Abstract
The rapid development of artificial intelligence significantly promotes collision-avoidance navigation of maritime autonomous surface ships (MASS), which in turn provide prominent services in maritime environments and enlarge the opportunity for coordinated and interconnected operations. Clearly, full autonomy of the collision-avoidance navigation for the MASS in complex environments still faces huge challenges and highly requires persistent innovations. In this chapter, major advances in state-of-the-art autonomous maritime vessels and systems, and collision avoidance technologies, are thoroughly addressed in various maritime scenarios, from academic to industrial sides. Moreover, compositions of autonomous navigation and E-navigation technologies are analyzed to efficiently systematically clarify the mechanism and principles in typical maritime environments, whereby trade-off between autonomy and navigation action are highlighted. Finally, in light of overview of promising collision avoidance and action planning technologies, it is pointed out that collision-free navigation would significantly benefits the integration of MASS autonomy in various maritime scenarios.
Access provided by Autonomous University of Puebla. Download conference paper PDF
Keywords
- Collision avoidance
- Motion planning
- Autonomous navigation systems
- E-navigation
- Maritime autonomous surface ships
1 Introduction
China is known as a big shipping nation with nearly 20,000 km of coastline and 120,000 km of inland waterway, but it has not fully utilized this advantage. In recent years, with the advancement of the “Thirteenth Five-Year Plan”, the “Belt and Road strategy”, and the “South China Sea Strategy” and other shipping strategies, China has gradually moved to national shipping power. Meanwhile, the rapid development of unmanned boats, autonomous ship, and bionic robotic fish, such as aquatic unmanned surface systems and underwater unmanned systems, has not only changed the pattern of the shipping economy, but also promoted the development of safe shipping, green shipping, and intelligent shipping. In July 2017, the “Development Plan of New Generation Artificial Intelligence Technology” is promulgated and issued by the State Council of China [1], in which proposed that breakthroughs should be made in the autonomous computing architecture of unmanned system and autonomous control of drones, as well as autonomous driving of cars, ships and rail transit. Obviously, research on autonomous ship technology has been put on the agenda at the national level. In 2016, Google robot AlphaGo defeated multi-time international competition champion Li Shishi. It even caused a sensation in the field of artificial intelligence [2]. Once again, artificial intelligence represented by deep reinforcement learning has caught the attention of experts and scholars in various fields, and the same is true for the shipping industry.
The history of shipping development is the continuous improvement of navigation safety performance and transportation benefits. The problem of ship navigation safety has always been a hot issue in the field of marine transportation engineering, and it is also one of the main aspects that drive the growth of MASS and their technical needs. Every year, marine accidents caused by human errors or faults, such as the negligent lookout of the on-duty driver, are common. Autonomy technology effectively replaces human pilots in ship maneuvering and cargo transportation, which greatly reduces the probability of human-induced marine accidents. At the present stage, autonomy technology is limited to applications such as unmanned boats and underwater robots, but unmanned transport cargo ships cannot yet achieve autonomous navigation and completely autonomous. In recent years, the research hotspots of many scholars and experts on autonomous navigation decision and planning are roughly divided into path planning, obstacle avoidance planning, trajectory planning and behavioral decision-making. Compared with path planning, collision avoidance and trajectory planning, behavioral decision-making considers time series and space constraints more. Behavioral decision-making systems are used to replace crew. Obstacle avoidance and approaching target ports are optimized goals. The behavioral decision-making is actually imitating the human crew's thinking activity or process of ship maneuvering. In each collision avoidance or transportation process, the optimal navigation strategy is determined from many schemes in accordance with its own behavioral constraints.
This work analyses current challenges and opportunities for collision avoidance and motion planning for maritime autonomous navigation systems. In particular, the following contributions are provided:
-
1.
Review of state-of -the-art autonomous vessel and collision avoidance technology.
-
2.
Characterization of applications for maritime autonomous navigation systems.
-
3.
Classification of maritime autonomous surface ships and autonomous navigation systems.
-
4.
Overview of existing and future collision avoidance and motion planning technologies.
2 State-of-the-Art Autonomous Vessel and Collision Avoidance Technology
2.1 Advances in the MASS
Autonomy technology of MASS is the integration of many intelligent ship technologies, including autonomous navigation technology (navigation situation awareness technology, navigation behavioral decision-making technology, motion control technology), intelligent engine room operation and maintenance, ship-shore communication, intelligent hull, integrated testing and other technologies. With the developing of artificial intelligence and communication technology, the level of ship automation has been gradually enhanced. Intelligent ship, marine intelligent transportation and unmanned ship technology and other related fields have also been widely researched by foreign institutions and experts represented by Europe and other countries.
In recent years, the Norwegian Fraunhofer CML, as the first organization to research the demonstration of the unmanned cargo ship, completed the project maritime unmanned navigation through intelligence in network (MUNIN) from 2012 to 2015 to verify the concept of the autonomous ship, which is defined as a ship mainly guided by the autonomous decision support system and controlled by the remote control operator of the shore control center. The communication architecture solutions for the autonomous ship bridge, the autonomous machine room, the shore operation center and the operators connecting the ship to shore have developed and verified [3]. Supported by the Norwegian Research Council, the University of science and technology of Norway started the autonomous marine operations and systems (AMOS) project research in 2013. The architecture of AMOS is shown in Fig. 1. It is expected to complete the research on autonomous ships and robot systems in 2023, and develop the structure and operation of safer, smarter and more environmentally friendly ships and offshore intelligent platforms [4]. In October 2016, the Norwegian forum for autonomous ships (NFAS) was established to release information about international conferences and reports related to MASS, and in October 2017, under the organization of NFAS and SINTEF ocean, Norway, China, the United States and other countries established the international network for autonomous ships (INAS), marking the research of MASS has been promoted to the national level, even to the international level [5, 6]. The SINTEF ocean laboratory in Trondheim, Norway, and Kongsberg, a technology company, jointly developed autonomous ship named Yara Birkeland, the first electric propulsion Unmanned Container Ship in the world. As shown in Fig. 2, the ship has a length of 70 m, a width of 15 m, and can carry 100–150 teu. It has been tested in the water pool of SINTEF since September 29, 2017. It can use its own installed GPS, radar and camera. For example, aircraft and sensors can avoid other ships in the channel, and realize auto-docking when arriving at the terminal point. In 2018, the autonomous navigation test from the port of Herøya in Norway to the port of Brevik has been realized for the first time [7].
Rolls-Royce of the UK and Stena Line AB of the Swedish ferry company will jointly develop the first intelligent ship sensing system. At the “Seminar of Unmanned Ship Technology” held in 2016, the “Development Plan of Advanced Unmanned Ship Application” was launched. It is expected that the use of remote support and specific function operations will gradually reduce the appointment of crew members in 2020; remote control of offshore MASS by 2025; remote control of ocean MASS by 2030; autonomous ocean-going MASS by 2035 [8]. At the national level, the UK has established the UK Maritime Autonomous Systems Regulatory Working Group (MASRWG) to develop a regulatory framework for MASS and industry-led behaviors and practices for the safe operation of MASS. The criteria, as shown in Table 1, are the classification of MASS in the United Kingdom. The second version of the code of conduct for the MASS industry was released in November 2018, the third version of the code of conduct for the MASS industry was released in November 2019, which include autonomous ships certification, registration of MASS, standards for MASS demonstration and testing areas in British waters, training, skills and qualifications and so on [9,10,11].
Other countries have also achieved excellent research results in unmanned ship. They have their own independently developed MASS, but most of them are used in the military field, such as the United States, Israel, France, Italy, Japan, Belarus and other countries, the parameters of unmanned surface vehicle (USV) developed by these countries are shown in Table 2 [10,11,12,13] (Figs. 3, 4, 5, 6, 7, 8, 9, 10 and 11).
According to statistics and comparisons of MASS in other countries, most countries have developed small USV earlier, and they are used for marine environmental monitoring or military reconnaissance and strike. The military use is represented by the “Spartan Scout” in the United States. It is the earliest and most versatile. The ship is light, shallow draft, fast maneuvering, and strong endurance. For intelligence, surveillance, reconnaissance/force protection, anti-mine operations, precision strike/anti-ship operations and anti-submarine operations. Since 2016, countries have begun researching large MASS, mostly used for cargo transportation and intelligent shipping.
However, the research on domestic unmanned cargo ship technology started late, and the technology lags behind foreign countries. From 2009 to 2017, Yunzhou Intelligent Technology Co., Ltd., Lingjing Technology, Harbin Engineering University, Wuhan University of Technology, Huazhong University of Science and Technology, Shanghai University, Dalian Maritime University and other institutions and universities of China only conducted relevant research on USV and autonomy navigation technology, and has achieved some excellent results in the marine environment information acquiring, pollution source detection and rescue salvage, etc., but for the autonomous cargo transport ship is only a preliminary study, the parameters on USV of various research institutions are shown in Table 3 [14,15,16,17,18,19,20].
As shown in Fig. 12, the center for Intelligent Maritime Vehicle of Dalian maritime university of China then developed a platform for “zhihai-1” unmanned surface vehicle. The research platform consists of unmanned aerial vehicle (UAV) body, which includes inflatable buoy and UAV landing platform, equipment box and support erected on the buoy. The hull is connected with a propulsion structure placed outside the ship body, which reduces the hull volume, has simple structure, and is directly water cooled, which greatly saves cost. The hull adopts two inflatable buoys to form a double hull structure, which enhances the navigation stability and is convenient Maintenance: the equipment boxes on both sides contain batteries to provide energy for the propulsion system. Electronic devices such as attitude sensors, GPS receivers, microprocessors and other electronic devices are placed in the equipment boxes in the middle, which can obtain GPS information, pitch angle, roll angle and heading angle, and output acceleration information in the attachment setting system, which greatly improves the measurement accuracy. The UAV adopts wireless communication components, which can directly communicate with external mobile terminals and ground control stations [21, 22].
In March 2016, China Classification Society issued the code for intelligent ships, which specifically introduces the architecture, function and technical requirements on intelligent navigation, intelligent hull, intelligent engine room, intelligent energy efficiency management, intelligent cargo management and intelligent integrated platform, as well as the main functions and implementation difficulties of autonomous navigation technology [23]. It is the first code in China, covering hull, onboard equipment and navigation. It is playing a great significance to promote the construction of intelligent ships and promote the development of autonomy technology.
In June 2017, HNA and China Classification society jointly established the “unmanned cargo ship development alliance” with several units at home and abroad, integrating domestic and foreign ship autonomous navigation technology, navigation situation awareness technology, sailing behavioral decision support technology, control and communication technology, aiming to develop the unmanned cargo ship. The alliance is the first enterprise alliance in China to research and develop the technology of unmanned cargo ship, which promotes the industrialization development of unmanned ship technology [24].
In July 2017, China shipbuilding industry, Dalian Maritime University, CCS and the Academy of water science of the Ministry of transport jointly built the joint key laboratory of unmanned ship technology and system. The laboratory mainly researches and develops the autonomous cargo ship from the aspects of the construction, autonomous navigation technology and system, control, etc., promotes the combination of research and production, and aims at the countries and research institutions with advanced unmanned technology in the field of unmanned vessel, such as Europe. In December 2017, Dalian Maritime University established “Research Institute for collaborative innovation of unmanned ship technology and system” at the annual meeting of scientific and technological innovation [25].
On July 18, 2017, the intelligent shipping seminar was held in Hangzhou, focusing on the four core topics of research status of intelligent shipping technology, application of intelligent shipping technology, maritime security in the era of intelligent shipping and prospect of intelligent shipping development, which include international conventions, revision of rules, promotion of domestic policies, R & D and application of intelligent shipping related technologies, and ships. The in-depth discussion on ship manufacturing and operation has been carried out, focusing on the close connection with relevant work of the International Maritime Organization (IMO), which will further promote the formation of domestic implementation plan and work plan for the development of intelligent shipping in the future [26].
In May 2018, the high-end forum of China's unmanned vessel technology and innovation was successfully held in Shanghai with the theme of “new opportunities for surface unmanned vessel in the era of artificial intelligence". Famous experts and professors from the Institute of automation of the Chinese Academy of Sciences, Harbin Engineering and other important research institutions of domestic unmanned vessel were invited to participate in the exchange and discussion, which promoted the rapid development and application of the new generation of artificial intelligence in China The best opportunity and opportunity for the development of the ship industry solved the bottleneck of the development of the traditional unmanned ship industry [27].
Autonomous navigation technology of unmanned vessel includes ship navigation situation awareness technology and collision avoidance behavioral decision technology. For the navigation situation awareness of MASS, the channel, surrounding ships and navigation status information can be obtained by the existing radar, Automatic Identification System (AIS), Electronic Chart Display and Information System (ECDIS), Global Positioning System (GPS) and other navigational instruments. The depth, water flow speed, wind speed, wind direction needs to be obtained by sensors. For non-ship obstacles, the laser scanner and radar fusion recognition should also be used [28,29,30,31,32]. However, MASS are still facing the scientific conundrum on intelligent recognition of small mobile targets at sea. For the behavioral decision technology of unmanned vessel collision avoidance, the application methods include improved artificial potential field, three-dimensional display, expert system, fuzzy logic, neural network, evolutionary computation, swarm intelligence and immune algorithm and other artificial intelligence and soft computing methods [33,34,35]. However, unmanned vessel still faces the difficult of autonomous decision-making of vessel navigation and intelligent collision avoidance behavioral decision in complex waters. With internet of things as the core technology, communication technology is mainly composed of general packet radio service (GPRS), wireless transmission technology and wireless receiving technology satellite communication [36, 37]. After the development of VHF data exchange system (VDES), navigation data (NAVDAT) and other communication technologies mature, they will be used as a part of the marine communication system to further improve the reliability of shore ship communication. Shore-based support system is composed of monitoring center and information support center. Under the “e-navigation” strategy, the unification and integration of shore-based information promotes the development of shore-based support for MASS. According to the research status of e-navigation, in the aspect of shore based support, we should focus on the shore-based information push service technology according to the navigation situation of MASS, to avoid information overload, to provide different real-time shore based support services according to the navigation stage, to provide intelligent information service and intelligent management information [38]. At present, the most prominent application is the integrated bridge system. The integrated bridge system has simple route planning, automatic collision avoidance and route tracking functions, but there is still a large distance from the real unmanned ship, especially under the conditions of high complexity, large calculation and high reliability, many integrated test theories and technologies still need further research and application.
2.2 Advances in Collision Avoidance and Action Planning Technology
Collision avoidance system plays the role of copilot in the whole autonomous navigation system. The problem to be solved is to determine the obstacle avoidance and navigation strategy on the basis of knowing the environmental information of the MASS. At present, the research on the technology of collision avoidance for MASS at home and abroad is mainly divided into local path planning, multi-ship intelligent collision avoidance, behavioral planning, motion control and so on. However, there are few researches on the behavioral decision-making of collision avoidance.
For the study on intelligent collision avoidance and motion planning of ships, the existing models mainly contain knowledge-based expert systems, fuzzy logic, artificial neural networks, intelligent algorithms (genetic algorithms, and ant colony algorithms etc.). In addition, a ship collision avoidance system based on the general structural model of the expert system has been established [39]. Moreover, a comprehensive and systematic study has been performed for the whole process of ship collision avoidance, and a mathematical model for the safety passing distance, pressing situation, and ship collision risk has been established. Yunsheng Fan, Xiaojie Sun, and Guofeng Wang [40] combined the velocity resolution method and backstepping tracking controller, a dynamic collision avoidance control method in the unknown ocean environment is presented. A novel dynamic programming (DP) method was proposed to generate the optimal multiple interval motion plan for MASS by Xiongfei Geng, Yongcai Wang, Ping Wang, et al. [41]. The method provided the lowest collision rate overall and better sailing efficiency than the greedy approaches. JH Ahn, KP Rhee, and YJ You [42] combined fuzzy inference systems with expert systems for collision avoidance systems. They proposed a method for calculating the collision risk using a neural network. Based on the distance to closest point of approach (DCPA) and the time to closest point of approach (TCPA), the multi-layer perceptron (MLP) neural network was applied to the collision avoidance system for compensating for the fuzzy logic. C Hua [43] optimized the shortest path and minimum heading of the local path and designed the path planning of the USV under the constraints of the close distance meeting model of the ship and 1972 International Collision Avoidance Rules. The target genetic algorithm realized the intelligent collision avoidance of USV through simulation. Marilia Abilio Ramos, Ingrid Bouwer Utne, and Ali Mosleh [44] presented a task analysis for collision avoidance through hierarchical task analysis and cognitive model for categorizing the tasks, which explored how crew can be a key factor for successful collision avoidance in future MASS navigation. The results provided valuable information for the design stage of the MASS.
The above-mentioned models usually have an assume complete environmental information. However, in an unknown or uncertain environment, prior knowledge of the environment is difficult to acquire. It is difficult to form a complete and accurate knowledge base, and the rule-based algorithm is difficult to cope with various situations. Therefore, in many practices, the system needs to have strong adaptive ability. Recently, deep reinforcement learning (DRL) combined with deep neural network models and reinforcement learning have made significant progress in the field of autonomous navigation for USV, unmanned aerial vehicles (UAV), and unmanned ground vehicles (UGV). Tai L, Li S, Liu M [45] combined deep learning and decision-making processes into a highly compact, fully connected network, with raw depth images as the input and the generated control commands as the outputs to achieve model-free obstacle avoidance behavior. Long P, Liu W, and Pan J [46] proposed a novel end-to-end framework for generating effective reactive collision avoidance strategies for distributed multi-agent navigation based on deep learning. Panov A I et al. [47] proposed an approach for using a neural network to perform the path planning on the grid and initially realize it based on deep reinforcement learning. M Bojarski et al. [48] used convolutional neural networks for end-to-end training driving behavioral data, mapping the raw pixels from a single-front camera directly to the steering commands for unmanned vehicle adaptation path planning. The performance of the model and results of learning were better than the traditional model, but the only improvement was that the model was less interpretable. Cheng Y. et al. [49] proposed a simple deep reinforcement learning obstacle avoidance algorithm based on the deep Q learning network, using a convolutional neural network to train the ship sensor image information. The interaction with the environment was included by designing the incentive function in reinforcement learning. The maximum expected value of the cumulative return was obtained, and the optimal driving strategy of the underactuated was derived. However, improvement in the literature research increases the complexity of the verification environment and dynamic obstacle environment. Compared with [49] Refs, the different and better aspects of [50] Refs are: On the one hand, [50] Refs uses long short-term memory (LSTM) to do deep learning network to simplify the network structure and improve the iterative rate. On the other hand, [50] Refs learns the ship navigation state data, including relative azimuth and relative distance improve the accuracy and effectiveness of decisions. An intelligent collision avoidance decision model of MASS based on deep reinforcement learning is established. The problems encountered in intelligent avoidance decision for MASS is analyzed, and the design criteria are put forward. Based on this, a decision-making model based on Markov decision process (MDP) is established [50] Refs. Solving the optimal strategy of intelligent decision-making model makes the maximum return which is in unmanned vessel state to behavior mapping through the value function A reward function is specifically designed for target approaching, off course and safety. Finally, the simulation experiments of the intelligent collision avoidance decision-making method based on deep reinforcement learning are carried out respectively in static and dynamic waters, so as to demonstrate the feasibility of proposed method in actual application by Chengbo W. and Xinyu Z. et al. [51,52,53,54,55].
For the study on motion control and trajectory tracking control of ships, Wang Ning et al. puts forward the analytical framework model of ship domain consent. Through the parametric and hierarchical study of the quaternion ship domain model, the shortcomings of the existing ship domain model such as subjectivity and uncertainty are overcome, and the accuracy and effectiveness of ship collision avoidance are improved [56,57,58,59]. In order to effectively deal with the extremely strong unmodeled dynamics, model uncertainty and unknown external interference of the USV, an intelligent self-structured robust adaptive track tracking control strategy independent of the model is proposed by N.W. et al., realized a new method of precise track tracking control of the surface ship under the unknown time-varying complex sea conditions, and then proposed a limited time tracking control strategy of the USV, accurately suppress and cancel external interference and system uncertainty [60,61,62,63,64,65,66]. To further support such a cooperative and coordinated manner for USVs, a new intelligent multi-task allocation and path planning algorithm has been proposed based upon the self-organizing map (SOM) and the fast-marching method (FMM) by Liu, Y., Zhou, X., and Tan, G. et al. [67,68,69].
3 Maritime Autonomous Navigation Systems
Maritime autonomous navigation systems of collision avoidance can increase the safety of life at sea. The minimize the risk of collisions to assist the Master or officer of watch (OOW) in their analysis of encounter situations by simultaneous plotting of all targets in the declared range. Meanwhile, the calculation of the safe course or speed to pass clear from all targets, according to the International Regulations for Preventing Collisions at Sea (COLREG). Therefore, it is recommended to develop performance standards that will assist the shipping community in proper analysis, design, testing and approval of such system.
This section provides a general perspective on navigation systems of collision avoidance for maritime autonomous surface ships and modules of autonomous navigation systems that are present in the future.
3.1 Challenges in Autonomous Navigation Systems in Uncertain Environment
The marine environment is changeable. The autonomous navigation of ship in the coastal waters is more complicated than cars driving on the roads. Combined with the characteristics of the marine environment, in view of the main difficulty faced by the intelligent decision for collision avoidance of MASS, the following problems to be faced by the behavioral decision of MASS is putting forward [70, 71]:
-
(1)
The marine environment is complex and changeable [72]. First of all, the marine natural environment is changeable, and the wind, current, surge, wave and other time-varying are strong, which greatly affects the autonomous navigation of ships. Offshore waters have strong structural navigation characteristics, with many types of divided navigation and a large amount of navigation information, such as light buoy, channel buildings, navigation signal lights, irregular small fishing boats and other external environmental factors. Therefore, the intelligent behavioral decision of MASS needs to consider the constraints of multi-source heterogeneous information and extract effective information.
-
(2)
The sea traffic is disorderly, and there are many types of participants [73]. Due to the different tonnages and types of ships, the maneuverability of ships is different. Therefore, the information such as ship types should be considered in the decision systems. It is a major issue to avoid small obstacles for the decision system, especially for the small fishing boats that are too fast to comply with the rules of maritime traffic during the fishing period, which causes the phenomenon of maritime traffic chaos.
-
(3)
The ultimate goal of autonomous navigation for MASS is to realize the thinking of brain like maneuvering [74]. When ship handling, the pilot considers people, ship and route as a whole, and carries out reactive sailing under the guidance of some maritime traffic rules, experience and intention. For intelligent collision avoidance decision of MASS, it is necessary to learn from the decision process of crew in dealing with complex traffic scenes, learn the driving experience and the fuzzy definition in the rules reasonably, and personify the navigation behavioral decision.
The complexity of the above three uncertain environments has a certain impact on the rationality and effectiveness of the autonomous navigation behavioral decision for MASS, which is mainly reflected in the closed loop of the whole voyage [75]. Three uncertain include the scene elements in the navigation situation, the space–time characteristics and status of the obstacles, the binary relationship between MASS and the obstacles effective modeling. Therefore, MASS needs effective description and modeling of behavior decision expert knowledge base (international maritime traffic rules, good seamanship) based on scene division, and intelligent collision avoidance decision and navigation decision reasoning based on self-learning of navigation situation.
In the actual voyage, the navigation behavioral decision of MASS still faces more uncertainties [76,77,78], such as:
-
(1)
Uncertainty of marine environment [79]. The sea is vast and infinite, and human's understanding of the sea is very limited. In the voyage, there are not complete kinds of environmental prior knowledge. Therefore, there are many uncertainties in the sea areas lacking of environmental prior knowledge, including water depth, reef and other disturbing and obstructing factors.
-
(2)
The uncertainty of navigation situation information perception [80]. Due to the rich information, it simply includes the information obtained by the internal sensor, the information obtained by the external sensor and the information transmitted (shared) by the third party. Internal sensors refer to the platform monitoring of MASS, generally refer to the health status of command data link, the operability and health status of sensors identified as critical, the operability and health status of onboard system (such as propeller, autopilot, collision avoidance system, etc.), watertight information, residual fuel, hull integrity, pitch, roll, heave and ship vibration dynamic. External sensors refer to GNSS, bow direction, sea condition, wind speed and direction, water depth below keel, radar target, sound signal and visual signal (other ship's light type). Data transmitted by the third party includes AIS data, meteorological forecast data and tide calendar data. Due to the different characteristics of these sensors (principle of action, sensing mechanism, data transmission), some uncertainty of sensing information will be caused.
-
(3)
There is uncertainty in the accuracy of the prediction of obstacle motion and collision trajectory [81,82,83,84]. The perception of all the sensors of MASS brings the space state information, and the whole decision-making process or the navigation process has distinct space–time characteristics. These sensors cannot detect or report the behavior intention and motion state of the dynamic obstacles, such as the motion direction and speed.
In the uncertain environment, the navigation decision system and algorithm should have the ability of situation assessment based multi-source heterogeneous information, the ability to infer the motion state of dynamic obstacles and the ability to generate the optimal navigation strategy, to deal with the above problems and uncertainties.
In view of the problems faced by marine autonomous navigation system, combined with maritime traffic rules, the system should meet the following design requirements.
-
(1)
Autonomy planning ability. For the identified targets and obstacles, the planned route or navigation motion shall have certain safety when the optimal collision avoidance, collision avoidance time and resuming sea navigation are reasonably planned on the ECDIS.
-
(2)
Real-time. Between the voyage, navigation environment is unpredictable, and the marine autonomous navigation and decision system must make real-time changes in the state and motion according to the changes in the navigation environment.
-
(3)
Rationality. There are many ambiguous provisions or descriptions in the COLREGS, such as good seamanship, early avoidance, large, wide and clear description. Therefore, when designing the system, the actual navigation situation should be satisfied as much as possible, and the reasonable maneuvering mechanism for collision risks should be in line with the COLREGS.
-
(4)
Course stability and direction keeping. In the course of navigation, in addition to crossing, overtaking, obstacle avoidance and other actions, the MASS shall not deviate from the route greatly, and shall keep driving on the route. If the ship deviates from the route due to disturbance, the route can be resumed automatically when the disturbance disappears.
-
(5)
Speed control. In the normal navigation state, the autonomous ship should generally navigate within the maximum and minimum speed limits. In the process of intelligent decision-making, it is usually necessary to adjust the ship's speed longitudinally to avoid obstacles. In specific sea areas, it is necessary to control the ship's speed according to local rules, in case of emergency or accident, emergency braking can be realized.
-
(6)
Collision avoidance. The MASS shall have the ability of collision avoidance in the course of navigation, and the actions taken include transverse turning, longitudinal acceleration and deceleration, ship stalling, etc.
3.2 Design of Maritime Autonomous Navigation Systems
Maritime autonomous navigation system is a complex system [85], which integrates many advanced intelligent technologies.
In this paper, the whole system is divided into four sub-systems: global route optimization, navigation situation awareness, navigation behavioral decision, and motion control and execution subsystem. As shown in Fig. 13, the overall system architecture of the navigation system for maritime autonomous surface ships is presented, which describes the collaborative relationship among the four sub-systems.
3.2.1 Global Route Optimization
The global route optimization subsystem is to set the waypoint with the help of ECDIS and GPS system in the early stage of cargo transportation for MASS, so as to realize the calculation and design of relatively better and safe routes for known obstacles and port-to-port [86]. For the whole voyage of MASS, in terms of data description, global route optimization is equivalent to optimizing the navigation strategy for global path planning. If there are obstacles or the original route is blocked in the voyage after planning, the global route optimization system will conduct quadratic programming to re-plan a reasonable and optimal global route. The commonly used algorithms are dynamic programming, a *, Dijkstra and trajectory point guidance [87,88,89,90,91].
3.2.2 Navigation Situation Awareness
Navigation situation awareness system is to use a variety of onboard instruments and equipment to actively perceive the internal and external information of the ship or marine navigation environment, and receive the data transmitted by the third party [92, 93]. Perception system is the basis of navigation behavioral decision and motion control of MASS. The accurate perception information is also an important benchmark of MASS research and development. There are many kinds of sensors and shipborne instruments in the navigation situation awareness system of MASS, such as ECDIS, radar, lidar, HD camera, sonar, AIS, etc., which can obtain high-precision position service information, maritime safety sailing information, hydrometeorological information, ship dynamic information and port information in real time [94]. This multi-source information is fused and processed. Static and dynamic obstacles are mapped in the ECDIS and sent to the behavioral decision system.
3.2.3 Decision-Making
The navigation behavioral decision system is the core part of the whole MASS—navigation brain [74, 95, 96]. The system takes the results of the perception system as input, and collects all the information of the navigation situation, including not only the current position, speed and course of the autonomous ship, but also the information of obstacles. The decision system of maritime autonomous navigation system is to determine the route and navigation strategy of the MASS on the basis of knowing navigation safety information [97].
3.2.4 Control and Execution
After the decision instruction is given by the decision system of maritime autonomous navigation system, the control and execution system of MASS will execute the instruction, mainly including speed planning and trajectory planning, corresponding to the MASS, that is, the control of the marine telegraph and rudder [98, 99]. There is also a feedback control layer based on the integrated error of ship attitude variables in this subsystem. On the voyage of autonomous navigation for MASS, there are often some errors between the actual navigation and the plan due to the uncertainty of the ocean current, swell and other environment. Therefore, the control system will be feedback controlled again based on these errors. On the one hand, the decision instructions can be adjusted in real time for re-planning to better conform to the current navigation behavioral. On the other hand, the navigation behavioral and motion can be corrected. The ship's navigation behavioral can avoid uncertain risks.
4 Trade-off Between Autonomy and Navigation Action
Autonomy levels, degrees of autonomy and similar concepts of MASS or maritime autonomous navigation systems have been discussed extensively all over the world after the unmanned ship is named maritime autonomous surface ships by International Maritime Organization (IMO). A general shortcoming is that most existing classification schemes define a very concrete context for the classification that may not fit other applications, such as autonomous ships. Common assumptions are that there is always a person in the vehicle as for the autonomous vessel [85] or that the controlled system always operate without any person on board, but only through teleoperation as in IMO's classification [100].
Taxonomies for the levels of autonomy in different types of systems have been presented in the document by several countries and institutions.
One of the classification societies suggesting levels of autonomy is Bureau Veritas [101]:
-
Level 0 Human operated—Automated or manual operations are under human control. The human makes all decisions and controls all functions.
-
Level 1 Human directed—Decision support, human makes decisions and actions. The system suggests actions, human makes decisions and actions.
-
Level 2 Human delegated—Human must confirm decisions. The system invokes functions, human can reject decisions during a certain time.
-
Level 3 Human supervised—System is not expecting confirmation, human is always informed of the decisions and actions. The system invokes functions without waiting for human reaction.
-
Level 4 Fully autonomous—System is not expecting confirmation, human is informed only in case of emergency. The system invokes functions without informing the human.
Lloyd's Register has also made a suggestion. The proposal they presented at the meeting of 13 November 2017 was at the time a draft and slightly modified from their original suggestion presented earlier in 2017. Below, their current suggestion of accessibility levels are listed, as Lloyd's Register now calls them [101]:
-
Level 0 No cyber access—no assessment—no descriptive note – included for information only.
-
Level 1 Manual cyber access—no assessment—no descriptive note—included for information only.
-
Level 2 Cyber access for autonomous/remote monitoring.
-
Level 3 Cyber access for autonomous/remote monitoring and control (onboard permission is required, and onboard override is possible).
-
Level 4 Cyber access for autonomous/remote monitoring and control (onboard permission is not required, and onboard override is possible).
-
Level 5 Cyber access for autonomous/remote monitoring and control (onboard permission is not required, and onboard override is not possible).
The UK Marine Industries Alliance has also published a document with definitions, a Code of Practice. The document gives guidelines for ships of less than 24 m in length, although some of them are to be applicable to larger ships as well. The suggested concepts of autonomy are as follows [101]:
-
Level 0 Manned—ship/craft is controlled by operators aboard.
-
Level 1 Operated—Under Operated control all cognitive functionality is within the human operator. The operator has direct contact with the unmanned ship over, for example, continuous radio (R/C) and/or cable (e.g. tethered UUVs and ROVs). The operator makes all decisions, directs and controls all vehicle and mission functions.
-
Level 2 Directed—Under Directed control some degree of reasoning and ability to respond is implemented into the unmanned ship. It may sense the environment, report its state and suggest one or several actions. It may also suggest possible actions to the operator, such as, for example, prompting the operator for information or decisions. However, the authority to make decisions is with the operator. The unmanned ship will act only if commanded and/or permitted to do so.
-
Level 3 Delegated—The unmanned ship is now authorized to execute some functions. It may sense environment, report its state and define actions, and report its intention. The operator has the option to object to (VETO) intentions declared by the unmanned ship during a certain time, after which the unmanned ship will act. The initiative emanates from the unmanned ship and decision-making is shared between the operator and the unmanned ship.
-
Level 4 Monitored—The unmanned ship will sense environment and report its state. The unmanned ship defines actions, decides, acts and reports its action. The operator may monitor the events.
-
Level 5 Autonomous—The unmanned ship will sense environment, define possible actions, decide and act. The unmanned ship is afforded a maximum degree of independence and self-determination within the context of the system's capabilities and limitations. Autonomous functions are invoked by the onboard systems at occasions decided by the same, without notifying any external units or operators.
The suggestions are made from different assumptions and the premises of the suggestions differ somewhat. There are four to six levels in the suggestions, with five levels being the most used one. However, the contents of the suggested levels are not similar, even if the number of levels is the same. There are still some similarities in most of the suggestions. The lowest level is in general a level where the human is in charge, whereas the highest level is one where the ship operates unassisted on its own. Some suggestions have left out the lowest level, whether that is because it demonstrates no automation whatsoever, or to merely decrease the amount of levels is not clear.
The level of autonomy is strongly correlated with the collision avoidance decision and motion planning capabilities required by such system, as illustrated in Fig. 14. In general, high levels of autonomy means low human decision requirements, while low levels of autonomy and automation will require more human navigation decision. In the extreme case of local collision avoidance, the demands for real-timing, rule-complaint and fast decision-making are very high. The lower left corner in the figure indicates an unfeasible situation, while the upper right corner is an ideal situation which enables higher performance and enhanced functionality beyond the minimum requirements.
5 Trends in Maritime Autonomous Navigation Systems
In May 2006, at the 81st meeting of the Maritime Safety Committee (MSC) of the IMO (International Maritime Organization), the Seven Countries Proposal- “Development of e-Navigation Strategy” was adopted and adopted of The International Association of Marine Aids to Navigation and Lighthouse Authorities (IALA). E-navigation refers to the coordinated collection, integration, exchange, display and analysis of maritime information on board and onshore by electronic means to enhance the navigational capabilities of berths and other related services improve the level of safety and security at sea and protect the marine environment [102].
The e-navigation concept was put forward to meet the rapid development of autonomous navigation technology and navigation assistance methods. It aims to achieve the optimization of maritime transportation by integrating the existing navigation assistance technology and tools. The e-navigation technology framework mainly includes three elements, the ship environment, the shore-based support environment, and the communication system. Ship environment refers to supporting the collection, integration, exchange, display and analysis of all information provided by ship-based sensors. Shore-based support environment refers to shore-based technical services that support shore-based applications, such as search and rescue, VTS, ports, and MSI (Maritime Safety Information) services, etc. Communication systems refer to the communication equipment and communication links between ships-ships, shore-ships. To this end, the overall technical architecture of e-navigation can be simply described as the three sides of the coin, as shown in Fig. 15. The front and back sides of the coin represent the ship environment and the shore-based support environment, and the side of the coin represents the link ship Communication system with shore [103].
At present, with the development of shipping industry, ships have shown the characteristics of large-scale, specialized, high-speed and intelligent. E-navigation tries to integrate the existing navigation technology to maximize the safety of ship navigation and improve the efficiency of maritime cargo transportation. MASS combined with artificial intelligence technology greatly reduces the impact of human factors on maritime transportation safety and improves the level of ship navigation safety. The combination of e-navigation technology and maritime autonomous navigation technology can effectively promote the development of intelligent and information technology of maritime transportation and enhance the safety of navigation.
In order to effectively improve the safety level of maritime transportation and combine the autonomous navigation with e-navigation, the overall technical framework of the autonomous navigation system of MASS based on e-navigation is shown in Fig. 16, and autonomous navigation is developed based on the intelligent environment state information perception, intelligent navigation decision and intelligent communication of e-navigation [104]. The application of e-navigation technology lays a foundation for the development of autonomous navigation of MASS, and also promotes the implementation of e-navigation strategy.
E-navigation relies on four major issues of perception, data, standards and transmission, and moves from theory to practical application. The application of e-navigation technology lays a foundation for the development of autonomous navigation technology of MASS, and the development of MASS also promotes the implementation of e-navigation strategy [105,106,107,108]. It integrates e-navigation technology and autonomous ship technology. In the data center, it establishes a database of the information sensed by the MASS based on the standard of S-100, and transmits information to the ship and the shore-based platform through the maritime cloud, so as to realize the autonomous navigation of MASS without collision.
The four major issues that e-navigation technology system mainly solves are perception, data, standard and transmission. From the common research of e-navigation and autonomous navigation of MASS, e-navigation development lays a technical foundation for the construction of autonomous navigation system in the aspects of intelligent perception, intelligent navigation decision, intelligent communication and intelligent control.
6 Conclusion
The importance of maritime autonomous navigation systems is undeniable and the opportunity for coordinated and interconnected operations is clear.
MASS may finish intelligent navigation through shore remote control center with long distance to the operations, so that dependence on more autonomy infrastructures such as maritime autonomous navigation system or collision avoidance decision support systems, motion planning systems must be expected. The cost, reliability, performance and availability of such systems are important issues.
Moreover, there is a wide variety of scenarios with different collision avoidance decision requirements with respect to data-rates, latency and importance. These are for instance, Command and control data (telemetry), sensor data for situation awareness, payload sensor data, collision avoidance transponder broadcasts and status information. Therefore, autonomous navigation strongly depends on the system autonomy level and situation needs.
This work reviews the major advancements on maritime autonomous navigation technology applied in several different scenarios, from transportation to scientific research. Moreover, it highlights how available technologies and systems can be composed in order to efficiently and effectively handling in maritime obstacle environments.
Existing and prototype maritime autonomous surface ships, sensors, autonomous navigation for collision avoidance technologies are characterized, describing their requirements and capabilities. Additionally, the tradeoff between fully autonomous operations versus shore remotely operated vessels is highlighted, taking into account the availability and performance of different autonomy level. The discussed opportunities are aligned with current trends in autonomous navigation system and e-navigation technologies.
References
Notice of the State Council on Printing and Distributing the New Generation Artificial Intelligence Development Plan. http://www.gov.cn/zhengce/content/2017-07/20/content_5211996.htm
Artificial Intelligence Event: AlphaGo robot against Go master Li Shishi. http://www.techweb.com.cn/irouter/2016-03-07/2290885.shtml
MUNIN (Maritime unmanned navigation through intelligence in network) Homepage. http://www.unmanned-ship.org/munin/
NTNU Homepage. https://www.ntnu.edu/amos/research
Norwegian Forum for Autonomous Ships (NFAS) Homepage. http://nfas.autonomous-ship.org/index-en.html
International Network for Autonomous Ships (INAS) Homepage. http://www.autonomous-ship.org/events.html
Yara Birkeland Homepage. https://www.yara.com/news-and-media/press-kits/yara-birkeland-press-kit/
AAWA—The Advanced Autonomous Waterborne Applications Homepage. http://www.rolls-royce.com/media/press-releases/yr-2016/21-06-2016-rr-publishes-vision-of-the-future-of-remote-and-autonomous-shipping.aspx
UK Maritime and Coastguard Agency (2018) Maritime autonomous surface ships—UK code of practice. The Society of Maritime Industries on behalf of Maritime, UK
Richter M (2006) Operational manning considerations for Spartan scout and sea fox unmanned surface vehicles (USV). Naval postgraduate school Monterey CA graduate school of business and public policy
Lin X-l, Zhang B-s (2018) Technical development and operational application of unmanned surface combat system. J Unmanned Undersea Syst 26(2):107–114
Wan J-x (2014) Status and development trends of foreign military unmanned surface boats. Natl Def Sci Technol 35(5):91–96
Kumar A, Kurmi J (2018) A review on unmanned water surface vehicle. Int J Adv Res Comput Sci 9(2):95
Yunzhou Intelligent Technology Co., Ltd. Homepage. http://www.yunzhou-tech.com/Products/detail/id/26.html
SWT Spirit Whale Technology Homepage. http://www.smartwhale.cn/a/chanpinxilie/shuizhicaiyang/2015/1221/39.html
School of Naval Architecture of Harbin Engineering University Homepage. http://sec.hrbeu.edu.cn/2018/0925/c443a201600/page.htm
Ma Y, Sheng G (2018) A sea and air autonomous cooperative search and rescue M3U platform [P], Hubei, CN108563242A, 21 Sept 2018
Industrial Technology Research Institute of Guangdong Huazhong University of Science and Technology Homepage. http://www.gongyanyuan.net.cn/document/201708/article1690.htm
Shanghai University Unmanned Boat Engineering Research Institute Homepage. http://www.jhai.shu.edu.cn/Default.aspx?Tabid=35148
NetEase Dalian Homepage. http://3g.163.com/local/article/E0NL5P6B04228KBM.html
Wang N, Gao Y, Weng Y, Zheng Z, Zhao H (2018) Implementation of an integrated navigation, guidance and control system for an unmanned surface vehicle, pp 717–722
Wang N, Sun Z, Jiao Y, Han G (2019) Surge-heading guidance based finite-time path-following of underactuated marine vehicles. IEEE Trans Veh Technol 68(9):8523–8532
He C (2016) Requirements of the six functional modules of the CCS intelligent ship code. China Ship Surv 190(3):84–85
Sohu Homepage. http://www.sohu.com/a/153098782_119707
China News Homepage. http://news.sina.com.cn/o/2017-07-06/doc-ifyhvyie0380669.shtml
Smart shipping seminar held in Hangzhou. http://zj.people.com.cn/n2/2017/0718/c186327-30492174.html
The Institute successfully hosted the 2018 China Unmanned Ship Technology Innovation Forum. http://www.iim.cas.cn/xwzx/kjxw/201806/t20180605_409579.html
Liu C-g, Chu X-m et al (2016) Review and prospect of ship intelligence. Ship Eng 3:77–84
Xu H (2012) The research on target detection technology for marine rada in image processing. M.A. thesis, Wuhan University of Technology of China, Wuhan
Wang XS (2016) Research or USV radar image target detection system. M.A. thesis, Dalian Maritime University of China, Dalian
Liu R-q (2017) Application of depth learning algorithm in ship electronic chart recognition. Ship Sci Technol 39(2A):83–85
Li X-m, Zhang X et al (2017) 3D Lidar-based marine object detection for USV. J Shanghai Univ (Nat Sci Ed) 23(1):27–36
Lyu H, Yin Y (2019) COLREGS-constrained real-time path planning for autonomous ships using modified artificial potential fields. J Navig 72(3):588–608
Lyu H, Yin Y (2018) Fast path planning for autonomous ships in restricted waters. Appl Sci 8(12):2592
Hongguang L, Yong Y et al (2016) Artificial intelligence and soft computation methods in automatic collision avoidance algorithms for ships. J Navig China 39(3):35–40, 118
Shanshan Wu, Qingshuang L et al (2017) Design of unmanned ship for water environment monitoring based on internet of things. Digit Technol Appl 5:165–166
Haien X, Huihui X et al (2017) Design and implementation of unmanned ship cloud control system based on 4G IoT technology. J Softw Guid 5:56–58
Ruiliang G, Yuguan Ji (2016) Intelligent ship technology and unmanned navigation technology. J Ship 27(5):82–87
Peng L (2010) AIS-based intelligent collision avoidance expert system for inland vessels and its implementation. M.A. thesis, Wuhan University of Technology of China, Wuhan
Fan Y, Sun X, Wang G (2019) An autonomous dynamic collision avoidance control method for unmanned surface vehicle in unknown ocean environment. Int J Adv Robot Syst 16:1–11. https://doi.org/10.1177/1729881419831581
Geng X, Wang Y, Wang P, Zhang B (2019) Motion plan of maritime autonomous surface ships by dynamic programming for collision avoidance and speed optimization. Sensors 19:434. https://doi.org/10.3390/s19020434
Ahn JH, Rhee KP, You YJ (2012) A study on the collision avoidance of a ship using neural networks and fuzzy logic. Appl Ocean Res 37(4):162–173
Chen H (2016) Preliminary study on local path planning of surface unmanned boats. M.A. thesis, Dalian Maritime University of China, Dalian
Ramos MA, Utne IB, Mosleh A (2019) Collision avoidance on maritime autonomous surface ships: operators’ tasks and human failure events. Saf Sci 116:33–44. https://doi.org/10.1016/j.ssci.2019.02.038
Tai L, Li S, Liu M (2016) A deep-network solution towards model-less obstacle avoidance. In: Proceedings of IEEE/RSJ international conference on intelligent robots and systems, Daejeon, South Korea, 9–14 Oct 2016, pp 2759–2764
Long P, Liu W, Pan J (2017) Deep-learned collision avoidance policy for distributed multiagent navigation. IEEE Robot Autom Lett 2:656–663. https://doi.org/10.1109/LRA.2017.2651371
Panov AI, Yakovlev KS, Suvorov R (2018) Grid path planning with deep reinforcement learning: preliminary results. Procedia Comput Sci 123:347–353. https://doi.org/10.1016/j.procs.2018.01.054
Bojarski M, Del Testa D, Dworakowski D et al (2016) End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (1), pp 1–9
Cheng Y, Zhang W (2018) Concise deep reinforcement learning obstacle avoidance for underactuated unmanned marine vessels. Neurocomputing 272:63–73. https://doi.org/10.1016/j.neucom.2017.06.066
Zhang X, Wang C, Liu Y, Chen X (2019) Decision-making for the autonomous navigation of maritime autonomous surface ships based on scene division and deep reinforcement learning. Sensors 19(18):4055
Wang C, Zhang X, Cong L, Li J, Zhang J (2019) Research on intelligent collision avoidance decision-making of unmanned ship in unknown environments. Evol Syst 10(4):649–658
Wang C, Zhang X, Li R, Dong P (2018) Path planning of maritime autonomous surface ships in unknown environment with reinforcement learning. In: International conference on cognitive systems and signal processing, Springer, Singapore, pp 127–137
Cheng-bo WANG, Xin-yu ZHANG, Jia-wei ZHANG, Zhi-guo DING, Lan-xuan AN (2019) Navigation behavioural decision-making of MASS based on deep reinforcement learning and artificial potential field. J Phys Conf Ser 1357(1):012026 (IOP Publishing)
Wang CB, Zhang XY et al (2018) On path planning of unmanned ship based on Q-learning. J Ship Ocean Eng 47(5):174–177
Wang C, Zhang X et al (2018) Method for intelligent obstacle avoidance decision-making of unmanned vessel in unknown waters. Chin J Ship Res 13(06):74–79
Wang N, Meng X, Xu Q, Wang Z (2009) A unified analytical framework for ship domains. J Navig 62(4):643–655
Xu Q, Meng X, Wang N, Zhang C (2009) Adaptive danger area-based danger model immune algorithm. In: International conference on intelligent computing and intelligent systems, vol 3. IEEE, pp 109–112
Wang N (2010) An intelligent spatial collision risk based on the quaternion ship domain. J Navig 63(4):733–749
Wang N, Tan Y, Liu SM (2011) Ship domain identification using fast and accurate online self-organizing parsimonious fuzzy neural networks. In: Proceedings of the 30th Chinese control conference, IEEE, pp 5271–5276
Wang N, Er MJ (2014) Self-constructing adaptive robust fuzzy neural tracking control of surface vehicles with uncertainties and unknown disturbances. IEEE Trans Control Syst Technol 23(3):991–1002
Wang N, Qian C, Sun JC, Liu YC (2015) Adaptive robust finite-time trajectory tracking control of fully actuated marine surface vehicles. IEEE Trans Control Syst Technol 24(4):1454–1462
Wang N, Pan X (2019) Path-following of autonomous underactuated ships: a translation-rotation cascade control approach. IEEE/ASME Trans Mechatron. https://doi.org/10.1109/TMECH.2019.2932205
Wang N, Deng Z (2019) Finite-time fault estimator-based fault-tolerance control for a surface vehicle with input saturations. IEEE Trans Ind Inform. https://doi.org/10.1109/TII.2019.2930471
Wang N, Sun Z, Jiao Y, Han G (2019) Surge-heading guidance based finite-time path-following of underactuated marine vehicles. IEEE Trans Veh Technol. https://doi.org/10.1109/TVT.2019.2927893
Wang N, Karimi HR (2019) Successive waypoints tracking of an underactuated surface vehicle. IEEE Trans Ind Inform. https://doi.org/10.1109/TII.2019.2922823
Wang N, Karimi HR, Li H, Su S-F (2019) Accurate trajectory tracking of disturbed surface vehicles: a finite-time control approach. IEEE/ASME Trans Mechatron 24(3):1064–1074
Liu Y, Song R, Bucknall R et al (2019) Intelligent multi-task allocation and planning for multiple unmanned surface vehicles (USVs) using self-organising maps and fast marching method. Inf Sci 496:180–197
Zhou X, Wu P, Zhang H, Guo W, Liu Y (2019) Learn to navigate: cooperative path planning for unmanned surface vehicles using deep reinforcement learning. IEEE Access 7:165262–165278
Tan G, Zou J, Zhuang J, Wan L, Sun H, Sun Z (2020) Fast marching square method based intelligent navigation of the unmanned surface vehicle swarm in restricted waters. Appl Ocean Res 95:102018
Lee J, Kim H, Hwang DH, Oh SH, So H (2018) Multi-radio integrated navigation system M&S software design for GNSS back-up. In: 2018 IEEE/ION position, location and navigation symposium (PLANS), IEEE, pp 1026–1033
Lisowski J (2019) Sensitivity of safe trajectory in a game environment on inaccuracy of radar data in autonomous navigation. Sensors 19:1816
Liang S, Zhi-Ming Q, Heng L (2018) A survey on route planning methods of AUV considering influence of ocean current. In: 2018 IEEE 4th international conference on control science and systems engineering (ICCSSE), IEEE, pp 288–295
Wang N, Jin X, Er MJ (2019) A multilayer path planner for a USV under complex marine environments. Ocean Eng 184:1–10
Xinping Y, Chao W et al (2017) Conceptual design of navigation brain system for intelligent cargo ship. J Navig China 40(4):95–98, 136
Yoo B, Kim J (2018) Ship route optimization considering on-time arrival probability under environmental uncertainty. In: 2018 OCEANS-MTS/IEEE Kobe Techno-Oceans (OTO), IEEE, pp 1–5
Jahnke A, Arp HPH, Escher BI, Gewert B, Gorokhova E, Kühnel D et al (2017) Reducing uncertainty and confronting ignorance about the possible impacts of weathering plastic in the marine environment. Environ Sci Technol Lett 4(3):85–90
Roy N, Burgard W, Fox D, Thrun S (1999) Coastal navigation-mobile robot navigation with uncertainty in dynamic environments. In: Proceedings 1999 IEEE international conference on robotics and automation (Cat. No. 99CH36288C), vol 1. IEEE, pp 35–40
Sormunen OVE, Goerlandt F, Häkkinen J, Posti A, Hänninen M, Montewka J et al (2015) Uncertainty in maritime risk analysis: extended case study on chemical tanker collisions. Proc Inst Mech Eng Part M J Eng Marit Environ 229(3):303–320
Katsanevakis S, Moustakas A (2018) Uncertainty in marine invasion science. Front Mar Sci 5:38
Park J, Choi J, Choi HT (2019) COLREGS-compliant path planning considering time-varying trajectory uncertainty of autonomous surface vehicle. Electron Lett 55(4):222–224
Park JS, Park C, Manocha D (2017) Intention-aware motion planning using learning based human motion prediction. In: Robotics: science and systems
Johansen TA, Perez T, Cristofaro A (2016) Ship collision avoidance and COLREGS compliance using simulation-based control behavior selection with predictive hazard assessment. IEEE Trans Intell Transp Syst 17(12):3407–3422
Patterson A, Lakshmanan A, Hovakimyan N (2019) Intent-aware probabilistic trajectory estimation for collision prediction with uncertainty quantification. arXiv preprint, arXiv:1904.02765(2019)
Soloperto R, Köhler J, Allgöwer F, Müller MA (2019) Collision avoidance for uncertain nonlinear systems with moving obstacles using robust model predictive control. In: 2019 18th European control conference (ECC), IEEE, pp 811–817
Liu S, Li, Jie T et al (2017) Creating autonomous vehicle systems. Synth Lect Comput Sci 6(1):1–186
Krata P, Szlapczynska J (2018) Ship weather routing optimization with dynamic constraints based on reliable synchronous roll prediction. Ocean Eng 150:124–137
Zaccone R, Martelli M (2018) A random sampling-based algorithm for ship path planning with obstacles. In: Proceedings of the international ship control systems symposium-iSCSS, Glasgow, pp 170–178
Lee SM, Roh MI, Kim KS, Jung H, Park JJ (2018) Method for a simultaneous determination of the path and the speed for ship route planning problems. Ocean Eng 157:301–312
Zaccone R, Figari M (2017) Energy efficient ship voyage planning by 3D dynamic programming. J Ocean Technol 12(4):49–71
Biyela P, Rawatlal R (2019) Development of an optimal state transition graph for trajectory optimisation of dynamic systems by application of Dijkstra’s algorithm. Comput Chem Eng 125:569–586
Liu C, Mao Q, Chu X, Xie S (2019) An improved A-star algorithm considering water current, traffic separation and berthing for vessel path planning. Appl Sci 9(6):1057
Sharma A, Nazir S (2017) Distributed situation awareness in pilotage operations: implications and challenges
Hyvönen M, Rajala M, Virtanen A, Jankkari J, Huhtala K, Ritala R (2015) Assistive situation awareness system for mobile multimachine work environments. IEEE Trans Intell Transp Syst 16(6):3403–3413
Raptodimos Y, Lazakis I, Theotokatos G, Varelas T, Drikos L (2016) Ship sensors data collection and analysis for condition monitoring of ship structures and machinery systems. In: Smart Ship Technology
Xinping Y, Feng M, Jialun L et al (2019) Applying the navigation brain system to inland ferries. In: 18th conference on computer and IT applications in the maritime industries, Tullamore, pp 156–162
Kienle M, Franz B, Winner H et al (2014) Concept and development of a unified ontology for generating test and use-case catalogues for assisted and automated vehicle guidance. IET Intell Transp Syst 8(3):183–189
Xue J, Chen Z, Papadimitriou E, Wu C, Van Gelder PHAJM (2019) Influence of environmental factors on human-like decision-making for intelligent ship. Ocean Eng 186:106060
Hanson BB, Hanson TE (2017) U.S. Patent No. 9,669,904. Washington, DC: U.S. Patent and Trademark Office, (2017).
Huang R (2018) Maritime intelligent real-time control system based on UAV. In: 2018 international conference on robots & intelligent system (ICRIS), IEEE, pp 10–12
Kutsuna K, Ando H, Nakashima T, Kuwahara S, Nakamura S (2019) NYK’s approach for autonomous navigation—structure of action planning system and demonstration experiments. J Phys Conf Ser 1357(1):012013 (IOP Publishing, Norway)
MSC 99/5/6: considerations on definitions for levels and concepts of autonomy-submitted by Finland, 12 March 2018
IMO's 81st Maritime Safety Committee Document (MSC 81/23/10): Japan, Marshall Islands, Netherlands, Norway, Singapore, United Kingdom and United States propose “Development of Electronic Navigation Strategy”
Wang CB et al (2017) e-Navigation and its data standard analysis. J World Shipp 40(1):22–24
Zongjiang G, Yingjun Z et al (2017) Research summary of unmanned ship. J Dalian Marit Univ 43(2):1–7
Im I, Shin D, Jeong J (2018) Components for smart autonomous ship architecture based on intelligent information technology. Procedia Comput Sci 134:91–98
Porathe T, Rødseth ØJ (2019) Simplifying interactions between autonomous and conventional ships with e-navigation. J Phys Conf Ser 1357(1):012041 (IOP Publishing)
Ahn J, Joung TH, Kang SG, Lee J (2019) Changes in container shipping industry: autonomous ship, environmental regulation, and reshoring. J Int Marit Saf Environ Aff Shipp 3(3–4):21–27
Jeong SH, Shim JH, Choi KS, Son YC (2018) Analysis and design of common platform core technology for maritime autonomous surface ships. J Adv Navig Technol 22(6):507–513
Acknowledgements
The authors thank the Editor-in-Chief, Technical Editor, and anonymous referees for their invaluable comments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, C., Wang, N., Xie, G., Su, SF. (2022). Survey on Collision-Avoidance Navigation of Maritime Autonomous Surface Ships. In: Su, SF., Wang, N. (eds) Offshore Robotics. Offshore Robotics. Springer, Singapore. https://doi.org/10.1007/978-981-16-2078-2_1
Download citation
DOI: https://doi.org/10.1007/978-981-16-2078-2_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2077-5
Online ISBN: 978-981-16-2078-2
eBook Packages: EngineeringEngineering (R0)