针对舰船操控台智能导航系统在复杂航行环境中面临的人机交互效率低、信号依赖性强等关键问题，设计基于人机交互技术的舰船操控台智能导航方法。以舰船操控台导航系统基本结构为基础，设计语音模态人机交互界面，利用语音意图理解框架与大语言模型解析指令并生成导航执行代码；将导航参数作为状态因子，引入RFR辅助GNSS-INS组合导航模型，构建RFR辅助因子图导航方法，确保舰船操控台智能导航效果。测试结果显示：该方法具备较好的人机交互效果，支持语音指令快速完成导航操作；在导航信号缺失时，生成的航行轨迹与设定航迹高度吻合；导航结果与设定航线的偏差最大值为（0.194,1.449,0.114）m，满足高精度导航要求。该方法显著提升了舰船导航的智能化水平和鲁棒性。
Design an intelligent navigation method for ship control consoles based on human-computer interaction technology to address key issues such as low human-machine interaction efficiency and strong signal dependence faced by intelligent navigation systems in complex navigation environments. Based on the basic structure of the ship control console navigation system, design a voice modal human-computer interaction interface, use a voice intent understanding framework and a large language model to parse instructions and generate navigation execution code; Using navigation parameters as state factors, an RFR assisted GNSS-INS integrated navigation model is introduced to construct an RFR assisted factor graph navigation method, ensuring the intelligent navigation effect of ship control consoles. The test results show that this method has good human-computer interaction effect and supports voice commands to quickly complete navigation operations; When the navigation signal is missing, the generated navigation trajectory matches the set trajectory altitude; The maximum deviation between the navigation result and the set route is (0.194, 1.449, 0.114) m, which meets the requirements of high-precision navigation. This method significantly improves the intelligence and robustness of ship navigation.
2025,47(13): 176-180 收稿日期：2025-1-3
DOI：10.3404/j.issn.1672-7649.2025.13.031
分类号：TP391
作者简介：方晓路(1985-),女,硕士,讲师,研究方向为视觉传达设计
参考文献：
[1] 朱曼, 文元桥, 孙吴强, 等. 一种基于扩展状态观测器的智能船舶Nomoto模型参数辨识方法[J]. 中国舰船研究, 2023, 18(3): 75-85.
ZHU M, WEN Y Q, SUN W Q, et al. Extended state observer-based parameter identification of Nomoto model for autonomous vessels[J]. Chinese Journal of Ship Research, 2023, 18(3): 75-85.
[2] 匡兴红, 黄傲威. 一种基于深度学习辅助的SINS/DVL组合导航方法[J]. 系统仿真学报, 2024, 36(8): 1810-1822.
KUANG X H, HUANG A W. A method based on deep learning for assisting SINS/DVL integrated navigation[J]. Journal of System Simulation, 2024, 36(8): 1810-1822.
[3] 王东宇, 张慧君, 李孝辉, 等. 遮挡环境下的基于AKF组合导航定位方法研究[J]. 电子测量与仪器学报, 2023, 37(5): 171-179.
WANG D Y, ZHANG H J, LI X H, et al. He Tao Research on positioning in covering environment with an AKF-based integrated navigation system[J]. Journal of Electronic Measurement and Instrumentation, 2023, 37(5): 171-179.
[4] 吴建峰, 程向红. 基于点线的视觉惯性导航系统初始化方法[J]. 中国惯性技术学报, 2024, 32(5): 463-467.
WU J F, CHENG X H. An initialization method for visual inertial navigation system based on point and line[J]. Journal of Chinese Inertial Technology, 2024, 32(5): 463-467.
[5] 李丹, 郭晓. 舰船卫星导航系统中信号融合误差纠偏技术[J]. 舰船科学技术, 2023, 45(21): 185-188.
LI D, GUO X. Research on signal fusion error correction technology in ship satellite navigation system[J]. Ship Science and Technology, 2023, 45(21): 185-188.
[6] 潘奇, 杨东华, 蔡委哲. 自然人机交互技术在雷达显控终端中的应用[J]. 现代雷达, 2024, 46(8): 78-83.
PAN Q, YANG D H, CAI W Z. Application of Natural Human-computer Interaction Technology in Radar Display and Control Terminal[J]. Modern Radar, 2024, 46(8): 78-83.
[7] 王湉, 范峻铭, 郑湃. 基于大语言模型的人机交互移动检测机器人导航方法[J]. 计算机集成制造系统, 2024, 30(5): 1587-1594.
WANG T, FAN J M, ZHENG P. Large language model-based approach for human-mobile inspection robot interactive navigation[J]. Computer Integrated Manufacturing Systems, 2024, 30(5): 1587-1594.
