No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Dynamic Adaptive Decision-Making Method for Autonomous Navigation of Ships in Coastal Waters
Abstract
The field of ship autonomous navigation has always garnered significant interest due to its future development potential for intelligent ships and unmanned ships. While there has been extensive research on autonomous navigation in open waters, less focus has been given to coastal waters due to the complexity of the environment and traffic flow. In order to resolve this problem, the dynamic adaptive decision-making method for ship autonomous navigation in coastal waters is presented. A digital twin environment model tailored to the characteristics of coastal waters has been developed, which can dynamically replicate the current ship navigation environment by incorporating multi-source heterogeneous information from ship equipment. The autonomous navigation decision-making method is obtained by integrating an Improved Velocity Obstacle (IVO) for ship collision avoidance and a Line of Sight (LOS) algorithm for ship trajectory tracking. Moreover, a time-rolling algorithm is employed to facilitate specific navigation decision-making in time-varying environments and to account for the uncertainty of target ship motion over time. This comprehensive algorithm has been tested and validated in two different scenarios. The results demonstrate that the proposed navigation decision-making method is reasonable and effective for the ship navigating in the coastal water, particularly in multi-ship encounter situations of target ships suddenly altering course or changing speed.
... For a balance between the need for timely decision-making and the reliability of predictions, a 15-minute prediction time is decided based on the environmental conditions, traffic density, and so on (Gao and Zhang 2024). The prediction ensures that our model is both practical and relevant to the operational realities of maritime navigation, providing robust support for the effective avoidance of collisions and navigational hazards (Zhao et al. 2024). ...
Given the immense potential value of the ocean, the exploration of underwater environments has never ceased. However, due to the limitations imposed on most sensors by the underwater environment, achieving underwater Simultaneous Localization and Mapping (SLAM) remains a challenging goal. Traditional visual SLAM approaches struggle underwater due to specific challenges such as light attenuation and water flow disturbances. In this paper, we propose a robust monocular visual SLAM system based on deep learning optical flow estimation, specifically designed for underwater scenarios. First, we developed a data augmentation strategy specifically designed for underwater conditions. Second, we propose a novel feature extraction network that incorporates Squeeze and Excitation layers within the encoder module. Additionally, we introduced an Attention ConvGRU module based on a global attention mechanism. This improved module can more efficiently iteratively update the optical flow estimates between adjacent frames. Our proposed method was evaluated on both benchmark and underwater datasets. Compared to traditional methods, our approach demonstrates superior robustness and accuracy. Additionally, compared to SLAM based on deep learning, our method significantly reduces training costs and exhibits better performance across most underwater dataset sequences. The code is available at: https://github.com/GodSkyWang/EUM-SLAM.
Ship autonomous collision avoidance has attracted increasing attention in recent years. However, more attention is paid to the scenario in which the target ship keeps its course and speed. Less attention is paid to the development of a collision avoidance decision-making system under the uncertainty of the target ship's movement in a complex multi-ship encounter situation. Based on the idea of model predictive control (MPC), this paper proposes an autonomous ship collision avoidance decision-making system (CADMS) suitable for the uncertainty of ship motion. The CADMS includes four modules: collision risk analysis module, control and execution module, ship trajectory prediction module and collision avoidance decision-making model. The proposed model can be implemented in the collision avoidance decision-making system for safe navigation or it can be included in the ship autonomous navigation process. The decision-making model is achieved from a risk identification-motion prediction-ship control-scheme implementation perspective, and the dynamic and uncertainty features of the ship action (i.e., alter course or change speed) are considered in the modelling process. The real-time rolling update of ship collision avoidance decisions is realised based on the time series rolling method. Four scenarios are designed to demonstrate the collision avoidance decision-making system's performance. The results show that the proposed collision avoidance decision-making system is a reasonable and effective system for collision avoidance, particularly in multi-ship encounter situations of target ships suddenly altering course or change speed.
Collision prevention is critical for navigational safety at sea, which has developed rapidly in the past decade and attracted a lot of attention. In this article, an improved velocity obstacle (IVO) algorithm for intelligent collision avoidance of ocean-going ships is proposed in various operating conditions, taking into count both a ship’s manoeuvrability and Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). An integrated model combines a three-degree-of-freedom manoeuvring model with ship propeller characteristics to provide a precise prediction of ships in various manoeuvring circumstances. In the given case, what is different to present studies, this improved algorithm allows for decision-making in two ways: altering course and changing speed. The proposed technique is demonstrated in a variety of scenarios through simulation. The findings reveal that collision-avoidance decision-making can intelligently avoid collisions with the target ships (TSs) in multi-ship situations.
To ensure navigation safety, unmanned surface vehicles (USVs) need to have autonomous collision avoidance capability. A large number of studies on ship collision avoidance are available, and most of these papers assume that the target ships keep straight or follows the International Regulations for Preventing Collisions at Sea (COLREGS). However, in the actual navigation process, the target ship may temporarily turn. Based on the above reasons, this paper proposes a multi-ship collision avoidance decision method for USVs based on the improved velocity obstacle algorithm. In the basic dynamic ship domain model, a collision risk model is constructed to improve the accuracy of the risk assessment between the USV and target ships. The velocity obstacle algorithm is combined with the dynamic ship domain, and the collision avoidance timing and method are judged according to the collision risk. The simulation results show that the decision method can handle the situation that the target ship temporarily turns and has an emergency collision avoidance capability. Compared with the traditional VO algorithm, the collision avoidance time of the method is shorter, and the number of course changes is less.
In the last few years, autonomous ships have attracted increasing attention in the maritime industry. Autonomous ships with an autonomous collision avoidance capability are the development trend for future ships. In this study, a ship manoeuvring process deduction-based dynamic adaptive autonomous collision avoidance decision support method for autonomous ships is presented. Firstly, the dynamic motion parameters of the own ship relative to the target ship are calculated by using the dynamic mathematical model. Then the fuzzy set theory is adopted to construct collision risk models, which combine the spatial collision risk index (SCRI) and time collision risk index (TCRI) in different encountered situations. After that, the ship movement model and fuzzy adaptive PID method are used to derive the ships’ manoeuvre motion process. On this basis, the feasible avoidance range and the optimal steering angle for ship collision avoidance are calculated by deducting the manoeuvring process and the modified velocity obstacle (VO) method. Moreover, to address the issue of resuming sailing after the ship collision avoidance is completed, the Line of Sight (LOS) guidance system is adopted to resume normal navigation for the own ship in this study. Finally, the dynamic adaptive autonomous collision avoidance model is developed by combining the ship movement model, the fuzzy adaptive PID control model, the modified VO method and the resume-sailing model. The results of the simulation show that the proposed methodology can effectively avoid collisions between the own ship and the moving TSs for situations involving two or multiple ships, and the own ship can resume its original route after collision avoidance is completed. Additionally, it is also proved that this method can be applied to complex situations with various encountered ships, and it exhibits excellent adaptability and effectiveness when encountering multiple objects and complex situations.
In this research, a hybrid approach for path planning of autonomous ships that generates both global and local paths, respectively, is proposed. The global path is obtained via an improved artificial potential field (APF) method, which makes up for the shortcoming that the typical APF method easily falls into a local minimum. A modified velocity obstacle (VO) method that incorporates the closest point of approach (CPA) model and the International Regulations for Preventing Collisions at Sea (COLREGS), based on the typical VO method, can be used to get the local path. The contribution of this research is two-fold: (1) improvement of the typical APF and VO methods, making up for previous shortcomings, and integrated COLREGS rules and good seamanship, making the paths obtained more in line with navigation practice; (2) the research included global and local path planning, considering both the safety and maneuverability of the ship in the process of avoiding collision, and studied the whole process of avoiding collision in a relatively entirely way. A case study was then conducted to test the proposed approach in different situations. The results indicate that the proposed approach can find both global and local paths to avoid the target ship.
Trajectory planning is one of the important technologies to ensure the safe navigation of the unmanned ship. This paper presents a dynamic path planning method based on the multi-layer Morphin adaptive search tree algorithm, which considers ship maneuverability, COLREGS, and good seamanship to harmonize the actions in the mixed traffic environment. First, the environment model is built according to the environment information of the rolling window; second, the feasible avoidance range of collision avoidance is calculated according to the velocity obstacle (VO) method. Finally, path optimization is carried out using the Morphin adaptive search tree algorithm. Through a case study and comparison with traditional artificial potential field (APF) models, the applicability and potential of the method are verified. This model can be applied to the autonomous navigation for unmanned ships as well as conventional manned ships and demonstrate good potential in smart shipping.
Recent studies have made significant development in path planning for ships. However some studies blindly obey rules of COLREGS (International Regulations for Preventing Collisions at Sea) or only adopt turning to starboard ignoring actual practice, like, turning to port and considering deviation from the planned route when taking actions for collision avoidance. In view of the COLREGS and ordinary seamen practice, this paper proposes collision avoidance actions before encounter situation and collision avoidance actions in an encounter situation. Based on the different stages of the encounter situation, it will add more choices for ships when taking action. To specify different stages of encounter situation clearly and take proper collision avoidance actions, this paper makes a quantitative analysis of three primary encounter situations; velocity obstacles (VO) is employed to find allowed velocity space for own ship (OS); by making further analysis of the relationship among distance at the closest point of approach, bow cross, and COLREGS, the method gives a clear direction for OS to search the best velocity in allowed velocity space for three primary encounter situations; VO utility function is applied to search specific value of the best velocity and is useful for different encounter situations. Simulations show that the results are effective and deterministic for collision avoidance. This method not only prevents blindly obeying rules of COLREGS but also promotes reducing deviation from the planned route.
Maritime Autonomous Surface Ships (MASS) attract increasing attention in recent years. Researchers aim at developing fully autonomous systems that replace the role of human operators. Studies either focus on supporting conflict/collision detection (for manned ships) or solving conflict automatically (for unmanned ships). The cooperation between human and machine has been less focused on in existing studies. However, this type of cooperation is essential both in practice and in the future: firstly, demands on navigational assistance are still strong for supporting navigators in manned ships; secondly, MASS with different autonomy levels require increasing cooperation between human operators and machines, e.g. monitoring automation, remotely controlling the ship, etc.; thirdly, the intelligence of human and the machines is highly complementary. Moreover, fully autonomous ships cannot replace all the manual ships overnight. Therefore, the future waterborne transport system will be a system in which both human-operated vessels and autonomous vessels exist.
In this article, we firstly provide an overview of existing modes of human-machine interaction (HMI) during ship collision avoidance. Then, we propose a framework of HMI oriented Collision Avoidance System (HMI-CAS) whose decision-making process is interpretable and interactive for human operators. The HMI-CAS facilitates automatic collision avoidance and enables the human operators to take over the control of the MASS safely. Moreover, the proposed framework acknowledges the under-actuated feature of ships. Simulations are carried out to demonstrate the proposed HMI-CAS. The results show that the proposed HMI-CAS can not only control the under-actuated MASS to avoid collision automatically but also share the decision-making with human operators and support the operators to control the MASS.
In this research, a hybrid approach for global path planning for Maritime Autonomous Surface Ship (MASS) is proposed, which generates the shortest path considering the collision risk and the proximity between path and obstacles. The collision risk concerning obstacles is obtained using Time-Varying Collision Risk (TCR) concept, taking into account the velocity constraint of the ship that can achieve during operation. The influence of proximity from obstacles is measured with the Fast Marching (FM) algorithm. A new cost function is proposed allowing to combine the influence of obstacle proximity and collision risk in the region. Finally, the Fast Marching Square algorithm is applied to generate the globally optimal path that can reach the pre-set destination. The contribution of this work is two-fold: 1) considering the velocity constraint of the own ship, together with its influences of collision risk into the global path planning stage of autonomous navigation. 2) measuring the collision risk induced by the obstacles from their comprehensive influences on the achievable velocity range using TCR concept, instead of numerical integration of risk measurement. The results of the case study indicate that the proposed approach can find an optimal path considering the collision risk and proximity from the obstacles.
The unmanned surface vehicle (USV) has been widely used to accomplish missions in the sea or dangerous marine areas for ships with sailors, which greatly expands protective capability and detection range. When USVs perform various missions in sophisticated marine environment, autonomous navigation and obstacle avoidance will be necessary and essential. However, there are few effective navigation methods with real-time path planning and obstacle avoidance in dynamic environment. With tailored design of state and action spaces and a dueling deep Q-network, a deep reinforcement learning method ANOA (Autonomous Navigation and Obstacle Avoidance) is proposed for the autonomous navigation and obstacle avoidance of USVs. Experimental results demonstrate that ANOA outperforms deep Q-network (DQN) and Deep Sarsa in the efficiency of exploration and the speed of convergence not only in static environment but also in dynamic environment. Furthermore, the ANOA is integrated with the real control model of a USV moving in surge, sway and yaw and it achieves a higher success rate than Recast navigation method in dynamic environment.
Collision prevention is critical for navigation safety at sea. At early ages, researchers aimed at developing navigational assistance systems for enhancing situational awareness of human operators as human is at the core of collision avoidance. Recently, autonomous vehicles have gained a remarkable amount of attention with a focus on solving collision problems by machines. This results in two groups of studies, both working on preventing collisions but with different focuses: one aims at conflict detection, and the other focuses on conflict resolution. This paper offers a comprehensive overview of collision prevention techniques based on the three basic processes of determining evasive solutions, namely, motion prediction, conflict detection, and conflict resolution. The strengths and weaknesses of different methods for these three fundamental processes are discussed. Limitations and new challenges are highlighted. Moreover, this review points out the differences between the research for manned and unmanned ships and how the research in the two domains can learn from each other. A potential roadmap for the transition from existing manned ships to fully unmanned ships is provided in the end.
Various reports have been given on the study of wind forces and moments acting on ships by using wind tunnel experiments over a long time. Utilizing these results, Yamano et al. and Isherwood proposed estimation methods of wind force coefficients by linear multiple regression model in the 1970's. After that, many kinds of ships have been built all over the world, for example VLCC, PCC, LNG, and so on. The estimation methods lack reliability when wind forces and moment of such kinds of ships are predicted, since these new types of ships aren't considered in the methods.Recently Yoneta et al. proposed a estimation method consisting of several force components, which is called a physical-mathematical model. However, the applicability of this method isn't enough discussed.In the present paper, we wish to report on a new and simpler method of estimating wind force and moment coefficients acing on ships by using stepwise method which comes under linear multiple regression analysis. This estimation method was obtained after considering various ships more than previous estimation methods and the effect of wind velocity profile that some reports have already pointed out its importance in the experimental condition. As there is no way to estimate heel moment caused by strong wind, a estimation method of it is also presented in order to make use of strict simulation of maneuverability for the first time.This method has been found to possess high practical value compared with previous estimation methods.
Ship collision avoidance has always been a concern and it is crucial for achieving safe navigation of ships at sea. There are many studies on ship collision avoidance in open water, but less attention on coastal waters considering the uncertainty of target ships due to the complexity of the environment and traffic flow. In this paper, collision avoidance decision-making research in coastal waters considering the uncertainty of target ships was proposed. Firstly, accurate ship trajectories are obtained by preprocessing the raw Automatic Identification System (AIS) data. Subsequently, the processed trajectories are clustered using the Ordering Points to Identify the Clustering Structure (OPTICS) algorithm and Hausdorff distance, acquiring a dataset for trajectory prediction of target ships. Then, a mixed Gaussian model is utilized to calculate the prior probability distribution of the prediction model, thus establishing a trajectory prediction model that considers the uncertainty of the target ship. Finally, ship maneuverability is simulated using the Mathematical Model Group (MMG) and Proportion Integration Differentiation (PID) models, and a collision avoidance decision-making model for ships is constructed. The proposed algorithm has been tested and verified in a case study. The results show that the approach effectively predicts the trajectory of the target ship and facilitates informed collision avoidance decision-making.
This paper proposes a multi-objective cooperative control method for a ship-towing system in congested water traffic environments. The control objectives are to coordinate multiple autonomous tugboats for transporting a ship to: (i) follow the waypoints, (ii) adjust the heading, (iii) track the speed profile, and (iv) resolve collisions. The problem is tackled by the design of multiple control agents distributed in two control layers. Based on the strategy of model predictive control (MPC), the supervisory controller in the higher layer calculates the towing angles and forces of the ship, the tug controller in the lower layer computes the tug thruster forces and moment. The consensus between the lower and higher layer control is achieved by using the altering direction method of multipliers (ADMM) that makes the predicted tug position and heading approach to the desired tug trajectory. Simulation experiments indicate that the proposed method coordinates multiple autonomous tugboats to transport a ship smoothly and effectively and succeeds in multiple control objectives, in the meantime, the avoidance operation complies with COLREGS rules.
This paper investigates the collision avoidance problem for autonomous underwater vehicle (AUV) with limited detection range via deep reinforcement learning method in an unknown underwater environment. Firstly, to deal with both unknown static and dynamic obstacles, we introduce two different event-triggered mechanism to generate obstacle-related states and reward the safe collision avoidance action of AUV, respectively. Secondly, the complete state space is customized by combining the state of AUV itself and the state related to a target area. In addition, considering the task requirement of reaching a target area with the shortest path, the complete reward function is designed. Then, we propose a novel event-triggered soft actor–critic (ET-SAC) algorithm for AUV collision avoidance, and give its detailed pseudo code and implementation architecture. Finally, training and evaluation are carried out in the simulation platform we designed, including unknown static obstacle environment and unknown dynamic obstacle environment in 2D/3D space, and the results confirm that the proposed algorithm of this paper is feasible and effective for AUV to avoid collision safely.
Collision between ships is one of the major contributors to ship accidents. To facilitate the development of the real-time collision risk analysis model for collision avoidance, in this research, an improved Rule-aware Time-varying Collision risk Model is proposed, which considers the estimation of target ship motion and the corresponding uncertainty in the risk analysis process. To make the collision risk model more in line with the actual situation, ship maneuverability, the COLREGs, and good seamanship are considered and integrated into the framework of the TCR model. Firstly, the Gaussian process is used to predict the potential trajectories of the target ship. Secondly, the Probabilistic Velocity Obstacle (PVO) model is utilized to integrate the uncertainty of the target ship's motion into the collision risk model. The collision risk is therefore formulated as a ratio of available maneuvers leading to a collision to all available maneuvers. To verify the effectiveness of collision risk, two actual target ships and six groups of collision risk detection experiments under different encounter scenarios were carried out. Compared with the traditional collision risk index model and original R-TCR model, the collision risk detected by the Improved R-TCR model is closer to the actual situation.
In this paper, the methods are proposed for underactuated autonomous underwater vehicle (AUV) to address three-dimensional (3D) path tracking and real-time obstacle avoidance. The errors of path tracking are generated based on the Serret–Frenet frame and line-of-sight (LOS) guidance law, while the errors in obstacle avoidance are obtained based on the carrier coordinate system to filter irrelevant environment information. On this basis, to deal with the complicated target path and unknown obstacles, the controller is designed by deep deterministic policy gradient (DDPG) algorithm and adaptive multi-constraints. The safety constraints are adopted in reward functions to avoid useless explorations and facilitate convergence. The training proceeds for path tracking and obstacle avoidance respectively. Compared to the original DDPG algorithm in the training, the proposed algorithm shows faster convergence. Various simulations are conducted under different initial conditions, and the results demonstrate the effectiveness of the proposed algorithm.
In this article, a new approach for ship-ship collision probability estimation based on the Cross-Entropy (CE) method is introduced, which can be treated as an adaptive importance sampler. It has the advantage of attaining low variance estimates of small collision probabilities, which will most often be the case in realistic scenarios. Furthermore, a risk-based Collision Avoidance (COLAV) system being able to take obstacle kinematic uncertainty and intention uncertainty into account is presented, namely the Probabilistic Scenario-Based Model Predictive Control (PSB-MPC). The collision probability estimator (CPE) is used in the risk assessment of the PSB-MPC, and tested in a simulation study, where the total system is validated. Simulation results show that the MPC is able to utilize the CPE for better risk assessment than the original version, in order to make safer decisions in close quarter situations and cases where nearby obstacles make unexpected maneuvers. It is also shown that when all vessels involved use the PSB-MPC, situations are resolved according to the traffic rules in a safe manner.
Ship autonomous navigation constitutes the most critical step in intelligent ships and is the major prerequisite for the all task completion of the marine autonomous surface ship (MASS). Reinforcement learning (RL) has been widely used in unmanned transport vehicles because of its excellent performance in solving continuous handling problems. This study proposes a MASS autonomous navigation system using dueling deep Q networks prioritized replay (Dueling-DQNPR) based on the ship automatic identification system (AIS) big data. A navigation environment with three difficulty levels were established to train the Dueling-DQNPR network in sequence by setting a reward mechanism. Moreover, the Dueling-DQNPR was improved by combining the prioritized experience replay, dueling structure and long–short-term memory unit to increase the network depth and ability to process continuous data. Finally, simulation training for the AIS trajectory data was carried out in waters near Zhoushan port. The results demonstrated that, through trial and error, the MASS could be controlled to arrive at its destination without collision. As a result, the proposed method may be applicable to MASS on-duty technology and intelligent ships.
Since sailing along the Northern Sea Route (NSR) through the Arctic Ocean comes into reality, commercial shipping developments including opening new liner services along this route have been put on the agenda. However, uncertainties within weather and ocean conditions in this region, especially during temperature-varying seasons, may cause failure to on-time arrivals, resulting unignorable or even unaffordable monetary losses. As a result, these uncertainties will inevitably affect cargo shippers’ willingness of choosing this being-explored route, even if on average its shipping time is much shorter than that of the traditional Asia-Europe shipping lines. In this context, the present paper describes a liner ship routing and scheduling problem considering schedule-sensitive demand and late-arrival penalty for operating incoming NSR shipping lines in the future. By using two types of uncertainty sets, bounded and budget-bounded uncertainty sets, we construct and solve two robust counterparts of this problem. The deterministic model and bounded robust model can be seen as special cases of the budget-bounded robust model when the uncertainty budget is set to null and full, respectively. A multifaceted case study of planning liner shipping routes and schedules along the NSR is conducted to validate the efficacy and efficiency of the proposed models and identify the effects of uncertainty bounds and budgets on the solution performance. The following facts and conclusions are revealed from the optimization results of the case study: The budget-bounded robust model functions the best in the worst condition; low revenue rate and high demand sensitivity are the major factors for excluding a candidate port from the route; the order of a visited port in the route decides the weight of its uncertainty budget on the entire shipping line; setting the uncertainty budget in a decelerative way will enhance the scheduling robustness of solutions.
In order to realize the autonomous collision avoidance of unmanned surface vehicles (USVs), an intelligent hybrid collision avoidance algorithm based on deep reinforcement learning is proposed. First, the navigation situation model of the USV is designed, the geometric model of the encounter between two ships is established based on navigation practice. According to static and dynamic obstacles, hybrid risk assessment and collision avoidance model are proposed, the risk factor is calculated. Then, for static obstacles, the collision cone is introduced, for dynamic ships, the COLREGS is observed, the encounter situation is quantified into five types. Collision avoidance strategy is formulated. Finally, the state, action, reward function and network structure are designed. Aiming at the problem of low utilization for samples in random sampling, this paper improves the original sampling mechanism of DDPG, and the priority sampling mechanism with cumulative pruning is proposed in this paper. Simulation experiments are carried out in several typical encounter scenarios. The results show that this algorithm can accurately judge the encounter situation, give reasonable collision avoidance actions, and realize effective collision avoidance in a complex environment with dynamic and static obstacles. The research can provide theoretical basis and method reference for autonomous navigation of USVs.
Abstrtact
This paper aims to investigate the U-turn made by ships far away from their destination docks (called off-destination-dock U-turns) in the narrow waterway using automatic identification system (AIS) data. Such U-turns are time-consuming and would occupy a long section of channel, causing the travel delay for other vessels. The Houston Ship Channel (HSC) was used as the case study. The purpose of the study was two-folded. First, for each cargo or tanker having trips in the channel, we aimed to build a methodological framework and corresponding solution algorithms to capture significant directional changes of a ship's trajectory so that the calculation could be based on much fewer points for U-turn analysis. Second, the proposed algorithms were applied to the HSC to identify the sections frequently used by those off-destination-dock U-turns. In a narrow busy waterway, cargos and tankers, may be forced to wait or make the U-turn at predetermined sections of channel due to their larger length and/or width. Identifying such sections (i.e., “hotspots”) can be useful for future channel developments and daily traffic management. The proposed methods and algorithms are generalized, so that they can be also applied to other narrow waterways in the same or similar situations.
Maritime Autonomous Surface Ships (MASS) have obtained much attention in recent years. Navigation with human–machine cooperation is the core for L1–L3 MASS. In this article, the development and trend of MASS are collected, and main research institutions are analysed based on MASS experimental projects and publications. The navigation modes of MASS are given, and main topics involved in human–machine cooperative navigation are presented. We focus on the research progress in the four aspects, i.e., modelling of ship navigating behaviour, enhanced navigation situation awareness, human–machine cooperation decision-making and human–machine cooperation navigation control, and then we compare the different methods and technologies for different issues of human–machine cooperative navigation. On the basis of current development, the deficiencies and unsolved problems of MASS human–machine cooperative navigation are analysed. The key theories and technologies of identification and risk assessment of navigating behaviour, situation awareness enhancement, human–machine cooperative decision-making, human–machine cooperative navigation, experimental platform and a case study of human–machine cooperative navigation are investigated, and relevant feasible approaches are provided. We believe the human–machine cooperative navigation will be an important breakthrough of MASS development, and inland and offshore waters will be the suitable navigation area for testing the performance of ship human–machine cooperative navigation.
Improving the autopilot capability of ships is particularly important to ensure the safety of maritime navigation.The unmanned surface vessel (USV) with autopilot capability is a development trend of the ship of the future. The objective of this paper is to investigate the path planning problem of USVs in uncertain environments, and a path planning strategy unified with a collision avoidance function based on deep reinforcement learning (DRL) is proposed. A Deep Q-learning network (DQN) is used to continuously interact with the visually simulated environment to obtain experience data, so that the agent learns the best action strategies in the visual simulated environment. To solve the collision avoidance problems that may occur during USV navigation, the location of the obstacle ship is divided into four collision avoidance zones according to the International Regulations for Preventing Collisions at Sea (COLREGS). To obtain an improved DRL algorithm, the artificial potential field (APF) algorithm is utilized to improve the action space and reward function of the DQN algorithm. A simulation experiments is utilized to test the effects of our method in various situations. It is also shown that the enhanced DRL can effectively realize autonomous collision avoidance path planning.
Collison between ships is one of the major contributors to maritime accidents. To reduce ship collision accidents, the research on collision avoidance decision-making has been drawing much attention from various parties. In this research, extensive literature and expert knowledge are collected and analyzed to identify the common sense and discrepancies between collision avoidance decision-making for theoretical research and navigation practices. The key factors that are considered in the two perspectives are identified and discussed, based on which, the knowledge structures that can represent the development of the process in the two perspectives are established. A series of comparisons between the knowledge structure based on theoretical research and navigation practices are conducted. The comparisons indicate clear common sense and discrepancies between the theoretical research and navigation practices regarding collision avoidance decision-making. The potential causes of them are also analyzed. The research results would be beneficial for the development of collision avoidance decision-making for both autonomous and conventional manned ships in maritime traffic.
COLREGs-based collision risk awareness model is urgently needed in real-time operating conditions. However, this is a complicated problem under various encounter situations, some of which are very complex. In order to quantify the collision risk in real operating conditions, a novel risk-informed collision risk awareness approach is proposed for real-time operating conditions. Firstly, the ship's actions are identified based on the Automatic Identification System (AIS) data. Secondly, the uncertainty of ship action patterns is analyzed by regarding the target ships as velocity obstacles. Then, the collision risk model is utilized to assess the collision risk level based on the uncertainty in the non-linear velocity obstacles algorithm considering responsibility. Finally, some case studies are carried out based on the proposed model. In the model, the dynamic and uncertainty features of the ship action dynamics in real operating conditions are considered, which could benefit on reducing ship collision accidents and improving the development of technologies on intelligent collision avoidance decision makings.
Ship collisions are major types of maritime accidents which may involve the loss of life and significant damage to property and the environment. Although many automatic ship collision avoidance algorithms have been suggested, most of them are only applicable to a single ship-to-ship encounter situation. Also, although there exist some studies on collision avoidance for multiple agent systems, maritime traffic rules have not been systematically incorporated in the algorithms which limit their practical applicability to real maritime traffic situations. In this study, we propose a rule-compliant automatic ship collision avoidance method that can be applied not only to single ship-to ship situations, but also to multiple-ship encounter situations with consideration of prediction uncertainty. In order to select appropriate evasive actions, a symmetric role-classification criterion is proposed by refining the current maritime traffic rules, and an efficient collision avoidance algorithm based on the probabilistic velocity obstacle method is applied. To verify and demonstrate the performance and practical utility of the proposed algorithm, Monte-Carlo simulations were conducted and the results are presented in this article.
This paper proposed a new collision avoidance decision-making system designed for autonomous ship. The system outputs collision avoidance decisions based on the latest information at a certain frequency, which is suitable for real ship application. Front end and back end are two main components of this system. Front end provides preliminary information while back end generates collision avoidance decisions. Based on modified velocity obstacle method, the multistage optimization decision model is introduced and various constrains are considered including ship maneuverability, multi-ship, COLREGS, off-course and seamanship. Then the interactive actions taken by other ships during collision avoidance process are further analyzed. The modified velocity obstacle method incorporates a Finite State Machine (FSM) which can be used to handle the dynamic behavior of other ships. Finally, the case study is completed on the Electronic Chart System (ECS) to show that the proposed collision avoidance decision-making system is robust and effective under various marine scenarios. Therefore, the system has great potential to be equipped on board in the future.
This paper proposes an AIS-data-based model to accurately estimate vessels' travel time and its distribution between any two points in a narrow channel. It is crucial to know the travel time (plus its distribution) between some critical points for traffic control. The model has two components: (1) to identify a vessel's destination dock, and its arrival and departure times (the key is how to separate a vessel's trips); and (2) to estimate a vessel's travel time from its destination dock (or a specific point) to another specific point, or vice versa. Travel time between two points is called traversal time. The proposed algorithms were then applied to the Houston Ship Channel (HSC) with the AIS data of 11 months in 2017, focusing on the outbound trips in the section above the Beltway-8 Bridge. Through the travel times of cargos and tankers from their destination docks to a point are likely to be normally distributed, their traversal times between two points are more likely to be lognormally distributed. The traversal time distribution is significantly impacted by vessel width, draft and type, but independent from time-of-day and month. The adjacent link traversal times are also highly positively correlated.
Avoidance of collisions at sea is crucial to navigational safety. In this paper, we use a distributed algorithm to communicate the entire collision avoidance trajectory information for each ship. In each communication, we suggest a new improvement function considering safety and efficiency to identify the avoidance ship in each cycle. Considering the nonlinear collision avoidance trajectory of ships, a new method for calculating the degree of danger using a velocity obstacle algorithm is proposed. Therefore, in each communication, each ship considers the avoidance behaviours of other ships in planning its avoidance trajectory. Additionally, we combine bi-criterion evolution (BCE) and the ant lion optimiser to plan the entire collision avoidance path. Three scenarios are designed to demonstrate the performance of this method. The results show that the proposed method can find a suitable collision-free solution for all ships.
This paper proposes a fuzzy logic-based intelligent decision-making approach for navigation strategy selection in the inland traffic separation scheme. The dynamic characteristics of navigation process, including free navigation, ship following and ship overtaking, are further analysed. The proposed model can be implemented in the decision support system for safe navigation or be included in the process of autonomous navigation. The decision-making model is achieved from the perception-anticipation-inference-strategy perspective, and the dynamic features of ships (i.e. speed, distance, and traffic flow) are comprehensively considered in the modelling process. From the results of both scenarios for overtaking and following, it illustrates that the timing is significant for strategy selection and should well consider the complex situation and ship behaviours, moreover, the proposed approach can be used for intelligent strategy selection.
Maritime collision risk prediction is crucial for the safety management of ocean transportation. Previous studies have primarily focused on near-miss collision risk of ship pairs, yet the risk due to congestion caused by multiple ships is significant. This paper proposes a novel space-time geographical approach for addressing multi-ship near-miss collision risk based on vessel motion behavior. The direction-constrained space-time prism is used to characterize the interaction possibility of ships, enabling potential collision risk to be evaluated. The advantage of direction-constrained space-time prism in analyzing ship movements is that it accounts for direction limitation thereby eliminating unreasonable estimation associated with the assumption of arbitrary changes in sailing direction through the classical space-time prism. This paper uses the trajectories of ships traveling the southeast coast of China to investigate the viability of the proposed approach. In comparison to the fuzzy quaternion ship domain model and closest point of approach-based methods, the proposed approach is capable of identifying hierarchical near-miss collision risks for different ships to improve risk evaluation. This is essential for ship path optimization that accounts for changes in the speed and course of ships. This work supports maritime collision risk forecasting, but also provides detailed insights for actionable steps to reduce risks.
Maritime transportation system has made a significant contribution to the development of the world economy. However, with the growth of quantity, scale, and speed of ships, maritime accidents still pose incrementing risk to individuals and societies in terms of multiple aspects, especially collision accidents between ships. Great effort is needed to prevent the occurrence of such accidents and to improve navigational safety and traffic efficiency. In this paper, extensive literature on probabilistic risk analysis on ship-ship collision was collected and reviewed focusing on the stakeholders which may benefit from the research and the methodologies and criteria adopted for collision risk. The paper identifies stakeholders, the modelling aspects (frequency estimation, causation analysis, etc.) in which the stakeholders are interested in. A classification system is presented based on the technical characteristics of the methods, followed by detailed descriptions of representative approaches and discussion. Areas for improvement of such risk analysis approaches are highlighted, i.e. identifying collision candidates, assessing the collision probability of multiple ships encounters, assessing the human and organizational factors. Three findings are concluded from this literature review: (1) Research on collision risk analysis and evaluation of ship encounters from individual ship perspective have facilitated the research in macroscopic perspective, and in turn, results from macroscopic research can also facilitate individual risk analysis by providing regional risk characteristics; (2) Current approaches usually estimate geometric probability by analysing data at certain intervals, which could lead to over/underestimation of the results; and (3) For causation probability induced by human and organisational factors in collision accidents, lack of data and uncertainty is still a problem to obtain accurate and reliable estimations. The paper also includes a discussion with respect to the applicability of the methods and outlines further work for improvement. The results in this paper are presented in a systematic structure and are formulated in a conclusive manner. This work can potentially contribute to developing better risk models and therefore better maritime transportation systems.
This paper presents a real-time and deterministic path planning method for autonomous ships or Unmanned Surface Vehicles (USV) in complex and dynamic navigation environments. A modified Artificial Potential Field (APF), which contains a new modified repulsion potential field function and the corresponding virtual forces, is developed to address the issue of Collision Avoidance (CA) with dynamic targets and static obstacles, including emergency situations. Appropriate functional and safety requirements are added in the corresponding virtual forces to ensure International Regulations for Preventing Collisions at Sea (COLREGS)-constrained behaviour for the own ship's CA actions. Simulations show that the method is fast, effective and deterministic for path planning in complex situations with multiple moving target ships and stationary obstacles and can account for the unpredictable strategies of other ships. The authors believe that automatic navigation systems operated without human interaction could benefit from the development of path planning algorithms.
Maritime accidents have been imposing various risks to individuals and societies in terms of human and property loss, and environmental consequences. For probabilistic risk analysis and management, collision candidate detection is the first step. Therefore, it is of great importance to further improve methods to detect possible collision scenarios. This paper proposes a Time Discrete Non-linear Velocity Obstacle (TD-NLVO) method for collision candidate detection, which is based on the Non-linear Velocity Obstacle algorithm and tested on historical AIS data (Automatic Identification System). Collision candidates are detected based on the perspective which considers a ship encounter as a process, rather than analysing traffic data at certain time slices. Case studies on single encounters of ship traffic in waterways environments are conducted and presented in this paper. The results indicate that the TD-NLVO method can effectively detect collision candidates which satisfy pre-set criteria. A comparison between seven other popular AIS data-based collision candidate methods is performed, and the results indicate that the proposed method outperforms the other methods regarding its robustness towards the choice of parameter settings.
In this article, a ship maneuverability based collision avoidance dynamic support system in close-quarters situation is presented. The dynamic calculation model of collision avoidance parameter is employed to calculate the dynamic DCPA and TCPA in real-time when ship is maneuvering. Then the collision avoidance dynamic support system is developed by combining the mathematical model of ship maneuvering motion, the control mechanism of ship maneuvering motion and the dynamic calculation model of collision avoidance parameter. Following this approach, the proposed system is able to eliminate the insufficiency of neglect of ship maneuverability in the process of avoiding collision. Moreover, by incorporating the close-quarters situation into the proposed collision avoidance dynamic support system, simulation examples consisting three encounter scenarios of two ships in close-quarters situation are applied to demonstrate the significance and necessity of ship maneuverability in the process of collision avoidance and illustrate the merits and effectiveness of the proposed system. The simulation results show that the proposed dynamic support system is a reasonable, effective and practicable system for collision avoidance, particularly in close-quarters situation.
Ship collision avoidance is highly dependent upon seamanship and rules. When ship collision risk exists, proper collision avoidance actions must be taken according to the correct encounter situation and determined stage. All autonomous collision avoidance (ACA) operations in the future must comply with given rules and seamanship practices, which make the quantitative analysis of them prerequisites for ACA. This study presents a novel quantitative analysis system for the International Regulations for Preventing Collisions at Sea (COLREG) Rules and Seamanship. The proposed system consists of three parts: an encounter situation discrimination model based on the mutually relative bearing of the “target ship” (TS) and “own ship” (OS); a stage discrimination model representing the extent of collision risk per different domain models for every potential situation and a model to determine collision avoidance action per COLREG, seamanship, and ship maneuverability information was established accordingly. The collision avoidance plans appropriate for different situations and stages are generated based on the rules, seamanship, and rudder steering direction judgments. A simulation scenario was utilized to validate the effectiveness and feasibility of the system.
This paper studied the waterway transportation in Sabine–Neches Waterway (SNWW) using the automatic identification system (AIS) data. The SNWW is the most important waterway in Southeast Texas, which serves as an energy gateway to the U.S. The purpose of this paper is two-folded: one is to investigate the waterway transportation features in the SNWW from a macro level (using aggregate AIS data); and more importantly, this paper aims to investigate the frequency of vessel conflicts, which reflects the risk of vessel collisions in the SNWW. To realize these two purposes, AIS data were firstly cleaned to fit our research requirements, and a practical AIS-based method was proposed to evaluate the frequency of various types of vessel conflicts in the SNWW. This paper identified a series of hot spots in the SNWW that experienced high frequencies of vessel conflicts between big vessels, as well as those carrying hazardous materials. The paper also investigated the impact of time-of-day on the frequency of vessel conflicts at each hot spot. The findings of this paper can help researchers and waterway management agencies better understand the risk of navigation in the SNWW.
He, Y.; Huang, L.; Xiong, Y., and Hu,W., 2015. The research of ship ACA actions at different stages on head-on situation based on CRI and COLREGS. In order to study the Automatic Collision-Avoidance (ACA) actions of vessels in head-on situation in accordance with rules of International Regulation for Preventing Collision at Sea (COLREGS 72) and ordinary practice of seaman, stags of vessel's meeting process were separated by Collision Risk Index (CRI) and Time to Immediate Danger (TID). The reason to correct Collision-Avoidance (CA) actions at different stages are different. CRI and TID were derived from defined Situation Elements (SE) in head -on situation. Then computing models of them and ACA actions at different stages were presented. The basis of this research is the center moved ship's elliptical domain theories and MMG three-free dimensional digital model which is calculated by ship's hydrodynamic equations. The following is proved by simulations: The mathematic models presented ensure rapid and reliable convergence of SE computing; new CRI model is much more in line with the thinking process of navigators and practice at sea than before; ACA actions in accordance with COLREGS rules and ordinary practice of seaman, can be produced by program. The research may make big improvement to the final achievement of ACA of ship in head-on situation.
This paper presents an autonomous motion planning algorithm for unmanned surface vehicles (USVs) to navigate safely in dynamic, cluttered environments. The algorithm not only addresses hazard avoidance (HA) for stationary and moving hazards, but also applies the International Regulations for Preventing Collisions at Sea (known as COLREGS, for COLlision REGulationS). The COLREGS rules specify, for example, which vessel is responsible for giving way to the other and to which side of the “stand-on” vessel to maneuver. Three primary COLREGS rules are considered in this paper: crossing, overtaking, and head-on situations. For autonomous USVs to be safely deployed in environments with other traffic boats, it is imperative that the USV's navigation algorithm obeys COLREGS. Furthermore, when other boats disregard their responsibility under COLREGS, the USV must fall back to its HA algorithms to prevent a collision. The proposed approach is based on velocity obstacles (VO) method, which generates a cone-shaped obstacle in the velocity space. Because VOs also specify on which side of the obstacle the vehicle will pass during the avoidance maneuver, COLREGS are encoded in the velocity space in a natural way. Results from several experiments involving up to four vessels are presented, in what we believe is the first on-water demonstration of autonomous COLREGS maneuvers without explicit intervehicle communication. We also show an application of this motion planner to a target trailing task, where a strategic planner commands USV waypoints based on high-level objectives, and the local motion planner ensures hazard avoidance and compliance with COLREGS during a traverse.
This paper considers a numerical analysis of ship maneuvering performance in the presence of incident waves and resultant ship motion responses. To this end, a time-domain ship motion program is developed to solve the wave–body interaction problem with the ship slip speed and rotation, and it is coupled with a modular-type 4-DOF maneuvering problem. In this coupled problem, the second-order mean drift force, which can play an important role in the ship maneuvering trajectory, is estimated by using a direct pressure integration method. The developed method is validated by observing the second-order mean drift force, and planar trajectories in maneuvering tests with and without the presence of incident waves. The comparisons are made for two ship models, Series 60 with block coefficient 0.7 and the S-175 containership, with existing experimental data. The maneuvering tests observed in this study include a zig-zag test in calm water, and turning tests in calm water and in regular waves. The present results show a fair agreement of overall tendency in maneuvering trajectories.
The Singapore Strait is considered as the bottleneck and chokepoint of the shipping routes connecting the Indian and the Pacific Ocean. Therefore, the ship collision risk assessment is of significant importance for ships passing through the narrow, shallow, and busy waterway. In this paper, three ship collision risk indices are initially proposed to quantitatively assess the ship collision risks in the Strait: index of speed dispersion, degree of acceleration and deceleration, and number of fuzzy ship domain overlaps. These three risk indices for the Singapore Strait are estimated by using the real-time ship locations and sailing speeds provide by Lloyd's MIU automatic identification system (AIS). Based on estimation of these three risk indices, it can be concluded that Legs 4W, 5W, 11E, and 12E are the most risky legs in the Strait. Therefore, the ship collision risk reduction solutions should be prioritized being implemented in these four legs. This study also finds that around 25% of the vessels sail with a speed in excess of the speed limit, which results in higher potentials of ship collision. Analysis indicates that the safety level would be significantly improved if all the vessels follow the passage guidelines.