Automatic collision avoidance of multiple ships based on deep Q-learning

As the number of ships for marine transportation increases with the globalisation of the world economy, waterways are becoming more congested than before. This situation will raise the risk of collision of the ships; hence, an automatic collision avoidance system needs to be developed. In this paper, a novel approach based on deep reinforcement learning (DRL) is proposed for automatic collision avoidance of multiple ships particularly in restricted waters. A training method and algorithms for collision avoidance of ships, incorporating ship manoeuvrability, human experience and navigation rules, are presented in detail. The proposed approach is investigated not only by numerical simulations but also by model experiments using three self-propelled ships. Through the systematic numerical and experimental validation, it is demonstrated the developed approach based on the DRL has great possibility for realising automatic collision avoidance of ships in highly complicated navigational situations.     

A novel framework for regional collision risk identification based on AIS data

Identification of regional collision risk in water area is of significance for the safety of navigation. However, traditional risk identification models are subject to the limitations in accuracy, short-term identification and traffic characteristics. Herein, a framework was put forward to identify regional collision risk instantaneously based on AIS data. The vessels were clustered by using the spatial clustering method. Afterwards, the framework was divided into two steps. Firstly, collision risk of each cluster was obtained by collision risk and contribution of the vessels within the cluster. An analytical method was adopted to identify collision risk of each vessel from the perspective of vessel pairs. Contribution of each vessel was determined by using improved Shapley value method in game theory. Secondly, regional collision risk was obtained by collision risk and contribution of each cluster. Case studies were carried out based on the AIS data of Northern Yellow Sea in China to validate the validity of the proposed framework. The results show that the proposed framework can effectively identify collision risk in water area, presenting the potential for collision risk monitoring and collision risk analysis of water area.     

AIS系统在海洋遥感卫星的应用与设计优化

目前国际和国内已普遍采用星载船舶自动识别系统（Automatic Identification System,AIS）接收系统提升针对全球船只信息的采集和监测能力。本文主要介绍了国内外星载AIS系统发展的主要进展及取得的成果,重点针对目前星载AIS系统存在的近海船只密集区域信号碰撞导致检测概率降低的技术问题,通过建模仿真找到具体原因,给出后续AIS星载载荷针对此问题在设计和应用上的优化建议。本文可作为后续星载AIS系统设计的参考。     

海上导航信息远程传输监控技术研究与应用

将北斗通信技术、船舶自动识别系统技术、航标遥测遥控技术以及GPS差分技术进行有效结合,研制了海上导航信息远程传输监控系统,对我国中、远海海域装有AIS设备的船舶进行跟踪与监控、可疑船舶的辨认、船舶的岸基调度、航标遥测遥控、GPS差分信息远程播发等。相比单一技术的应用,海上导航信息远程传输监控系统不受天气条件限制,无需人员定期出海维护,具有设备集成度高、导航差错率低、功能全面、成本效益好等特点。     

基于BiLSTM模型的远洋渔船类型识别研究

船舶自动识别系统(Automatic identification system,AIS)为渔业资源和渔船捕捞活动管理和研究提供了可能.明确船舶作业类型是开展AIS信息渔业研究应用前提,为渔业研究和管理提供渔船捕捞类型基础数据支撑,保障渔船作业安全和监督非法捕捞渔业活动,作者通过搜集整理3000多艘已知类型船舶信息,从...     

Assessment of manoeuvring performance of large tankers in restricted waterways: a real-time simulation approach

During the past 30 years there has been a steady growth in the size and number of ships that use the Strait of Istanbul (Bosporus) which is one of the most hazardous, crowded, difficult and potentially dangerous waterways in the world. There have been over 200 accidents over the past decade resulting in loss of life and serious damage to the environment. This paper presents the results of a real-time ship manoeuvring simulation study investigating the manoeuvring performance of large tankers in the Bosporus. The study was conducted with a ship manoeuvring simulator which is capable of subjecting a given hull form to any combination of environmental conditions, i.e. wind, current and wave drift forces. The results indicate that when realistic environmental conditions are taken into account the size of ships which can navigate safely in compliance with the traffic separation lanes is limited.     

Basic Design Criteria for Bridges Crossing Open Sea and Bay Area

Bridge design is a combination of art, science, and technology. Design of bridges crossing open sea and bay areas is always of a great challenge to engineers. Basic design criteria dealing with ownership and financing, location, expected service life, traffic models and capacity, environmental evaluation, risk policy, and extreme events shall be established as early as possible. In this article, the guidelines for conceptual design are first presented. Structural design criteria for extreme events such as seismic, wind, and vessel collision are then discussed.     

Basic Design Criteria for Bridges Crossing Open Sea and Bay Area

Bridge design is a combination of art, science, and technology. Design of bridges crossing open sea and bay areas is always of a great challenge to engineers. Basic design criteria dealing with ownership and financing, location, expected service life, traffic models and capacity, environmental evaluation, risk policy, and extreme events shall be established as early as possible. In this article, the guidelines for conceptual design are first presented. Structural design criteria for extreme events such as seismic, wind, and vessel collision are then discussed.     

船只目标SAR、HFSWR和AIS多手段融合探测的点迹关联分析

A space-borne synthetic aperture radar （SAR）, a high frequency surface wave radar （HFSWR）, and a ship automatic identification system （AIS） are the main remote sensors for vessel monitoring in a wide range. These three sensors have their own advantages and weaknesses, and they can complement each other in some situations. So it would improve the capability of vessel target detection to use multiple sensors including SAR, HFSWR, and A/S to identify non-cooperative vessel targets from the fusion results. During the fusion process of multiple sensors＇ detection results, point association is one of the key steps, and it can affect the accuracy of the data fusion and the efficiency of a non-cooperative target＇s recognition. This study investigated the point association analyses of vessel target detection under different conditions： space- borne SAR paired with AIS, as well as HFSWR, paired with AIS, and the characteristics of the SAR and the HFSWR and their capability of vessel target detection. Then a point association method of multiple sensors was proposed. Finally, the thresholds selection of key parameters in the points association （including range threshold, radial velocity threshold, and azimuth threshold） were investigated, and their influences on final association results were analyzed.     

A Novel Approach of Using Selected Unconventional Geodesic Methods of Estimation on VTS Areas

Abstract

The Vessel Traffic Service (VTS) systems belong to the fundamental tools used in ensuring a high level of safety across sea basins with heavy traffic, where the presence of navigational hazards poses a great risk of collision or a ship running aground. In order to determine the mutual location of ships, VTS systems obtain information from different facilities, such as coastal radar stations, AIS, and vision systems. Fixing a ship’s position is always accompanied by a degree of error, but the degree of error depends on the specific position fixing system used. In order to increase the accuracy of position fixing in VTS systems, the authors propose the use of contemporary geodetic methods. The article presents the theoretical fundamentals of two unconventional geodesic methods of estimation: M estimation and M_split(q)estimation and the authors’ own proposal of their application in VTS systems. The article concludes with a test verifying theoretical assumptions, performed with the use of a computer application allowing position fixing with the use of selected robust adjustment methods. Furthermore, an example is presented of M_split(q)estimation as used for the acquisition of low-signal radar echoes, which in VTS systems are not automatically identified for tracking. The level of the echo signal makes it difficult for a VTS controller to separate these objects from typical radar noise and interference.     

基于AIS信息校准的双频地波雷达的船只融合跟踪

高频地波雷达（HFSWR）和自动船只确认系统（AIS）是船只跟踪的重要传感器。高频地波雷达可以用来跟踪探测区域的所有船只,而AIS只能用来确认合作船只的信息。由于海杂波的干扰,使用单频率地波雷达的船只跟踪会淹没在布拉格峰值的盲区里,改变探测频率是克服这一缺点的有效手段。在这种背景下,我们提出一种基于AIS校准的双频雷达融合探测算法。因为不同频率的地波雷达测量与AIS的测量值存在系统误差,所以AIS信息可以用来估计和校准地波雷达的每个频率的系统误差。首先,将合作目标的点迹测量与地波雷达的点迹测量通过JVC分配算法进行点迹关联。从合作船只的点迹关联结果中,双频雷达的系统误差可以估计和校准。其次,基于校准的双频雷达数据,使用融合JPDA-UKF算法进行船只跟踪。通过真实探测的数据的实验结果显示所提算法可以实时跟踪船只,相比单频率跟踪可以进一步提高跟踪能力和跟踪精度。     

Economic evaluation of vessel traffic service (VTS): A contingent valuation study

Maritime safety has become a major concern in Korea. As an alternative to improve maritime safety, the Korean government is considering enhancing infrastructure associated with maritime safety, in the form of a vessel traffic service (VTS) facility for high density waterways. This study estimates the public value of a VTS facility construction project using the contingent valuation (CV) method. A CV survey using person-to-person interviews was administered to 400 randomly selected households to elicit their willingness to pay (WTP) for the project. Overall, the respondents accepted the contingent market, and on average, Korean households were willing to pay a significant amount toward the project. The mean WTP for the project is estimated to be approximately KRW 4149.5 (USD 3.7) per year per household, which is statistically significant. The estimate of the fiduciary benefit to Korean households is approximately KRW 11.07 billion (USD 9.91 million) per year for five years. The results are expected to be useful for policy-makers in determining the economic feasibility of a VTS.     

基于AIS的船舶会遇局面紧迫度量化分析

近年来船舶大型化、高速化的发展以及数量的不断递增,导致船舶碰撞概率大大增加。为更好地保障船舶航行安全,提出船舶会遇局面紧迫度这一概念。该概念表征船舶在当前航行状态下由于一定范围内所有其他船舶的存在而处于的会遇局面的紧迫程度,其旨在帮助船舶驾驶员实时感知并掌握船舶在海上航行时所处会遇局面的状况,从而据此加以判断并及时采取措施规避碰撞风险。建立了船舶会遇局面紧迫度的计算模型,该模型以考虑到本船速度的动态圆形领域为空间约束条件,综合考虑其他船舶相对于本船的方位分布和距离这两个指标的影响,基于信息量量化紧迫度。利用2016年1月1日天津港AIS数据进行紧迫度的计算与分析,计算结果与实际相符,该计算模型能够准确反映船舶在航行过程中所处会遇局面的紧迫程度。利用双线性内插法建立天津港区域紧迫度二维彩色平面分布图,其表达效果优于传统热度图。     

海商法视角下对CMI无人船调查问卷的思考

为解决无人船适用海商法存在的问题,促进我国无人船海上运输产业的健康可持续发展,文章从法理的角度阐释国际海事委员会无人船调查问卷中无人船的法律地位、船长和船员的认定以及无人船的碰撞责任,提出无人船适用海商法存在不确定性风险;在海商法领域,无人船的法律地位认定、船长和船员的识别以及船舶碰撞责任的适用仍存在问题,解决上述问题的有效路径是明确无人船的法律地位、将岸基控制人员识别为船员、采用过错责任原则认定无人船的碰撞责任以及合理分配船东与生产者之间的碰撞责任,以合理规避无人船的风险。     

基于深度学习和时空特征融合的海洋渔船密度预测方法

为了从海量渔船轨迹数据中挖掘隐含的信息和知识,进而为渔业行政主管部门的决策提供科学依据,本研究以AIS渔船轨迹数据为研究对象,提出了一种基于深度学习和面向时空特征融合的海洋渔船密度预测方法：首先,利用渔船轨迹数据集对渔船行驶区域进行网格划分;其次,筛选出渔船高密度区域进行研究,避免数据稀疏性问题;再次,根据渔船轨迹数据的时空分析,构建三维时空融合矩阵;最后,通过卷积循环神经网络模型捕获渔船分布的时间和空间特征,并利用卷积神经网络的堆叠加强对空间特征的学习。实验通过东海海域渔船真实轨迹数据进行具体测试,结果表明渔船密度预测值与真实值非常接近,平均绝对误差为4×10-4,模型较好地拟合了渔船密度分布特征,有效地提高了渔船捕捞热点预测的准确性和鲁棒性。     

面向海运统计的AIS大数据挖掘分析研究

为解决传统海运产业统计方法数据质量不高、时效性差、统计产品陈旧短缺、公信力不足等的问题,提出基于AIS大数据挖掘分析开展海运统计的方法.详细阐述了基于AIS大数据的海运统计分析技术路线、大数据平台技术架构,以及电子围栏分析、航行事件分析、航次分析和统计指标生成等关键模型算法.以2019年3月至5月全球大宗货品船舶的AIS数据应用为例表明,该方法可提供港口、海上通道和大宗货品三方面的海运大数据统计指标,为实现海运即时化、准确化、精细化的统计分析与展现提供了新思路.     

Optimized support vector regression algorithm-based modeling of ship dynamics

This study contributes to solving the problem of how to derive a simplistic model feasible for describing dynamics of different types of ships for maneuvering simulation employed to study maritime traffic and furthermore to provide ship models for simulation-based engineering test-beds. The problem is first addressed with the modification and simplification of a complicated and nonlinearly coupling vectorial representation in 6 degrees of freedom (DOF) to a 3 DOF model in a simple form for simultaneously capturing surge motions and steering motions based on several pieces of reasonable assumptions. The created simple dynamic model is aiming to be useful for different types of ships only with minor modifications on the experiment setup. Another issue concerning the proposed problem is the estimation of parameters in the model through a suitable technique, which is investigated by using the system identification in combination with full-scale ship trail tests, e.g., standard zigzag maneuvers. To improve the global optimization ability of support vector regression algorithm (SVR) based identification method, the artificial bee colony algorithm (ABC) presenting superior optimization performance with the advantage of few control parameters is used to optimize and assign the particular settings for structural parameters of SVR. Afterward, the simulation study on identifying a simplified dynamic model for a large container ship verifies the effectiveness of the optimized identification method at the same time inspires special considerations on further simplification of the initially simplified dynamic model. Finally, the further simplified dynamic model is validated through not only the simulation study on a container ship but also the experimental study on an unmanned surface vessel so-called I-Nav-II vessel. Either simulation study results or experimental study results demonstrate a valid model in a simple form for describing the dynamics of different types’ ships and also validate the performance of the proposed parameter estimation method.     

舰船卫星探测实验中利用AIS获取现场同步数据的可行性分析

在SAR与AIS联合探测探测舰船目标实验中,通过对2010-11-05T06：51渤海海峡Radarsat-2影像的和与之时空匹配的AIS数据比较,发现2种手段探测到的静止的舰船目标能够精确的匹配,但是运动的舰船目标存在一定的偏差.分析了偏差产生的原因,其中距离向偏差是由时间误差引起的;方位向偏差主要是由多普勒频移造成的;这与运动舰船目标的航速、航向及SAR与AIS的探测时间误差有关.在此基础上建立了数学模型,分析上述参数对偏差的影响,并对偏差加以修正,从而实现了SAR与AIS探测结果的匹配.     

Application of failure and fracture criteria during a tanker head-on collision

In this paper a discussion of three failure criteria during a tanker collision takes place. The ‘Fracture Criterion’ developed recently [Glykas, A., Samouelides, E., Das, P.K. (1996) Energy absorption capacity of plates under lateral loading. Proceedings of the 6th International Conference of Offshore and Polar Engineers, Los Angeles '96, Vol. IV, pp. 502–509.], deals with the amount of energy required so that arbitrary crack propagation originates from microscopic material flaws of the steel structure, in areas of high strain concentration during large deflections. This fracture criterion is applied in critical areas of a tanker bow structure during head-on collision with a vertical rigid body and its validity is examined in comparison to other two state of the art failure criteria. The penetration of the tanker vessel as well as the time to rest from the initiation of the collision are determined in relation to the failure criteria.