. https://doi.org/10.1007/978-981-99-0479-2_340
- [4] J. Liu, “Air target intention recognition based on incomplete multi-granulation rough set,” 2022 IEEE Asia-Pacific Conf. on Image Processing, Electronics and Computers, pp. 944-947, 2022. https://doi.org/10.1109/IPEC54454.2022.9777527
- [5] Y. Wang, J. Wang, S. Fan, and Y. Wang, “Quick intention identification of an enemy aerial target through information classification processing,” Aerospace Science and Technology, Vol.132, Article No.108005, 2023. https://doi.org/10.1016/j.ast.2022.108005
- [6] S.-H. Li, F.-L. Yan, and Y.-Q. Li, “An improved multi target ship recognition model based on deep convolutional neural network,” J. Adv. Comput. Intell. Intell. Inform., Vol.28, No.1, pp. 216-223, 2024. https://doi.org/10.20965/jaciii.2024.p0216
- [7] B. Tan, Q. Li, T. Zhang, and H. Zhao, “The research of air combat intention identification method based on BiLSTM + Attention,” Electronics, Vol.12, No.12, Article No.2633, 2023. https://doi.org/10.3390/electronics12122633
- [8] P. Wang, Y. Wang, and X. Gong, “An air target tactical intention recognition method based on the fusion deep learning network model,” 2nd Int. Conf. on Electronic Information Engineering, Big Data, and Computer Technology (Proc. SPIE Vol.12642), Article No.126422I, 2023. https://doi.org/10.1117/12.2674845
- [9] M. Zhou, Z. Wang, J. Wang, and Z. Dong, “A hybrid path planning and formation control strategy of multi-robots in a dynamic environment,” J. Adv. Comput. Intell. Intell. Inform., Vol.26, No.3, pp. 342-354, 2022. https://doi.org/10.20965/jaciii.2022.p0342
- [10] P. Veličković et al., “Graph attention networks,” arXiv:1710.10903, 2017. https://doi.org/10.48550/arXiv.1710.10903
- [11] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, Vol.9, No.8, pp. 1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735
- [12] Z. Lei, Z. Dong, and D. Wu, “Target tactical intention recognition based on fuzzy dynamic Bayesian network,” Proc. of the 2019 Int. Conf. on Modeling, Analysis, Simulation Technologies and Applications (MASTA 2019), pp. 241-244, 2019. https://doi.org/10.2991/masta-19.2019.41
- [13] T. Chang, D. Kong, W. Dai, Q. Wang, and H. Sun, “Threat assessment method based on the information fusion of target operation intention,” Control and Decision, Vol.34, No.3, pp. 591-601, 2019 (in Chinese). https://doi.org/10.13195/j.kzyjc.2017.1177
- [14] S. Cao, Y. Liu, and S. Xue, “Target tactical intention recognition method of improved high-dimensional data similarity,” Transducer and Microsystem Technologies, Vol.36, No.5, pp. 25-28, 2017 (in Chinese). https://doi.org/10.13873/j.1000-9787(2017)05-0025-04
- [15] Z. Liu, M. Chen, Q. Wu, and S. Chen, “Prediction of unmanned aerial vehicle target intention under incomplete information,” Scientia Sinica Informationis, Vol.50, No.5, pp. 704-717, 2020 (in Chinese). https://doi.org/10.1360/SSI-2019-0106
- [16] F. Teng et al., “A GRU-based method for predicting intention of aerial targets,” Computational Intelligence and Neuroscience, Vol.2021, Article No.6082242, 2021. https://doi.org/10.1155/2021/6082242
- [17] F. Teng, Y. Song, and X. Guo, “Attention-TCN-BiGRU: An air target combat intention recognition model,” Mathematics, Vol.9, No.19, Article No.2412, 2021. https://doi.org/10.3390/math9192412
- [18] F. Teng, X. Guo, Y. Song, and G. Wang, “An air target tactical intention recognition model based on bidirectional GRU with attention mechanism,” IEEE Access, Vol.9, pp. 169122-169134, 2021.
- [19] A. P. Yunus, K. Morita, N. C. Shirai, and T. Wakabayashi, “Time series self-attention approach for human motion forecasting: A baseline 2D pose forecasting,” J. Adv. Comput. Intell. Intell. Inform., Vol.27, No.3, pp. 445-457, 2023. https://doi.org/10.20965/jaciii.2023.p0445
- [20] H. Yin, D. Li, Y. Wang, and X. Li, “Adaptive dynamic occupancy guidance for air combat of UAV,” Unmanned Systems, Vol.12, No.1, pp. 29-46, 2024. https://doi.org/10.1142/S2301385024500031
- [21] H. Liu, Z. Ma, X. Deng, and W. Jiang, “A new method to air target threat evaluation based on Dempster-Shafer evidence theory,” 2018 Chinese Control and Decision Conf., pp. 2504-2508, 2018. https://doi.org/10.1109/CCDC.2018.8407546
- [22] R. Ying, J. You, C. Morris, X. Ren, W. L. Hamilton, and J. Leskovec, “Hierarchical graph representation learning with differentiable pooling,” Proc. of the 32nd Int. Conf. on Neural Information Processing Systems, pp. 4805-4815, 2018.
- [23] J. Li, P. Wang, H. Li, and K. Shi, “Enhanced time-expanded graph for space information network modeling,” Science China Information Sciences, Vol.65, No.9, Article No.192301, 2022. https://doi.org/10.1007/s11432-020-3202-2
- [24] H. He, Z. Peng, P. Shang, W. Wang, and X. Pei, “An end-to-end intent recognition method for combat drone swarm,” Proc. of the 8th Int. Workshop on Advanced Computational Intelligence and Intelligent Informatics, pp. 167-177, 2024. https://doi.org/10.1007/978-981-99-7590-7_14
- [25] C. Qu, Z. Guo, S. Xia, and L. Zhu, “Intention recognition of aerial target based on deep learning,” Evolutionary Intelligence, Vol.17, No.1, pp. 303-311, 2024. https://doi.org/10.1007/s12065-022-00728-9
- [26] W. Ou, S. Liu, X. He, and S. Guo, “Tactical intention recognition algorithm based on encoded temporal features,” Command Control & Simulation, Vol.38, No.6, pp. 36-41, 2016 (in Chinese).
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.