船舶远程驾控人机交互界面优化设计研究

李梦霞; 徐图远; 邹天悦; 柳晨光; 郑茂; 初秀民; 严新平

doi:10.19818/j.cnki.1671-1637.2025.03.020

船舶远程驾控人机交互界面优化设计研究

doi: 10.19818/j.cnki.1671-1637.2025.03.020

李梦霞^{1, 2, 3},
徐图远^{1, 2, 3, 4},
邹天悦^{1, 2, 3, 4},
柳晨光^{1, 2, 3},
郑茂^{1, 2, 3},
初秀民^{1, 2, 3},
严新平^{1, 2, 3, 4, ,}

1.
武汉理工大学水路交通控制全国重点实验室，湖北武汉 430063
2.
武汉理工大学智能交通系统研究中心，湖北武汉 430063
3.
武汉理工大学国家水运安全工程技术研究中心，湖北武汉 430063
4.
武汉理工大学交通与物流工程学院，湖北武汉 430063

基金项目:

a国家自然科学基金项目 52401422

中国博士后科学基金项目 GZC20241296

详细信息

作者简介:
李梦霞(1994-)，女，浙江东阳人，武汉理工大学副研究员，工学博士，从事船舶远程驾控与自主航行研究

通讯作者:
严新平(1959-)，男，江西莲花人，中国工程院院士，武汉理工大学教授，工学博士

中图分类号: U664.82
计量
- 文章访问数: 273
- HTML全文浏览量: 115
- PDF下载量: 20
- 被引次数: 0
出版历程
- 收稿日期: 2024-05-23
- 录用日期: 2025-04-30
- 修回日期: 2025-03-06
- 刊出日期: 2025-06-28

Research on optimal design of human-machine interaction interface of remote navigation and control ships

LI Meng-xia^{1, 2, 3},
XU Tu-yuan^{1, 2, 3, 4},
ZOU Tian-yue^{1, 2, 3, 4},
LIU Chen-guang^{1, 2, 3},
ZHENG Mao^{1, 2, 3},
CHU Xiu-min^{1, 2, 3},
YAN Xin-ping^{1, 2, 3, 4
, ,}

1.
State Key Laboratory of Maritime Technology and Safety, Wuhan University of Technology, Wuhan 430063, Hubei, China
2.
Intelligent Transport System Research Center, Wuhan University of Technology, Wuhan 430063, Hubei, China
3.
National Engineering Research Center for Water Transport Safety, Wuhan University of Technology, Wuhan 430063, Hubei, China
4.
School of Transportation and Logistics Engineering, Wuhan University of Technology, Wuhan 430063, Hubei, China

Funds:

National Natural Science Foundation of China 52401422

China Postdoctoral Science Foundation Project GZC20241296

More Information

Corresponding author: YAN Xin-ping (1959-), male, academician of Chinese Academy of Engineering, professor, PhD, xpyan@whut.edu.cn

Article Text (Baidu Translation)

摘要

摘要: 为保障船舶远程驾驶的安全性与可靠性，提出了一种船舶远程驾控人机交互界面优化方法，深入挖掘远程驾控员在操控过程中的视觉注意力分布变化情况，基于视点时序演化规律和界面分区重要度进行人机交互界面优化；通过分析在子界面的时序分布，提炼视点时序演化规律；建立子界面之间的逻辑关系和影响数值，通过相互影响程度量化各子界面的重要程度；基于视点时序演化规律和界面分区重要度的分析，确定人机交互界面各分区的位置关系、排列顺序和界面占比，实现对船舶远程驾控人机交互界面的优化；以重庆奉节船舶远程驾驶试验为例，开展转向、追越等场景试验。分析结果表明：在远程驾控员视点时序演化规律中，视点在“船艏视角”和“远程遥控船舶工况”之间相互转换有接近50%的占比；在界面重要度分析中，“船艏视角”和“远程遥控船舶工况”2个界面的视点分布权重总和有近70%占比。所提方法适用于远程驾驶船舶的人机交互界面优化设计，可面向不同智能化等级的远程驾驶船舶，提出人机交互界面优化设计方案。
- 水路运输 /
- 远程驾控 /
- 人机交互界面 /
- 眼动特征 /
- 界面重要度 /
- 视点演化规律
Abstract: To ensure the safety and reliability of ship remote navigation, an optimization method for the human-machine interaction (HMI) interface for remote navigation and control ships was proposed. The changes in visual attention distribution during the remote-controlled operation conducted by remote operators were deeply investigated. The HMI interface was optimized by considering the evolution patterns of viewpoint time series and the importance of interface partitions. By analyzing the distribution of viewpoint time series in sub-interfaces, the evolution patterns of viewpoint time series were extracted. The logical relationship and influence degrees among sub-interfaces were established, and the importance of each sub-interface was quantified based on the degree of mutual influence. According to the evolution patterns of viewpoint time series and the importance of interface partitions, the position relationship, arrangement order, and interface proportion of each partition of the HMI interface were determined, thus realizing the optimization of the HMI interface for remote navigation and control ships. Turning and overtaking scenarios of remote navigation and control ships were tested in Fengjie, Chongqing. Analysis results show that in terms of the evolution patterns of viewpoint time series during remote navigation, the viewpoint accounts for nearly 50% of the transitions between the "bow perspective" and the "operating conditions of remote-controlled ships". In the interface importance analysis, the total proportion of viewpoint distribution in these two interfaces accounts for nearly 70%. The proposed method is applicable to the optimized design of HMI interfaces for remote-controlled ships and can provide the corresponding optimized design schemes for such ships with different levels of intelligence.
- water transport /
- remote navigation and control /
- HMI interface /
- eye movement feature /
- interface importance /
- viewpoint evolution pattern

HTML全文

图 1 人机交互界面优化技术路线

Figure 1. Technical approach of optimization for HMI inferences

下载: 全尺寸图片幻灯片

图 2 试验船舶

Figure 2. Test ship

下载: 全尺寸图片幻灯片

图 3 岸基驾控中心实景

Figure 3. Real scene of shore-based control center

下载: 全尺寸图片幻灯片

图 4 Tobii Pro系列遥测式眼动仪

Figure 4. Remote eye tracker "Tobii Pro"

下载: 全尺寸图片幻灯片

图 5 人机交互界面

Figure 5. HMI inference

下载: 全尺寸图片幻灯片

图 6 数据分析区域划分

Figure 6. Regional segmentation based on data analysis

下载: 全尺寸图片幻灯片

图 7 权重有向分布

Figure 7. Weighted directed distribution

下载: 全尺寸图片幻灯片

图 8 视点热力分布

Figure 8. Viewpoint thermal distribution

下载: 全尺寸图片幻灯片

图 9 关刀峡水道

Figure 9. Guandao Gorge waterway

下载: 全尺寸图片幻灯片

图 10 转向追越场景轨迹

Figure 10. Trajectory of turning-to and chasing scene

下载: 全尺寸图片幻灯片

图 11 人机交互界面视点转移规律

Figure 11. Law of viewpoint transfer in HMI interface

下载: 全尺寸图片幻灯片

图 12 转向追越场景视点热力分布

Figure 12. Viewpoint thermal distribution in turning-to and chasing scene

下载: 全尺寸图片幻灯片

图 13 转向场景视点转移规律

Figure 13. Law of viewpoint transfer in turning-to scene

下载: 全尺寸图片幻灯片

图 14 转向场景视点热力分布

Figure 14. Viewpoint thermal distribution in turning-to scene

下载: 全尺寸图片幻灯片

图 15 追越场景视点转移规律

Figure 15. Law of viewpoint transfer in chasing scene

下载: 全尺寸图片幻灯片

图 16 追越场景视点热力分布

Figure 16. Viewpoint thermal distribution in chasing scene

下载: 全尺寸图片幻灯片

图 17 人机交互界面优化设计方案(等级2)

Figure 17. HMI optimization design scheme (degree two)

下载: 全尺寸图片幻灯片

图 18 人机交互界面优化设计方案(等级3)

Figure 18. HMI optimization design scheme (degree three)

下载: 全尺寸图片幻灯片

表 1 眼动仪技术参数

Table 1. Parameters of eye tracker

规格项目	指标参数
眼球追踪技术	基于视频的瞳孔角膜反射式眼动仪，明瞳与暗瞳追踪。单眼动追踪传感器捕获双眼图像，提供3D空间内准确的视线位置、眼睛位置和瞳孔直径测量。
采样频率/Hz	60或33
精确度/(°)	0.26(平均误差)
准确度/(°)	0.45
眼动仪延迟	约1帧
眨眼时间补偿	约1帧
追踪恢复时间/ms	50
操作距离	从眼动仪起45~95 cm
头动自由度	从眼动仪起65~75 cm
推荐屏幕尺寸	最大27英寸(16∶9比例)
数据处理	Tobii EyeChip^TMASIC芯片
功耗	典型功耗小于2.0 W，最大功耗为6.0 W
参照光源	暗瞳光源模组、明瞳光源模组

下载: 导出CSV

表 2 部分数据示例

Table 2. Partial data examples

记录时间戳	船艏视角-A	实时运动状态-B	船舶工况-C	驾驶台舱内视角-D	电子航道图与AIS融合-E
1705371376019	0	0	0	0	1
1705371376039	1	0	0	0	0
1705371376059	0	0	0	1	0
1705371376079	1	0	0	0	0
1705371376099	0	1	0	0	0

下载: 导出CSV

表 3 人机交互界面优化标准

Table 3. Optimization standard of HMI interface

界面位置关系		界面面积占比
界面视点演化规律(视点转移链路概率占比)	标准	界面分区重要度(分区重要度权重)	标准
最大或不小于40%	界面相邻	a	界面占比a±10%
30%~40%	界面间隔不大于1
其他	界面允许间隔

下载: 导出CSV

表 4 试验初始参数

Table 4. Initial parameters

会遇局面	船舶	初始位置		初始速度/kn	初始航向/(°)	相对距离/m
会遇局面	船舶	经度/(°)	纬度/(°)	初始速度/kn	初始航向/(°)	相对距离/m
转向	本船	109.428 0	30.994 2	1.56	280
追越	本船	109.434 4	30.992 4	8.28	080	376.26
追越	目标船	109.437 6	30.993 5	5.52	064	376.26

下载: 导出CSV

表 5 子界面转移总体比例分布

Table 5. Overall transfer ratio distribution across sub-interfaces %

转移后	转移前
转移后	A	B	C	D	E
A	0.00	4.56	25.42	5.04	1.20
B	5.52	0.00	5.28	0.24	0.48
C	24.22	5.28	0.00	3.84	3.60
D	5.28	0.72	3.36	0.00	0.48
E	0.96	0.96	2.88	0.72	0.00

下载: 导出CSV

表 6 转向场景子界面转移比例分布

Table 6. Transfer ratio distribution in turning-to scene across sub-interfaces %

转移后	转移前
转移后	A	B	C	D	E
A	0.00	5.10	25.00	6.12	1.53
B	5.61	0.00	3.06	0.51	1.02
C	25.00	2.55	0.00	3.57	4.08
D	5.10	1.53	3.57	0.00	0.00
E	1.53	1.02	4.08	0.00	0.00

下载: 导出CSV

表 7 追越场景子界面转移比例分布

Table 7. Transfer ratio distribution in chasing scene across sub-interfaces %

转移后	转移前
转移后	A	B	C	D	E
A	0.00	4.07	25.79	4.07	0.90
B	5.43	0.00	7.24	0.00	0.00
C	23.53	7.69	0.00	4.07	3.17
D	5.43	0.00	3.17	0.00	0.90
E	0.45	0.90	1.81	1.36	0.00

下载: 导出CSV

参考文献(27)

[1]	YOU X, MA F, LU S, et al. An integrated platform for the development of autonomous and remote-control ships[C]//TUHH. Proceedings of the 19th Conference on Computer and IT Applications in the Maritime Industries (COMPIT 2020). Pontignano: TUHH, 2020: 316-327.
[2]	马枫, 陈晨, 刘佳仑, 等. 船岸协同支持下的内河船舶远程驾控系统关键技术研究[J]. 中国舰船研究, 2022, 17(5): 125-133. MA Feng, CHEN Chen, LIU Jia-lun, et al. Key technologies of ship remote control system in inland waterways under ship-shore cooperation conditions[J]. Chinese Journal of Ship Research, 2022, 17(5): 125-133.
[3]	王远渊, 刘佳仑, 马枫, 等. 智能船舶远程驾驶控制技术研究现状与趋势[J]. 中国舰船研究, 2021, 16(1): 18-31. WANG Yuan-yuan, LIU Jia-lun, MA Feng, et al. Review and prospect of remote control intelligent ships[J]. Chinese Journal of Ship Research, 2021, 16(1): 18-31.
[4]	VENTIKOS N P, CHMURSKI A, LOUZIS K. A systems-based application for autonomous vessels safety: hazard identification as a function of increasing autonomy levels[J]. Safety Science, 2020, 131: 10.
[5]	MAN Y M, WEBER R, CIMBRITZ J, et al. Human factor issues during remote ship monitoring tasks: an ecological lesson for system design in a distributed context[J]. International Journal of Industrial Ergonomics, 2018, 68: 231-244.
[6]	PEETERS G, YAYLA G, CATOOR T, et al. An inland shore control centre for monitoring or controlling unmanned inland cargo vessels[J]. Journal of Marine Science and Engineering, 2020, 8(10): 27.
[7]	HAN C, ABEYSIRIWARDHANE A, CHAI S, et al. Future directions for human-centered transparent systems for engine room monitoring in shore control centers[J]. Journal of Marine Science and Engineering, 2022, DOI: 10.3390/jmse10010022.
[8]	NIU Y F, GAO Y, ZHANG Y T, et al. Improving eye-computer interaction interface design: ergonomic investigations of the optimum target size and gaze-triggering dwell time[J]. Journal of Eye Movement Research, 2019, 12(3): 14.
[9]	KLIEGL R, GRABNER E, ROLFS M, et al. Length, frequency, and predictability effects of words on eye movements in reading[J]. European Journal of Cognitive Psychology, 2004, 16(1/2): 262-284.
[10]	叶凤云, 常琳, 秦琴, 等. 基于虚假信息特征的社交媒体大学生用户感知信任研究[J]. 情报理论与实践, 2024, 47(10): 118-127. YE Feng-yun, CHANG Lin, QIN Qin, et al. Research of social media college students' perceived trust on false information features[J]. Information Studies: Theory and Application, 2024, 47(10): 118-127.
[11]	范超杰, 韩得民, 刘嘉滢, 等. 基于驾驶绩效的铁路人因安全评价指标体系研究[J]. 铁道科学与工程学报, 2024, 21(11): 4442-4455. FAN Chao-jie, HAN De-min, LIU Jia-ying, et al. Railway human factors safety evaluation index system based on driving performance[J]. Journal of Railway Science and Engineering, 2024, 21(11): 4442-4455.
[12]	TOREINI P, LANGNER M, MAEDCHE A. Using eye-tracking for visual attention feedback[C]//NEURO I S. Proceedings of the Information Systems and Neuroscience (NeuroIS) Retreat Workshop. Berlin: Springer, 2019: 2-6.
[13]	ZHOU X C, CEN Q Y, QIU H F. Effects of urban waterfront park landscape elements on visual behavior and public preference: evidence from eye-tracking experiments[J]. Urban Forestry and Urban Greening, 2023, 82: 10.
[14]	CHOU W Y S, TRIVEDI N, PETERSON E, et al. How do social media users process cancer prevention messages on Facebook? An eye-tracking study[J]. Patient Education and Counseling, 2020, 103(6): 1161-1167.
[15]	JONES W, KLAIMAN C, RICHARDSON S, et al. Eye-tracking-based measurement of social visual engagement compared with expert clinical diagnosis of autism[J]. Journal of the American Medical Association, 2023, 330(9): 854-865.
[16]	LEE D Y, SHIN Y, PARK R W, et al. Use of eye tracking to improve the identification of attention-deficit/hyperactivity disorder in children[J]. Scientific Reports, 2023, 13(1). 14469.
[17]	NORDFäLT J, AHLBOM C P. Utilising eye-tracking data in retailing field research: a practical guide[J]. Journal of Retailing, 2024, 100(1): 148-160.
[18]	苏思晴, 吕婷. 云旅游: 基于眼动实验的在线评论对旅游直播体验的影响研究[J]. 旅游学刊, 2022, 37(8): 86-104. SU Si-qing, LYU Ting. Virtual tourism: the impact of online comments on experience of tourism live broadcast based on eye movement[J]. Tourism Tribune, 2022, 37(8): 86-104.
[19]	郭晓芳, 赵伟慧, 张金滨. 基于眼动实验蒙古族服饰特征差异及分类研究[J]. 丝绸, 2024, 61(5): 94-104. GUO Xiao-fang, ZHAO Wei-hui, ZHANG Jin-bin. Research on the differences and classification of Mongolian costumes' characteristics based on eye-moving experiment[J]. Journal of Silk, 2024, 61(5): 94-104.
[20]	LI Y, DENG J, WU Q, et al. Eye-tracking signals based affective classification employing deep gradient convolutional neural networks[J]. International Journal of Interactive Multimedia and Artificial Intelligence, 2021, 7(2): 34-43.
[21]	郑一航, 李刚, 果霖, 等. 基于眼动追踪技术的直流往复锯造型兴趣区研究[J]. 电动工具, 2024(2): 1-4, 12. ZHENG Yi-hang, LI Gang, GUO Lin, et al. Research on the area of interest for DC reciprocating saw modeling based on eye tracking technology[J]. Electric Tool, 2024(2): 1-4, 12.
[22]	ZONTONE P, AFFANNI A, BERNARDINI R, et al. Emotional response analysis using electrodermal activity, electrocardiogram and eye tracking signals in drivers with various car setups[C]// IEEE. Proceedings of the 28th European Signal Processing Conference (EUSIPCO 2021). New York: IEEE, 2021: 18-22.
[23]	杜志刚, 潘晓东, 郭雪斌. 公路隧道进出口行车安全评价指标应用研究[J]. 同济大学学报(自然科学版), 2008, 36(3): 325-329. DU Zhi-gang, PAN Xiao-dong, GUO Xue-bin. Evaluation index's Application studies on safety at highway tunnel's entrance and exit[J]. Journal of Tongji University (Natural Science), 2008, 36(3): 325-329.
[24]	张杰. 基于眼动仪的驾驶员视点分布特性研究[J]. 湖南交通科技, 2012, 38(4): 153-155, 70. ZHANG Jie. Research on the distribution characteristics of driver's viewpoint based on eye tracker[J]. Hunan Communication and Technology, 2012, 38(4): 153-155, 70.
[25]	LIU S, YIN G. Research on color adaptation of automobile head-up display interface[C]//IEEE. 2021 IEEE 8th International Conference on Industrial Engineering and Applications (ICIEA 2021). New York: IEEE, 2021: 55-59.
[26]	李旭彪, 肖春, 李鼎夫. 山地城市快速路弯坡路段驾驶员眼动行为特性[J]. 公路, 2021, 66(8): 275-280. LI Xu-biao, XIAO Chun, LI Ding-fu. Characteristics of eye movement behavior of drivers on curved slopes of expressways in mountainous cities[J]. Highway, 2021, 66(8): 275-280.
[27]	李梦霞, 徐图远, 邹天悦, 等. 内河船舶远程驾控技术试验[J]. 交通运输工程学报, 2025, 25(2): 141-155. doi: 10.19818/j.cnki.1671-1637.2025.02.009 LI Meng-xia, XU Tu-yuan, ZOU Tian-yue, et al. Experimental research on remote navigation and control technology for inland waterway ships[J]. Journal of Traffic and Transportation Engineering, 2025, 25(2): 141-155. doi: 10.19818/j.cnki.1671-1637.2025.02.009