充分理解无人艇自主执行任务时面临的复杂场景，并有效组织多源数据为无人艇自主决策提供依据是无人艇领域研究的关键问题。针对无人艇领域知识表示问题以及任务场景下的自主决策问题，本文提出一种无人艇领域知识图谱的建模框架，融合多种类型的数据，为知识推理提供了知识库支撑。在此基础上，提出一种融合元路径信息的图神经网络嵌入模型来解决无人艇自主决策下的知识推理问题，最后在构建的无人艇领域知识图谱（USV-KG）上进行了链接预测实验，并与当前的基线知识图谱嵌入模型进行对比研究，结果表明该模型在多个指标上都达到了最优，为无人艇自主决策提供了有效的决策支持。
Fully understanding the complex scenarios that unmanned surface vehicles (USV) face during autonomous task execution, and effectively organizing multi-source data to provide a basis for autonomous decision-making, are key research challenges in the USV field. To address the issues of knowledge representation in the USV domain and autonomous decision-making in task scenarios, this paper proposes a knowledge graph modeling framework for the USV field, which integrates various types of data to support knowledge reasoning. On this basis, a graph neural network embedding model incorporating meta-path information is proposed to solve the knowledge reasoning problem in the context of USV autonomous decision-making. Finally, link prediction experiments were conducted on the constructed USV knowledge graph (USV-KG) and compared with current baseline knowledge graph embedding models. The research results show that this model achieves optimal performance across multiple metrics, providing effective decision support for USV autonomous decision-making.
2025,47(13): 46-51 收稿日期：2024-7-7
DOI：10.3404/j.issn.1672-7649.2025.13.009
分类号：U662
基金项目：国家自然科学基金重大项目（61991412）
作者简介：韩一博(1999-),男,硕士,研究方向为无人艇自主决策、知识推理
参考文献：
[1] 郭忠毅, 龙飞, 樊慧津, 等. 基于CLIPS的智能无人飞艇故障诊断专家系统开发[J]. 计算技术与自动化, 2020, 39(1): 1-7.
GUO Z Y, LONG F, FAN H J, et al. Fault diagnosis expert system development for intelligent airship based on CLIPS[J]. Computing Technology and Automation, 2020, 39(1): 1-7.
[2] CHEN X, HUANG C, YAO L, et al. Knowledge-guided deep reinforcement learning for interactive recommendation[C]//2020 International Joint Conference on Neural Networks (IJCNN), IEEE, 2020.
[3] D’ANIELLO G, GAETA M. Dominance-based rough set approach supporting experts in situation assessment[C]//2019 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA), IEEE, 2019.
[4] LI X, BILBAO S, MARTÍN-WANTON T, et al. SWARMs ontology: A common information model for the cooperation of underwater robots[J]. Sensors, 2017, 17(3): 569.
[5] GAO M, SHI G Y. Ship-collision avoidance decision-making learning of unmanned surface vehicles with automatic identification system data based on encoder-Decoder automatic-response neural networks[J]. Journal of Marine Science and Engineering, 2020, 8(10): 754.
[6] CHEN C, SEFF A, KORNHAUSER A, et al. Deepdriving: Learning affordance for direct perception in autonomous driving[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015.
[7] JI S, PAN S, CAMBRIA E, et al. A survey on knowledge graphs: Representation, acquisition, and applications[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 33(2): 494-514.
[8] ZHANG Q, WEN Y, ZHOU C, et al. Construction of knowledge graphs for maritime dangerous goods[J]. Sustainability, 2019, 11(10): 2849.
[9] CHEN Y, WANG J, ZHU S, et al. Knowledge graph construction for foreign military unmanned systems[C]//China Conference on Knowledge Graph and Semantic Computing. Singapore: Springer Nature Singapore, 2022.
[10] 马玉凤, 向南, 豆亚杰. 军事系统工程中的知识图谱应用及研究[J]. 系统工程与电子技术, 2022, 44(1): 146-153.
MA Y F, XIANG N, DOU YJ. Appliction and research of knowledge graph in military system engineering[J]. System Engineering and Electrinics, 2022, 44(1): 146-153.
[11] ZHANG G, CAO X, ZHANG M. A knowledge graph system for the maintenance of coal mine equipment[J]. Mathematical problems in engineering, 2021(1): 2866751.
[12] WANG J, LI R, LI R, et al. A knowledge-based deep learning method for ECG signal delineation[J]. Future Generation Computer Systems, 2020, 109: 56-66.
[13] WANG K, LIEW J H, ZOU Y, et al. Panet: Few-shot image semantic segmentation with prototype alignment[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.
[14] SEVGILI O, PANCHENKO A, BIEMANN C. Improving neural entity disambiguation with graph embeddings[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, 2019.
[15] BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating embeddings for modeling multi-relational data[J]. Advances in Neural Information Processing Systems, 2013.
[16] DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2d knowledge graph embeddings[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2018.
[17] SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[C]//The semantic web: 15th international conference, ESWC 2018, Heraklion, Crete, Greece, June 3–7, 2018, Proceedings 15. Springer International Publishing, 2018.
[18] FU X, ZHANG J, MENG Z, et al. Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding[C]//Proceedings of the Web Conference 2020, 2020.
