Ship Collision Avoidance Research Articles

A Path Planning Method for Ship Collision Avoidance Considering Spatial–Temporal Interaction Effects

Efficient and reliable path planning is crucial for smart ships when avoiding collisions with static and dynamic obstacles in complex marine environments. This research proposes a novel path planning method based on the fast marching method to specifically assist with safe navigation for autonomous ships. At the very beginning, a unified representation is specially produced to describe the path planning space based on the parametric fast marching speed function. In addition, the spatial–temporal interaction effects of dynamic obstacles are considered and integrated into the construction of planning space. Subsequently, a path optimization strategy is put forward based on the trajectory prediction of dynamic objects. Particularly, the effectiveness of the method has been validated and evaluated through a number of simulations, which proves that such a method is practical in narrow and crowded waterways.

Decision-making method for multi-ship collision avoidance based on improved extensive game model

In the case of multi-ship encounter situations, most collision accidents are caused by not having timely and coordinated collision avoidance behaviors. Therefore, it is necessary to introduce an automatic collision avoidance method in the process of collision avoidance to quickly generate multi-ship collision avoidance decisions based on encounter situations. Multi-ship collision avoidance is a dynamic game used among officers under situations of multi-ship encounters. Considering the defects of the classic extensive game method in ship collision avoidance decision-making, the improved extensive game method is proposed, based on the velocity obstacle method. The feasible region of velocity is taken as the optional action range of the game to narrow down the action set. The simulation results show that the proposed method can effectively transform the multi-ship collision avoidance game problem into a 2-ship collision avoidance game problem, reduce the optional action range of a collision avoidance action set, and improve decision-making speed, while ensuring the safety of multi-ship navigation.

A novel ship collision risk evaluation algorithm based on the maximum interval of two ship domains and the violation degree of two ship domains

In the research of ship collision avoidance, the evaluation of ship collision risk is an important part to determine whether there is a potential collision risk. In the field of ship collision avoidance, using an appropriate method to calculate the ship collision risk has always been a hot topic. To address the issues that only qualitative evaluation using the ship domain and the distance to the closest point of approach (DCPA) does not reflect the true distance between the two ships when the closest point of approach (CPA) parameters are used, a novel ship collision risk evaluation model is proposed. (1) A fuzzy quaternion ship domain (FQSD) model is established for the own ship (OS) and the target ship (TS) at the same time. (2) The two parameters the maximum interval of two ship domains (MISD) and the violation degree of two ship domains (VDSD) are introduced, which are solved based on Support Vector Machine for Classification (SVC) and geometric methods, respectively, and the ship collision probability model is established based on these two parameters. (3) Based on the momentum conservation theorem, considering the mass ratio of two ships, ship type, collision velocity and the location of the collision damage, the consequences of ship collision are calculated. (4) Based on the ship collision probability and ship collision consequences, a ship collision risk evaluation model is proposed. The simulation verification is performed under the three encounter situations of head-on, crossing, and overtaking, based on Maneuvering Model Group using the basic ship parameters of Dalian Maritime University's teaching-training ships “YUKUN” and “YUUPENG” to establish the model proposed in this paper. Simultaneously, it is compared to the ship collision risk evaluation method based on ship domain, CPA parameters, and spatial collision risk model. The simulation results demonstrate the superiority and efficacy of the ship collision risk evaluation algorithm proposed in this paper, which is an effective method for assessing ship collision risk.

Intelligent Ship Collision Avoidance Algorithm Based on DDQN with Prioritized Experience Replay under COLREGs

Ship collisions often result in huge losses of life, cargo and ships, as well as serious pollution of the water environment. Meanwhile, it is estimated that between 75% and 86% of maritime accidents are related to human factors. Thus, it is necessary to enhance the intelligence of ships to partially or fully replace the traditional piloting mode and eventually achieve autonomous collision avoidance to reduce the influence of human factors. In this paper, we propose a multi-ship automatic collision avoidance method based on a double deep Q network (DDQN) with prioritized experience replay. Firstly, we vectorize the predicted hazardous areas as the observation states of the agent so that similar ship encounter scenarios can be clustered and the input dimension of the neural network can be fixed. The reward function is designed based on the International Regulations for Preventing Collision at Sea (COLREGs) and human experience. Different from the architecture of previous collision avoidance methods based on deep reinforcement learning (DRL), in this paper, the interaction between the agent and the environment occurs only in the collision avoidance decision-making phase, which greatly reduces the number of state transitions in the Markov decision process (MDP). The prioritized experience replay method is also used to make the model converge more quickly. Finally, 19 single-vessel collision avoidance scenarios were constructed based on the encounter situations classified by the COLREGs, which were arranged and combined as the training set for the agent. The effectiveness of the proposed method in close-quarters situation was verified using the Imazu problem. The simulation results show that the method can achieve multi-ship collision avoidance in crowded waters, and the decisions generated by this method conform to the COLREGs and are close to the level of human ship handling.

Automatic traffic scenarios generation for autonomous ships collision avoidance system testing

The Collision Avoidance (CA) system constitutes a key enabling technology for the Maritime Autonomous Surface Ships (MASS), the appropriate functionality of which is critical for assuring the navigation safety. Although several techniques including testing of the collision scenarios in a virtual environment can be employed, the trust of testing phase results depends on the number of tested scenarios and their coverage. This study aims at proposing a systematic and automatic process for the generation of the traffic scenarios that can be employed for the CA system testing. First, the range of the investigated parameters is defined, and samples of potential traffic parameters are generated using Sobol sequences. Subsequently, hazardous traffic scenarios are identified from the initially generated scenarios by using predefined rules. For these hazardous scenarios, a risk vector considering weather conditions and traffic conditions is calculated. A clustering algorithm is employed to identify the groups of traffic conditions that can be encountered based on each scenario risk vector and COLREGs traffic scenarios. For each of these groups, the riskiest scenario is provided as input for the test cases development, thus, simplifying the selection process of testing scenarios. The process is applied to a theoretical Short Sea Shipping autonomous vessel, whereas the derived results are employed to discuss the advantages and disadvantages of the developed process.

A New Method of Inland Water Ship Trajectory Prediction Based on Long Short-Term Memory Network Optimized by Genetic Algorithm

Ship position prediction plays a key role in the early warning and safety of inland waters and maritime navigation. Ship pilots must have in-depth knowledge of the future position of their ship and target ship in a specific time period when maneuvering the ship to effectively avoid collisions. However, prediction accuracy and computing efficiency are crucial issues that need to be worked out at present. To solve these problems, in this paper, the deep long short-term memory network framework (LSTM) and genetic algorithm (GA) are introduced to predict the ship trajectory of inland water. Firstly, the collected actual automatic identification system (AIS) data are preprocessed and a series of typical trajectories are extracted from them; then, the LSTM network is used to predict the typical trajectories in real time. Considering that the hyperparameters of the LSTM network have difficulty obtaining the optimal solution manually, the GA is used to optimize hyperparameters of LSTM; finally, the GA-LSTM trajectory prediction model is constructed with the optimal network parameters and compared with the traditional support vector machine (SVM) model and LSTM model. The experimental results show that the GA-LSTM model effectively improves the accuracy and speed of trajectory prediction, with outstanding performance and good generalization, which possess certain reference values for the development of collision avoidance of unmanned ships.

DCA-Based Collision Avoidance Path Planning for Marine Vehicles in Presence of the Multi-Ship Encounter Situation

The problem of ship collision avoidance path planning is one of the key problems in the ship motion control field. Aiming at the high computational time problem of path planning in multi-ship encounter situations and the impact of the target ship’s action changes on path planning, this paper proposes a dynamic path-planning method based on dynamic cluster analysis (DCA), which is used to dynamically cluster target ships with similar attributes into a group ship, reducing the number of calculated targets and improving the efficiency of path planning. Taking into full consideration the action requirements of the International Regulations for Preventing Collisions at Sea (COLREGs), the course alteration action matrix (CAAM) for collision avoidance is established to limit the space of candidate solutions. On the basis of the rapid optimization capability of the deterministic optimization algorithm (DOA), a dynamic monitoring mechanism is introduced to establish a multi-ship encounter intelligent collision avoidance decision-making model that meets the needs of real-time collision avoidance. The simulation results showed that the method can obtain a dynamic collision avoidance path that is safe and feasible.

Ship collision avoidance behaviour recognition and analysis based on AIS data

A novel approach is proposed to automatically identify the ship collision avoidance behaviour from ship trajectories based on an improved Sliding Window Algorithm. The approach has three main stages: (1) determining the ships’ obligations according to the Convention on the International Regulations for Preventing Collision at Sea (COLREGs); (2) assessing the rudder angle according to the true bearing of the target ship; (3) identifying the corresponding ship handling behaviour from the ship trajectory taking into account the Rate of Turn and its derivative based on the Sliding Window Algorithm. Four typical encounter scenarios are studied to demonstrate the feasibility and effectiveness of the proposed method. The approach is then applied to near collision scenarios identified in the maritime traffic off the continental coast of Portugal, which allowed the characterization of the relative and spatial distributions of the locations at which the ships take evasive manoeuvres. The results show that the approach can be applied to accurately detect the ship collision avoidance behaviour from Automatic Identification System trajectory data, and the characterization of the collision avoidance behaviour can potentially be used by situational awareness systems and as the basis for ship collision avoidance decision-making.

Ship Collision Avoidance and Anti Grounding Using Parallelized Cost Evaluation in Probabilistic Scenario-Based Model Predictive Control

The ability to effectively process large amounts of information in reasonable time will be important for robust deliberative collision avoidance (COLAV) planning algorithms. Failure to do so can lead to collision, and can be compared to lack of proper supervision from officers on watch (OOW). The main contribution in this article is a parallelized implementation of the Probabilistic Scenario-Based Model Predictive Control (PSB-MPC) on a Graphical Processing Unit (GPU) platform which incorporates both dynamic obstacle avoidance and anti-grounding. Simulation results demonstrate that the COLAV planner can produce collision-free trajectories with respect to grounding hazards and nearby vessels at relatively low computational cost, and which also comply to the COLREGS when deemed possible. Corresponding run-time results show that the algorithm utilizing parallel processing performs better than the alternative for increasing numbers of own-ship control behaviours, nearby static and dynamic obstacles, and dynamic obstacle prediction scenarios considered.

Collaborative Collision Avoidance for Autonomous Ships Using Informed Scenario-Based Model Predictive Control

There exist several collision avoidance algorithms for autonomous ships. But the majority of them do not utilize information about other ships’ intentions, except for observed position and velocity. As the attention for large-sized autonomous ships to be used in logistics is growing, autonomous ships will need to collaborate and negotiate with other ships to prevent reactive and agile collision avoidance maneuvers. As a first step towards a collaborative collision avoidance algorithm, we implemented a reactive short-range algorithm by utilizing other ships’ trajectory plans. We aimed to improve the existing Scenario-Based Model Predictive Control (SB-MPC) algorithm by including route exchange-based trajectory predictions and called it the Informed SB-MPC. Additionally, we introduce adaptive and conditional parameter selection methods for the SB-MPC design. Hereby we implemented the compliance with the COLREGs Rule 18 concerning responsibility between vessels in addition to the existing Rules 13-17. The performance of the new method is demonstrated with head-on, crossing, overtaking, and multiple ships scenarios.

Research on Ship Collision Avoidance Decision Based on Improved Ant Colony Algorithm

Research on Ship Collision Avoidance Decision Based on Improved Ant Colony Algorithm

Scenario-Based Model Predictive Control with Several Steps for COLREGS Compliant Ship Collision Avoidance

The main question investigated is whether additional decision steps can improve vessel behavior produced by the collision avoidance method scenario based model predictive control (SBMPC). The method, which functions by predicting alternative paths resulting from a finite number of alternative control behaviors, then selecting which behavior to apply by use of a cost function, was originally formulated to allow switching between several behaviors on the prediction horizon. However, current implementations have been limited to a single control step. To compare the single-step and multi-step SBMPC, a simulation study was performed, where different configurations for the number, positioning and possible control actions were tested. In the course of the simulation study it became clear that identifying situations producing a significant difference between the two methods was difficult to identify and the multi-step SBMPC led to only minor improvements in very few scenarios. Nevertheless, multi-step decisions can be visualized to give better situational awareness, and also have additional benefits with other trajectory parameterizations and less uncertain predictions of other ship trajectories.

A Survey of Recent Machine Learning Solutions for Ship Collision Avoidance and Mission Planning

Machine Learning (ML) techniques have gained significant traction as a means of improving the autonomy of marine vehicles over the last few years. This article surveys the recent ML approaches utilised for ship collision avoidance (COLAV) and mission planning. Following an overview of the ever-expanding ML exploitation for maritime vehicles, key topics in the mission planning of ships are outlined. Notable papers with direct and indirect applications to the COLAV subject are technically reviewed and compared. Critiques, challenges, and future directions are also identified. The outcome clearly demonstrates the thriving research in this field, even though commercial marine ships incorporating machine intelligence able to perform autonomously under all operating conditions are still a long way off.

Optimal control of ship collision avoidance problem

The continuous increasing of maritime traffic amplified the severity of the collision risk issue in the maritime domain. Therefore, the calculus and optimization of ship’s navigation without collision risks have been known as a major challenge for the scientific researches’ community. Several solutions were proposed to enhance the maritime safety. The topic was covered as an optimal control problem with state constraints using Nonlinear Model Predictive Control in order to consider the nonlinearity of the ship motion. Other researches relied on calculating risks of collisions in ocean navigation by metaheuristic methods or by neural networks in order to cover multi-ship collision risk situation. In this paper, a detailed description of necessary elements used in the analysis of the maritime navigation without collision issue is presented including the ship motion, the International Regulations for Preventing Collisions at Sea COLREGs rules, and the navigation cost. An analytical study of optimal control based on Pontryagin’s Maximum Principle to avoid ship collision situation with more efficiency is proved and detailed. Simulation results that show the efficiency of the described method are calculated using MATLAB.

Intent Inference-Based Ship Collision Avoidance in Encounters With Rule-Violating Vessels

All vessels operating in a marine environment are required to comply with the international regulations for preventing collisions at sea (COLREGs), which provide the guidelines and evasive procedures required to resolve potential conflicts between vessels. However, not all vessels strictly abide by COLREGs, often leading to dangerous situations. This paper presents a novel approach for robust collision avoidance in encounter situations involving COLREG-violating vessels. A probabilistic velocity obstacle algorithm based on intent inference is designed and implemented with consideration of the tradeoff between the adherence to traffic rules and the proactive evasive actions for safety. One-to-one and multi-ship encounter situations in the presence of rule-violating vessels are examined through Monte-Carlo simulations, and the results are discussed to demonstrate the feasibility and performance of the proposed approach.

Local Route Planning for Collision Avoidance of Maritime Autonomous Surface Ships in Compliance with COLREGs Rules

A maritime autonomous surface ship (MASS) ensures safety and effectiveness during navigation using its ability to prevent collisions with a nearby target ship (TS). This avoids the loss of human life and property. Therefore, collision avoidance of MASSs has been actively researched recently. However, previous studies did not consider all factors crucial to collision avoidance in compliance with the International Regulations for Preventing Collisions at Sea (COLREGs) Rules 5, 7, 8, and 13–17. In this study, a local route-planning algorithm that takes collision-avoidance actions in compliance with COLREGs Rules using a fuzzy inference system based on near-collision (FIS-NC), ship domain (SD), and velocity obstacle (VO) is proposed. FIS-NC is used to infer the collision risk index (CRI) and determine the time point for collision avoidance. Following this, I extended the VO using the SD to secure the minimum safe distance between the MASS and the TS when they pass each other. Unlike previous methods, the proposed algorithm can be used to perform safe and efficient navigation in terms of near-collision accidents, inferred CRI, and deviation from the course angle route by taking collision-avoidance actions in compliance with COLREGs Rules 5, 7, 8, and 13–17.

Navigation Situation Clustering Model of Human-Operated Ships for Maritime Autonomous Surface Ship Collision Avoidance Tests

The collision avoidance system is one of the core systems of MASS (Maritime Autonomous Surface Ships). The collision avoidance system was validated using scenario-based experiments. However, the scenarios for the validation were designed based on COLREG (International Regulations for Preventing Collisions at Sea) or are arbitrary. Therefore, the purpose of this study is to identify and systematize objective navigation situation scenarios for the validation of autonomous ship collision avoidance algorithms. A data-driven approach was applied to collect 12-month Automatic Identification System data in the west sea of Korea, to extract the ship’s trajectory, and to hierarchically cluster the data according to navigation situations. Consequently, we obtained the hierarchy of navigation situations and the frequency of each navigation situation for ships that sailed the west coast of Korea during one year. The results are expected to be applied to develop a collision avoidance test environment for MASS.

Modeling of relative collision risk based on the ships group situation

The collision risk of ships is a fuzzy concept, which is the measurement of the likelihood of a collision between ships. Most of existed studies on the risk of multi-ship collision are based on the assessment of two-ship collision risk, and collision risk between the target ship and each interfering ship is calculated respectively, to determine the key avoidance ship. This method is far from the actual situation and has some defects. In open waters, it is of certain reference value when there are fewer ships, but in busy waters, it cannot well represent the risk degree of the target ship, since it lacks the assessment of the overall risk of the perceived area of the target ship. Based on analysis of complexity of ships group situation, the concept of relative domain was put forward and the model was constructed. On this basis, the relative collision risk was proposed, and the corresponding model was obtained, so as to realize risk assessment. Through the combination of real ship and simulation experiments, the variation trend, stability and sensitivity of the model were verified. The results showed that risk degree of the environment of ships in open and busy waters could be well assessed, and good references for decision-making process of ships collision avoidance could be provided.

A RESEARCH ON TECHNIQUES, MODELS AND METHODS PROPOSED FOR SHIP COLLISION AVOIDANCE PATH PLANNING PROBLEM

The development of soft computing techniques in recent years has encouraged researchers to study on the path planning problem in ship collision avoidance. These techniques have widely been implemented in marine industry and technology-oriented novel solutions have been introduced. Various models, methods and techniques have been proposed to solve the mentioned path planning problem with the aim of preventing reoccurrence of the problem and thus strengthening marine safety as well as providing fuel consumption efficiency. The purpose of this study is to scrutinize the models, methods and technologies proposed to settle the path planning issue in ship collision avoidance. The study also aims to provide certain bibliometric information which develops a literature map of the related field. For this purpose, a thorough literature review has been carried out. The results of the study have pointedly showed that the artificial intelligence methods, fuzzy logic and heuristic algorithms have greatly been used by the researchers who are interested in the related field.

DETERMINISTIC-BASED SHIP ANTI-COLLISION ROUTE OPTIMIZATION WITH WEB-BASED APPLICATION

Most of the accidents are caused by human error at sea so, decision making process made by navigators should be more computerised and automated. The supported decision making can be a step forward to decrease the risk of collision. This paper, in this respect, aims to present a deterministic approach to support optimum collision avoidance trajectory. This approach involves a collision avoidance course alteration. A web-based application coded with "JavaScript" programming language on the "Processing" software platform which allows the own ship to change her course in a deterministic manner to avoid collision optimally has been introduced. Algorithm structure of the method has been formulated and organized according to the International Regulation for Preventing Collision at Sea (COLREGs). The experimental tests results have revealed that the system is practicable and feasible and considerably outperforms heuristic-based method. It is thought that the developed method can be applied in an intelligent avoidance system on board and provides contribution to ship collision avoidance process, automation of ship motion control and ship traffic engineering.