Search

Discussions surrounding Maritime Autonomous Surface Ships (MASS) are occurring in academia, industry, and the International Maritime Organization (IMO). Automatic collision avoidance, as one of the key technologies of MASS, is the core of the autonomous navigation function of MASS, and its role is to solve the autonomous collision avoidance problem during MASS navigation. Convention on the International Regulations for Preventing Collisions at Sea (COLREGS) is a fundamental basis for automatic collision avoidance, and the navigation of MASS should adhere to it. However, the applicability of MASS to COLREGS has not yet been resolved. Responding to these issues, the paper proceeds to analyze the principal challenges of MASS to COLREGS in terms of the application of MASS to good seamanship, the neglect provision, the lookout provision, the insight of one another provision, and the problems of the deviation provision. Furthermore, suggestions are put forth for the revision of COLREGS, including the mode of revision, the reconstruction of MASS collision liability, the long-term coexistence of MASS and traditional ships, and the risk control of COLREGS revision in the context of artificial intelligence. These suggestions aim to establish a foundation for a more effective adaptation to the advent of the MASS era. [ABSTRACT FROM AUTHOR]

This research addresses the crucial problem of collision avoidance decision making for autonomous ships under diverse encounter situations. Building upon the Deep Deterministic Policy Gradient (DDPG) algorithm, appropriate reward functions based on the International Regulations for Preventing Collisions at Sea (COLREGS) have been designed to effectively guide intelligent agents in acquiring optimal strategies. By incorporating the concept of potential reward shaping, the proposed approach ensures efficient obstacle avoidance while adhering strictly to the established rules. Moreover, extensive simulations have been conducted to validate the algorithm’s performance in collision avoidance for both dual-ship and multi-ship scenarios under varying encounter situations, and a comparative analysis with the TD3 algorithm has been undertaken. The obtained results demonstrate that the proposed algorithm exhibits rapid convergence and stable training performance. The resulting models successfully achieve collision-free navigation while strictly adhering to the COLREGS. Particularly, in two-ship encounter situations, the proposed algorithm outperforms the trajectory planned by the TD3 algorithm in terms of shorter path length and higher efficiency. [ABSTRACT FROM AUTHOR]

Decision-making for collision avoidance in complex maritime environments is a critical technology in the field of autonomous ship navigation. However, existing collision avoidance decision algorithms still suffer from unstable strategy exploration and poor compliance with regulations. To address these issues, this paper proposes a novel autonomous ship collision avoidance algorithm, the dynamically adjusted entropy proximal policy optimization (DAE-PPO). Firstly, a reward system suitable for complex maritime encounter scenarios is established, integrating the International Regulations for Preventing Collisions at Sea (COLREGs) with collision risk assessment. Secondly, the exploration mechanism is optimized using a quadratically decreasing entropy method to effectively avoid local optima and enhance strategic performance. Finally, a simulation testing environment based on Unreal Engine 5 (UE5) was developed to conduct experiments and validate the proposed algorithm. Experimental results demonstrate that the DAE-PPO algorithm exhibits significant improvements in efficiency, success rate, and stability in collision avoidance tests. Specifically, it shows a 45% improvement in success rate per hundred collision avoidance attempts compared to the classic PPO algorithm and a reduction of 0.35 in the maximum collision risk (CR) value during individual collision avoidance tasks. [ABSTRACT FROM AUTHOR]

This research addresses the crucial problem of collision avoidance decision making for autonomous ships under diverse encounter situations. Building upon the Deep Deterministic Policy Gradient (DDPG) algorithm, appropriate reward functions based on the International Regulations for Preventing Collisions at Sea (COLREGS) have been designed to effectively guide intelligent agents in acquiring optimal strategies. By incorporating the concept of potential reward shaping, the proposed approach ensures efficient obstacle avoidance while adhering strictly to the established rules. Moreover, extensive simulations have been conducted to validate the algorithm’s performance in collision avoidance for both dual-ship and multi-ship scenarios under varying encounter situations, and a comparative analysis with the TD3 algorithm has been undertaken. The obtained results demonstrate that the proposed algorithm exhibits rapid convergence and stable training performance. The resulting models successfully achieve collision-free navigation while strictly adhering to the COLREGS. Particularly, in two-ship encounter situations, the proposed algorithm outperforms the trajectory planned by the TD3 algorithm in terms of shorter path length and higher efficiency.

The study presents an optimized Unmanned Surface Vehicle (USV) collision avoidance decision-making strategy in restricted waters based on the improved Proximal Policy Optimization (PPO) algorithm. This approach effectively integrates the ship domain, the action area of restricted waters, and the International Regulations for Preventing Collisions at Sea (COLREGs), while constructing an autonomous decision-making system. A novel set of reward functions are devised to incentivize USVs to strictly adhere to COLREGs during autonomous decision-making. Also, to enhance convergence performance, this study incorporates the Gated Recurrent Unit (GRU), which is demonstrated to significantly improve algorithmic efficacy compared to both the Long Short-Term Memory (LSTM) network and traditional fully connected network structures. Finally, extensive testing in various constrained environments, such as narrow channels and complex waters with multiple ships, validates the effectiveness and reliability of the proposed strategy. [ABSTRACT FROM AUTHOR]

Complex multi-vessel encounter situations are a challenging problem for ships to avoid collisions, and the International Regulations for Preventing Collision at Sea, 1972 (COLREGs) do not provide a clear delineation of multi-vessel encounter situations and the responsibility of collision avoidance (CA). Furthermore, Marine Autonomous Surface Ships (MASS), which realize autonomous navigation functions, face the problem of recognizing complex multi-ship encounter situations and the corresponding CA decisions. In this study, we adopt the velocity obstacle (VO) algorithm to visualize and identify the danger of multi-ship encounters with the own ship (OS) as the first viewpoint. Additionally, we consider the motion changes in target ships (TSs) and their possible CA behaviors as the basis of the ship's CA decision-making. According to COLREGs, a simplified method for classifying the encounter situations of multiple clustered ships is proposed, considering the coupling of collision hazards and CA responsibilities between related TSs. On this basis, the corresponding CA decisions for each classified situation are proposed, and a large number of simulation experiments are conducted based on the proposed method by considering the three-ship and four-ship encounter model in the Imazu problem as an example. The experimental results indicate that the proposed method can effectively recognize the complex multi-ship encounter situation in the Imazu problem, and it can adjust the CA measures of the OS in time according to the COLREGs and the behavior of TSs. This provides the basis and reference for MASS when facing complex multi-ship encounter situations. [ABSTRACT FROM AUTHOR]

Path planning is one of the core issues in the autonomous navigation of an Unmanned Surface Vehicle (USV), as the accuracy of the results directly affects the safety of the USV. Hence, this paper proposes a USV path planning algorithm that integrates an improved Particle Swarm Optimisation (PSO) algorithm with a Dynamic Window Approach (DWA). Firstly, in order to advance the solution accuracy and convergence speed of the PSO algorithm, a nonlinear decreasing inertia weight and adaptive learning factors are introduced. Secondly, in order to solve the problem of long path and path non-smoothness, the fitness function of PSO is modified to consider both path length and path smoothness. Finally, the International Regulations for Preventing Collisions at Sea (COLREGS) are utilised to achieve dynamic obstacle avoidance while complying with maritime practices. Numerical cases verify that the path planned via the proposed algorithm is shorter and smoother, guaranteeing the safety of USV navigation while complying with the COLREGS. [ABSTRACT FROM AUTHOR]

The International Regulations for Preventing Collisions at Sea 1972 (COLREGs) have been the cornerstone of maritime navigation since their introduction. Knowledge and implementation of these rules are paramount in collision avoidance at sea. However, terms found in these rules are sometimes imprecise or fuzzy, as they are written by humans for humans, giving them some freedom in interpretation. The term Very Large Ship used in Rule 7 of the COLREGs is, by its nature, fuzzy. While human navigators understand this term's meaning, it could be challenging for machines or autonomous ships to understand such an unprecise expression. Fuzzy sets could easily describe unprecise terms used in maritime navigation. A fuzzy set consists of elements with degrees of membership in a set, making them perfect for interpreting some terms where boundaries are unclear. This research was conducted among 220 navigational experts to describe linguistic variables used in maritime regulations. This research consists of an internationally distributed questionnaire. Membership data were collected with the adapted horizontal method, and the results were statistically analyzed, followed by regression analyses to describe the range and shape of membership functions. A conceptual model of the implementation of linguistic variables is presented. The novelty of this study derives from the data collecting, modeling, and quantification of the important but neglected linguistic term Very Large Ship based on a large number of navigational experts. The same quantification method could be easily used for other COLREGs linguistic variables, which could easily lift barriers to advances in intelligent solutions based on fuzzy sets. The obtained quantified fuzzy sets can be used in decision support or control systems used by conventional or autonomous ships in the future. [ABSTRACT FROM AUTHOR]

The accurate timing for collision avoidance actions is crucial for preventing maritime collisions. Traditional methods often rely on collision risk assessments, using quantitative indicators like the Distance to the Closest Point of Approach (DCPA) and the Time to the Closest Point of Approach (TCPA). Ship Officers on Watch (OOWs) are required to execute avoidance maneuvers once these indicators reach or exceed preset safety thresholds. However, the effectiveness of these indicators is limited by uncertainties in the maritime environment and the human behaviors of OOWs. To address these limitations, this study introduces a machine learning method to learn collision avoidance behavior from empirical data of ship collision avoidance, particularly in cross-encounter situations. The research utilizes Automatic Identification System (AIS) data from the open waters around Ningbo Zhoushan Port. After data preprocessing and applying spatio-temporal constraints, this study identifies ship trajectory pairs in crossing scenarios and calculates their relative motion parameters. The Douglas–Peucker algorithm is used to identify the timing of ship collision avoidance actions and a collision avoidance decision dataset is constructed. The Random Forest algorithm was then used to analyze the factors affecting the timing of collision avoidance, and six key factors were identified: the distance, relative speed, relative bearing, DCPA, TCPA, and the ratio of the lengths of the giving-way and stand-on ships. These factors serve as inputs for the XGBoost algorithm model, which is enhanced with Particle Swarm Optimization (PSO), and thus constructing a ship collision avoidance decision model. In addition, considering the inherent errors in any model and the dynamic nature of the ship collision avoidance process, an action time window for collision avoidance is introduced, which provides a more flexible time range for ships to make timely collision avoidance responses based on actual conditions and the specific encounter environment. This model provides OOWs with accurate timing for taking collision avoidance decisions. Case studies have validated the practicality and effectiveness of this model, offering new theoretical foundations and practical guidance for maritime collision avoidance. [ABSTRACT FROM AUTHOR]

Local path planning, as an essential technology to ensure intelligent ships' safe navigation, has attracted the attention of many scholars worldwide. In most existing studies, the impact of COLREGS has received limited consideration, and there is insufficient exploration of the method in complex waters with multiple interfering ships and static obstacles. Therefore, in this paper, a generation method for a time–space overlapping equivalent static obstacle line for ships in multi-ship encounter scenarios where both dynamic and static obstacles coexist is proposed. By dynamically inferring ships' encounter situations and considering the requirements of COLREGS, the influence of interfering ships and static obstacles on the navigation of the target ship at different times in the near future is represented as static obstacle lines. These lines are then incorporated into the scene that the target ship encountered at the path planning moment. Subsequently, the existing path planning methods were extensively utilized to obtain the local path. Compared with many common path planning methods in random scenarios, the effectiveness and reliability of the method proposed are verified. It has been demonstrated by experimental results that the proposed method can offer a theoretical basis and technical support for the autonomous navigation of unmanned ships. [ABSTRACT FROM AUTHOR]

A path planning method for unmanned surface vessels (USV) in dynamic environment is proposed to address the impact of dynamic environments on path planning results and the lack of dynamic obstacle avoidance capabilities. First, the considering ocean current rapidly exploring random tree (RRT*) (COC-RRT*) algorithm was proposed for global path planning. The RRT* algorithm has been enhanced with the integration of the virtual field sampling algorithm and ocean current constraint algorithm. The COC-RRT* algorithm optimizes the global planning path by adjusting the path between the parent nodes and child nodes. Second, according to the limitations of the International Regulations for Preventing Collisions at Sea (COLREGs), the improved dynamic window approach (DWA) is applied for local path planning. To enhance the ability of avoid dynamic obstacles, the dist function in the DWA algorithm has been improved. Simulation experiments were conducted in three scenarios to validate the proposed algorithm. The experimental results demonstrate that, in comparison with other algorithms, the proposed algorithm effectively avoids dynamic obstacles and mitigates the influence of the space-varying ocean current environment on the path-planning outcome. Additionally, the proposed algorithm exhibits high efficiency and robustness. The results verified the effectiveness of the proposed algorithm in dynamic environments. [ABSTRACT FROM AUTHOR]

In order to effectively deal with collisions in various encounter situations in open water environments, a ship collision avoidance model was established, and multiple constraints were introduced into the velocity obstacle method, a method to determine the ship domain by calculating the safe distance of approach was proposed. At the same time, the ship collision avoidance model based on the ship domain is analyzed, and the relative velocity set of the collision cone is obtained by solving the common tangent line within the ellipse. The timing of starting collision avoidance is determined by calculating the ship collision risk, and a method for ending collision avoidance is proposed. Finally, by comparing the simulation experiments of the improved algorithm with those of the traditional algorithm and the actual ship experiment results of manual ship maneuvering, it is shown that the method can effectively avoid collisions based on safe encounter distances that comply with navigation experience in different encounter situations. At the same time, it has better performance in collision avoidance behavior. It has certain feasibility and practical applicability. [ABSTRACT FROM AUTHOR]

Automatic collision avoidance decision making for vessels is a critical challenge in the development of autonomous ships and has become a central point of research in the maritime safety domain. Effective and systematic collision avoidance strategies significantly reduce the risk of vessel collisions, ensuring safe navigation. This study develops a multi-vessel automatic collision avoidance decision-making method based on deep reinforcement learning (DRL) and establishes a vessel behavior decision model. When designing the reward function for continuous action spaces, the criteria of the "Convention on the International Regulations for Preventing Collisions at Sea" (COLREGs) were adhered to, taking into account the vessel's collision risk under various encounter situations, real-world navigation practices, and navigational complexities. Furthermore, to enable the algorithm to precisely differentiate between collision avoidance and the navigation resumption phase in varied vessel encounter situations, this paper incorporated "collision avoidance decision making" and "course recovery decision making" as state parameters in the state set design, from which the respective objective functions were defined. To further enhance the algorithm's performance, techniques such as behavior cloning, residual networks, and CPU-GPU dual-core parallel processing modules were integrated. Through simulation experiments in the enhanced Imazu training environment, the practicality of the method, taking into account the effects of wind and ocean currents, was corroborated. The results demonstrate that the proposed algorithm can perform effective collision avoidance decision making in a range of vessel encounter situations, indicating its efficiency and robust generalization capabilities. [ABSTRACT FROM AUTHOR]

Decision-making for collision avoidance in complex maritime environments is a critical technology in the field of autonomous ship navigation. However, existing collision avoidance decision algorithms still suffer from unstable strategy exploration and poor compliance with regulations. To address these issues, this paper proposes a novel autonomous ship collision avoidance algorithm, the dynamically adjusted entropy proximal policy optimization (DAE-PPO). Firstly, a reward system suitable for complex maritime encounter scenarios is established, integrating the International Regulations for Preventing Collisions at Sea (COLREGs) with collision risk assessment. Secondly, the exploration mechanism is optimized using a quadratically decreasing entropy method to effectively avoid local optima and enhance strategic performance. Finally, a simulation testing environment based on Unreal Engine 5 (UE5) was developed to conduct experiments and validate the proposed algorithm. Experimental results demonstrate that the DAE-PPO algorithm exhibits significant improvements in efficiency, success rate, and stability in collision avoidance tests. Specifically, it shows a 45% improvement in success rate per hundred collision avoidance attempts compared to the classic PPO algorithm and a reduction of 0.35 in the maximum collision risk (CR) value during individual collision avoidance tasks.

This paper investigates the adaptive neural event-triggered control for an underactuated surface vessel (USV), considering constraints of the obstacle's vicious maneuvering and the limited communication channel. In the algorithm, a novel logical phantom virtual ship (LPVS) guidance principle is developed to generate the global path following reference and the obstacle avoidance order in the simulation results, where the corresponding operation comply to the suggestion in international regulations for prevention collision at sea (COLREGs). The improved design of velocity obstacle (VO) method can guarantee its predictive capability to prevent the obstacle's vicious maneuvering. As for the control module, the adaptive event-triggered control algorithm is proposed by employing the robust neural damping technique and the input event-triggered mechanism. And the derived adaptive law can effectively solve perturbations from the gain uncertainty and the external disturbances. Through the theoretical analysis, all signals of the closed-loop control system are with the semi-globally uniform ultimate bounded (SGUUB) stability. The simulation experiments have been presented to verify the obstacle avoidance effectiveness and the burden-some superiority of the algorithm. • The obstacle's vicious maneuvering is considered in the control design of USV. • The proposed LPVS guidance principle complies to the suggestion in COLREGs. • The derived adaptive law can effectively solve perturbations from gain uncertainty. • The closed-loop system is the semi-global uniformly ultimately bounded. [ABSTRACT FROM AUTHOR]

This research introduces a two-stage deep reinforcement learning approach for the cooperative path planning of unmanned surface vehicles (USVs). The method is designed to address cooperative collision-avoidance path planning while adhering to the International Regulations for Preventing Collisions at Sea (COLREGs) and considering the collision-avoidance problem within the USV fleet and between USVs and target ships (TSs). To achieve this, the study presents a dual COLREGs-compliant action-selection strategy to effectively manage the vessel-avoidance problem. Firstly, we construct a COLREGs-compliant action-evaluation network that utilizes a deep learning network trained on pre-recorded TS avoidance trajectories by USVs in compliance with COLREGs. Then, the COLREGs-compliant reward-function-based action-selection network is proposed by considering various TS encountering scenarios. Consequently, the results of the two networks are fused to select actions for cooperative path-planning processes. The path-planning model is established using the multi-agent proximal policy optimization (MAPPO) method. The action space, observation space, and reward function are tailored for the policy network. Additionally, a TS detection method is introduced to detect the motion intentions of TSs. The study conducted Monte Carlo simulations to demonstrate the strong performance of the planning method. Furthermore, experiments focusing on COLREGs-based TS avoidance were carried out to validate the feasibility of the approach. The proposed TS detection model exhibited robust performance within the defined task. [ABSTRACT FROM AUTHOR]

The study presents an optimized Unmanned Surface Vehicle (USV) collision avoidance decision-making strategy in restricted waters based on the improved Proximal Policy Optimization (PPO) algorithm. This approach effectively integrates the ship domain, the action area of restricted waters, and the International Regulations for Preventing Collisions at Sea (COLREGs), while constructing an autonomous decision-making system. A novel set of reward functions are devised to incentivize USVs to strictly adhere to COLREGs during autonomous decision-making. Also, to enhance convergence performance, this study incorporates the Gated Recurrent Unit (GRU), which is demonstrated to significantly improve algorithmic efficacy compared to both the Long Short-Term Memory (LSTM) network and traditional fully connected network structures. Finally, extensive testing in various constrained environments, such as narrow channels and complex waters with multiple ships, validates the effectiveness and reliability of the proposed strategy.

Path planning is one of the core issues in the autonomous navigation of an Unmanned Surface Vehicle (USV), as the accuracy of the results directly affects the safety of the USV. Hence, this paper proposes a USV path planning algorithm that integrates an improved Particle Swarm Optimisation (PSO) algorithm with a Dynamic Window Approach (DWA). Firstly, in order to advance the solution accuracy and convergence speed of the PSO algorithm, a nonlinear decreasing inertia weight and adaptive learning factors are introduced. Secondly, in order to solve the problem of long path and path non-smoothness, the fitness function of PSO is modified to consider both path length and path smoothness. Finally, the International Regulations for Preventing Collisions at Sea (COLREGS) are utilised to achieve dynamic obstacle avoidance while complying with maritime practices. Numerical cases verify that the path planned via the proposed algorithm is shorter and smoother, guaranteeing the safety of USV navigation while complying with the COLREGS.

Complex multi-vessel encounter situations are a challenging problem for ships to avoid collisions, and the International Regulations for Preventing Collision at Sea, 1972 (COLREGs) do not provide a clear delineation of multi-vessel encounter situations and the responsibility of collision avoidance (CA). Furthermore, Marine Autonomous Surface Ships (MASS), which realize autonomous navigation functions, face the problem of recognizing complex multi-ship encounter situations and the corresponding CA decisions. In this study, we adopt the velocity obstacle (VO) algorithm to visualize and identify the danger of multi-ship encounters with the own ship (OS) as the first viewpoint. Additionally, we consider the motion changes in target ships (TSs) and their possible CA behaviors as the basis of the ship’s CA decision-making. According to COLREGs, a simplified method for classifying the encounter situations of multiple clustered ships is proposed, considering the coupling of collision hazards and CA responsibilities between related TSs. On this basis, the corresponding CA decisions for each classified situation are proposed, and a large number of simulation experiments are conducted based on the proposed method by considering the three-ship and four-ship encounter model in the Imazu problem as an example. The experimental results indicate that the proposed method can effectively recognize the complex multi-ship encounter situation in the Imazu problem, and it can adjust the CA measures of the OS in time according to the COLREGs and the behavior of TSs. This provides the basis and reference for MASS when facing complex multi-ship encounter situations.

In this paper, we propose a collision avoidance method based on deep reinforcement learning (DRL) that simultaneously controls the path and speed of a ship. The DRL is actively applied in machine control and artificial intelligence. To verify the proposed method, we applied it to the Imazu problem. It provides benchmark scenarios for collision avoidance. In particular, we compared and analyzed the collision avoidance performance according to the level of learning and various parameters to ensure that the proposed method displays optimal avoidance performance. The results indicated that the proposed method can determine a safe avoidance path for a given situation. Finally, to compare the performance of the proposed method, we compared the collision avoidance method based on the path–speed control of the OS proposed in this study with the collision avoidance method that controls only the path of the OS (Chun et al., 2021). We observed that the proposed method failed in 6 out of 20 scenarios of the Imazu problem when only the path of the OS was controlled. However, it succeeded in collision avoidance in all the 20 scenarios when both path and speed were controlled simultaneously.

The International Regulations for Preventing Collisions at Sea 1972 (COLREGs) have been the cornerstone of maritime navigation since their introduction. Knowledge and implementation of these rules are paramount in collision avoidance at sea. However, terms found in these rules are sometimes imprecise or fuzzy, as they are written by humans for humans, giving them some freedom in interpretation. The term Very Large Ship used in Rule 7 of the COLREGs is, by its nature, fuzzy. While human navigators understand this term’s meaning, it could be challenging for machines or autonomous ships to understand such an unprecise expression. Fuzzy sets could easily describe unprecise terms used in maritime navigation. A fuzzy set consists of elements with degrees of membership in a set, making them perfect for interpreting some terms where boundaries are unclear. This research was conducted among 220 navigational experts to describe linguistic variables used in maritime regulations. This research consists of an internationally distributed questionnaire. Membership data were collected with the adapted horizontal method, and the results were statistically analyzed, followed by regression analyses to describe the range and shape of membership functions. A conceptual model of the implementation of linguistic variables is presented. The novelty of this study derives from the data collecting, modeling, and quantification of the important but neglected linguistic term Very Large Ship based on a large number of navigational experts. The same quantification method could be easily used for other COLREGs linguistic variables, which could easily lift barriers to advances in intelligent solutions based on fuzzy sets. The obtained quantified fuzzy sets can be used in decision support or control systems used by conventional or autonomous ships in the future.

Local path planning, as an essential technology to ensure intelligent ships’ safe navigation, has attracted the attention of many scholars worldwide. In most existing studies, the impact of COLREGS has received limited consideration, and there is insufficient exploration of the method in complex waters with multiple interfering ships and static obstacles. Therefore, in this paper, a generation method for a time–space overlapping equivalent static obstacle line for ships in multi-ship encounter scenarios where both dynamic and static obstacles coexist is proposed. By dynamically inferring ships’ encounter situations and considering the requirements of COLREGS, the influence of interfering ships and static obstacles on the navigation of the target ship at different times in the near future is represented as static obstacle lines. These lines are then incorporated into the scene that the target ship encountered at the path planning moment. Subsequently, the existing path planning methods were extensively utilized to obtain the local path. Compared with many common path planning methods in random scenarios, the effectiveness and reliability of the method proposed are verified. It has been demonstrated by experimental results that the proposed method can offer a theoretical basis and technical support for the autonomous navigation of unmanned ships.

In this study, an intelligent hybrid algorithm based on deep-reinforcement learning (DRL) is proposed to achieve autonomous navigation and intelligent collision avoidance for a smart autonomous marine surface vessel (SMASV). First, the kinematic model of the SMASV is used, and clauses 13 to 17 of the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) are introduced. Then, the electronic chart is rasterized and used for path planning. Next, states, actions, and reward functions are designed, and collision avoidance strategies are formulated. In addition, a temperature factor and a constrained loss function are used to improve the soft actor–critic (SAC) algorithm. This improvement reduces the challenges of hyperparameter adjustment and improves sampling efficiency. By comparing the improved SAC algorithm with other deep-reinforcement learning (DRL) algorithms based on strategy learning, it is proved that the improved SAC algorithm converges faster than the other algorithms. During the experiment, some unknown obstacles are added to the simulation environment to verify the collision-avoidance ability of the trained SMASV. Moreover, eight sea areas are randomly selected to verify the generalization ability of the intelligent-navigation system. The results show that the proposed method can plan a path for the SMASV accurately and effectively, and the SMASV decision-making behavior in the collision-avoidance process conforms to the COLREGs in both unknown and dynamic environments. [ABSTRACT FROM AUTHOR]

According to The International Regulations for Preventing Collisions at Sea, 1972, ships can only determine their collision avoidance responsibilities in accordance with the rules of "Conduct of Vessels in Sight of One Another" if the dynamic and category of the target ship is identified to be using lights and/or shapes during encounters at sea. Then, appropriate actions can be taken, and the effectiveness of the collision avoidance actions can be checked during the subsequent maneuvering process. In order to analyze and solve the problems related to lights and shapes and to adapt to the development of ship size, speed, and intelligence, this paper firstly reviews the development history and revision process of lights and shapes. Furthermore, it explains the collision avoidance responsibility of ships in sight of one another, analyzes the role of lights and shapes in the collision avoidance process, and summarizes the lights and shapes displayed by different categories of ships. Next, through qualitative and quantitative analysis, the relationship between the visibility distance of lights and shapes and the timing of ship avoidance actions is examined. Finally, the paper points out current problems related to lights and shapes, including: (1) non-uniform visibility distance of lights, (2) insufficient visibility distance of lights, and (3) small size of shapes, and proposes solutions to these problems from theoretical and practical perspectives, including: (1) unifying the visibility distance of masthead light, sidelights, and sternlight to 6 nautical miles, (2) unifying the visibility distance of the sternlight to 3 nautical miles, and (3) unifying the diameter size of shapes and the vertical distance between shapes to 1.8 m. [ABSTRACT FROM AUTHOR]

In this paper, combined with the improved artificial potential field (IAPF) method and the nonlinear model predictive control (NMPC) algorithm, a collision avoidance decision-making support scheme considering ship maneuverability and the International Regulations for Preventing Collisions at Sea (COLREGs) is proposed. First, to comply with the requirements of COLREGs, an improved repulsive potential field is presented for different encounter scenarios when the ship detects the risk of collision, and the coordinated ship domain is applied to provide safety criteria for collision avoidance. Then, by transforming the MMG model to a discrete-time nonlinear system, the NMPC is utilized to predict the future state of the ship according to the current state, and the IAPF method is incorporated to calculate the potential field in each future state as the objective function. Following this approach, the action taken to avoid collision is more effective, the ship motion in avoiding collision is more accurate, and the collision avoidance decision making is more reasonable. Finally, two simulation examples of multi-ship encounter scenarios are applied to illustrate the merits and effectiveness of the proposed collision avoidance decision-making support scheme. [ABSTRACT FROM AUTHOR]

In crowded waters with unknown obstacle motion information, traditional methods often fail to ensure safe and autonomous collision avoidance. To address the challenges of information acquisition and decision delay, this study proposes an optimized autonomous navigation strategy that combines deep reinforcement learning with internal and external rewards. By incorporating random network distillation (RND) with proximal policy optimization (PPO), the interest of autonomous ships in exploring unknown environments is enhanced. Additionally, the proposed approach enables the autonomous generation of intrinsic reward signals for actions. For multi-ship collision avoidance scenarios, an environmental reward is designed based on the International Regulations for Preventing Collision at Sea (COLREGs). This reward system categorizes dynamic obstacles into four collision avoidance situations. The experimental results demonstrate that the proposed algorithm outperforms the popular PPO algorithm by achieving more efficient and safe collision avoidance decision-making in crowded ocean environments with unknown motion information. This research provides a theoretical foundation and serves as a methodological reference for the route deployment of autonomous ships. [ABSTRACT FROM AUTHOR]

The route planning of intelligent ship has been studied a lot, especially in the dynamic planning of collision avoidance, but it is still faced with some difficulties, such as complex model structure, poor compatibility of collision avoidance rules, difficult to practice and so on. Therefore, this paper adopts the integration of field model theory and COLREGs for real-time ship route planning, taking into account the model efficiency and application value. It uses FM algorithm as the basic route planning algorithm, introducing the virtual electric field model to construct the ship navigation situation, and gives the guidance strategy of collision avoidance behavior under different encounter situations considering the COLREGs and daily navigation experience, which integrates it into the field model to form a real-time collision avoidance adjustment route planning algorithm. The proposed algorithm has been compared and verified by simulation in multiple scenes, it is worth mentioning that the algorithm can potentially be developed to advance collision-free route planning in unconstructed environment.

Unmanned vessels have been receiving increasing attention over the past few years. In the research and development sector, Autonomous Surface Vessels have been used for over a decade with different degrees of autonomy. The most advanced vessels are already (circum) navigating the oceans, and the question is raised to what extent they are aligned with relevant international maritime legislation. Currently, there is a noted lack of concrete legal clarification on how to adapt Autonomous Surface Vessels to legal instruments such as the 1972 Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). This paper examines to what extent a fully Autonomous Surface Vessel can comply with a possible amended version of COLREGs. The analysis is conducted from legal and technical perspectives.

ObjectiveIn order to solve the multi-objective collision avoidance problem of unmanned surface vehicles (USVs) in open waters, this paper takes a medium-sized USV as the object and carries out the research and application exploration of a local path planning algorithm based on the Convention on the International Regulations for Preventing Collisions at Sea (COLREGS). MethodsA virtual obstacle line method is proposed to load the constraints of COLREGS based on the RRT algorithm for meeting the practical requirements of collision avoidance path planning in open water. In light of the problem that the RRT algorithm does not consider the speed dimension, a velocity obstacle (VO) algorithm is introduced. Next, a VO-RRT fusion algorithm is proposed and given the most dangerous obstacle strategy in order to solve the problem of real-time collision avoidance under multi-objective conditions. ResultsThe simulation and real ship test results show that the proposed algorithm has better real-time performance and takes less than 50 ms to undertake path re-planning. The collision avoidance path planned by the algorithm meets the relevant requirements of Articles 6, 8 and 13–18 of COLREGS. The proposed method can effectively deal with the multi-target collision avoidance problem in open waters. ConclusionThe proposed method has good rule compliance, real-time and safety performance, and high practical value.

Ship motion planning is a core issue of autonomous navigation for maritime autonomous surface ships (MASS). This paper proposes a novel model predictive artificial potential field (MPAPF) motion planning method for complex encounter scenarios considering collision avoidance rules. A new ship domain is established, in which a closed interval potential field function is designed to represent the inviolable properties of the ship domain. A Nomoto model with a predefined speed during motion planning is adopted to generate followable paths conforming to the ship kinematics. To solve the local optima problem of traditional artificial potential field (APF) method and guarantee the collision avoidance safety in complex encounter scenarios, a motion planning method based on model predictive strategy and artificial potential field, i.e., MPAPF, is proposed. In this method, the ship motion planning problem is transformed to a non-linear optimization problem with multiple constraints including maneuverability, navigation rules, navigable waterway, etc. Simulation results from 4 case studies show that the proposed MPAPF algorithm can solve the problems above and generate feasible motion paths to avoid ship collision in complex encounter scenarios compared to variants of APF, A-star and rapidly-exploring random trees (RRT). • Path planning is converted to a non-linear receding optimization problem. • An eccentric ship domain conforming to COLREGs rules is generated. • A new APF function for different types of encounter obstacles is proposed. [ABSTRACT FROM AUTHOR]

The quality of unmanned surface vehicle (USV) local path planning directly affects its safety and autonomy performance. The USV local path planning might easily be trapped into local optima. The swarm intelligence optimization algorithm is a novel and effective method to solve the path-planning problem. Aiming to address this problem, a hybrid bacterial foraging optimization algorithm with a simulated annealing mechanism is proposed. The proposed algorithm preserves a three-layer nested structure, and a simulated annealing mechanism is incorporated into the outermost nested dispersal operator. The proposed algorithm can effectively escape the local optima. Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) rules and dynamic obstacles are considered as the constraints for the proposed algorithm to design different obstacle avoidance strategies for USVs. The coastal port is selected as the working environment of the USV in the visual test platform. The experimental results show the USV can successfully avoid the various obstacles in the coastal port, and efficiently plan collision-free paths. [ABSTRACT FROM AUTHOR]

Automatic collision avoidance decision making for vessels is a critical challenge in the development of autonomous ships and has become a central point of research in the maritime safety domain. Effective and systematic collision avoidance strategies significantly reduce the risk of vessel collisions, ensuring safe navigation. This study develops a multi-vessel automatic collision avoidance decision-making method based on deep reinforcement learning (DRL) and establishes a vessel behavior decision model. When designing the reward function for continuous action spaces, the criteria of the “Convention on the International Regulations for Preventing Collisions at Sea” (COLREGs) were adhered to, taking into account the vessel’s collision risk under various encounter situations, real-world navigation practices, and navigational complexities. Furthermore, to enable the algorithm to precisely differentiate between collision avoidance and the navigation resumption phase in varied vessel encounter situations, this paper incorporated “collision avoidance decision making” and “course recovery decision making” as state parameters in the state set design, from which the respective objective functions were defined. To further enhance the algorithm’s performance, techniques such as behavior cloning, residual networks, and CPU-GPU dual-core parallel processing modules were integrated. Through simulation experiments in the enhanced Imazu training environment, the practicality of the method, taking into account the effects of wind and ocean currents, was corroborated. The results demonstrate that the proposed algorithm can perform effective collision avoidance decision making in a range of vessel encounter situations, indicating its efficiency and robust generalization capabilities.

In order to effectively deal with collisions in various encounter situations in open water environments, a ship collision avoidance model was established, and multiple constraints were introduced into the velocity obstacle method, a method to determine the ship domain by calculating the safe distance of approach was proposed. At the same time, the ship collision avoidance model based on the ship domain is analyzed, and the relative velocity set of the collision cone is obtained by solving the common tangent line within the ellipse. The timing of starting collision avoidance is determined by calculating the ship collision risk, and a method for ending collision avoidance is proposed. Finally, by comparing the simulation experiments of the improved algorithm with those of the traditional algorithm and the actual ship experiment results of manual ship maneuvering, it is shown that the method can effectively avoid collisions based on safe encounter distances that comply with navigation experience in different encounter situations. At the same time, it has better performance in collision avoidance behavior. It has certain feasibility and practical applicability.

This research introduces a two-stage deep reinforcement learning approach for the cooperative path planning of unmanned surface vehicles (USVs). The method is designed to address cooperative collision-avoidance path planning while adhering to the International Regulations for Preventing Collisions at Sea (COLREGs) and considering the collision-avoidance problem within the USV fleet and between USVs and target ships (TSs). To achieve this, the study presents a dual COLREGs-compliant action-selection strategy to effectively manage the vessel-avoidance problem. Firstly, we construct a COLREGs-compliant action-evaluation network that utilizes a deep learning network trained on pre-recorded TS avoidance trajectories by USVs in compliance with COLREGs. Then, the COLREGs-compliant reward-function-based action-selection network is proposed by considering various TS encountering scenarios. Consequently, the results of the two networks are fused to select actions for cooperative path-planning processes. The path-planning model is established using the multi-agent proximal policy optimization (MAPPO) method. The action space, observation space, and reward function are tailored for the policy network. Additionally, a TS detection method is introduced to detect the motion intentions of TSs. The study conducted Monte Carlo simulations to demonstrate the strong performance of the planning method. Furthermore, experiments focusing on COLREGs-based TS avoidance were carried out to validate the feasibility of the approach. The proposed TS detection model exhibited robust performance within the defined task.

Aiming at the path planning problem of unmanned surface vehicle (USV) in complex dynamic environment with moving multi-obstacle ships, a path planning method based on improved RRT*-Smart (RTSNew) was designed.Firstly, the sampling mode of nodes was optimized, nodes were sampled in the polar coordinate system with USV as the origin, an elliptical sampling range constraint was adopted to avoid invalid sampling, and a historical path buffer pool was used to make full use of the historical path.The optimization greatly reduced the amount of calculation and improved the speed of path planning.Secondly, the expansion mode of nodes was improved.In order to avoid treating dynamic obstacles as static obstacles, time information was added to each node to realize dynamic collision detection and the full use of dynamic obstacles motion information greatly improves the feasibility of the planned path.At the same time, considering the maneuverability of USV, the angle constraint was added in expansion of nodes to ensure smooth path.Finally, virtual obstacles were designed to mobile obstacle ships to make the planned path comply with International Regulations for Preventing Collisions at Sea (COLREGS).Based on VREP platform, the USV navigation simulation experiments and comparative experiments were carried out.The results show that RTSNew can make USV reach the destination efficiently and safely, and it performs better in planning efficiency, path optimization and path security than traditional methods in complex dynamic environment with multi-obstacle ships.RTSNew ensures that the motion path complies with COLREGS, and solves the problems of traditional methods: treating the dynamic obstacles as static obstacles, ignoring COLREGS, large amount of calculation and low efficiency, not suitable for the complex dynamic environment with moving multi-obstacle ships.

Collision Avoidance Systems require correct and unambiguous application of the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). Ship-to-ship dialogs, aimed at sharing encounter data to comply with COLREGs and reaching maneuvering agreements, would help to reduce the risk of collision. Finite State Machine (FSM) is a mathematical model for describing the sequential behavior of a control program. Sequential function chart (SFC) based on FSM, is a graphical programming language for Programmable Logic Controllers, defined by the international standard IEC 61131-3. In this work, SFC language is used to model and program the set of states and transitions involved in the ship-to-ship dialogs initiated when one of them detects a risky situation. SFC facilitates the development, verification, and maintenance of the control program. The implemented ship-to-ship communications to share data will help in eliminating differences in decision-making and achieving safer encounters. An example of a risky encounter illustrates this assertion, not contemplated in the related studies consulted. The implemented dialogs will enable sharing information on the encounter characteristics and reaching agreements on the maneuvers to be performed, or maintaining a record about disagreements.

Ships transport large volumes of cargo, and are therefore major contributors to the global economy. Ship collisions can cause significant economic losses. Path-planning algorithms can prevent such collisions by suggesting the optimal path for navigation. Conventional path-planning algorithms are disadvantageous, because they do not consider the navigation practices followed by experienced navigators. Therefore, in this study, we developed the requirements for optimal local path planning of autonomous ships by considering the open sea, restricted waters, and two-ship and multi-ship interactions, in addition to the navigation practices adopted by navigators and rules in COLREGs part B. First, the navigation practices under various scenarios were collected. Subsequently, these practices were linked to COLREGs part B to extract the key rules and keywords related to collision avoidance. Finally, the requirements for generating the optimal local path were drafted based on the rules and keywords. The utility of the requirements was demonstrated by applying them to representative path-planning algorithms for the timely and accurate evaluation of their effectiveness. The proposed requirements can be utilized to improve the existing path-planning algorithms and develop superior algorithms in the future. [ABSTRACT FROM AUTHOR]

Collision avoidance is critical in unmanned surface vehicles (USVs) and is especially challenging in scenarios involving ships of different intelligence levels. To address this problem, inspired by risk analysis and collision avoidance habits of seafarers, this paper proposes a human-like collision avoidance method based on deep reinforcement learning (DRL) and velocity obstacle (VO). It first introduces a navigation impact factor (NIF) calculation module based on fuzzy theory to simulate human beings' attention mechanisms when facing multiple ships. To be compatible with human beings' regulations, the convention on the International Regulations for Preventing Collisions at Sea (COLREGs) is first to be integrated into the calculation of the NIF calculation module, and the VO algorithm is incorporated into the reward function, which can reduce collision risks in paths and improve safety requirements. In addition, a series of reward functions are carefully designed to balance safety, smoothness, and driving operation. To validate the performance, experiments are conducted on our virtual simulation platform. The results show that our algorithm can accurately assess the impact of target ships (TS) on own ship (OS) in complex environments and can obey the COLREGs. Collision avoidance can be achieved effectively and the path is smoother. [ABSTRACT FROM AUTHOR]

This study presents a novel ship route planning algorithm that takes into account both operational economy and safety by integrating the A∗ algorithm with a collision avoidance algorithm that evaluates the Collision Risk Index (CRI) between the own ship and the target ship. The CRI-based A∗ algorithm defines a penalty zone, allowing the own ship to explore safe routes based on the International Regulations for Preventing Collisions at Sea 1972 (COLREGs) and performs an adaptive and effective node search on an extended local map grid according to various encounter situations. The proposed algorithm is validated through simulations of head-on, fine-broad crossing, converging crossing, and overtaking encounters, indicating an economical and safe optimum route compared to conventional ship domain-based route planning.

Since the rise of intelligent control and multi-sensor integration technology, the development of autonomous ships has been significantly growing over the last decade. This advancement has painted a picture of extreme change with a radical alteration of human factors and new operating models. Inherent with the development of such ships, some concerns regarding their safe operation and integration into the maritime regulatory framework arose. Although the introduction of autonomous vessels is not an impending factor, it is the future, and one day will come into application. The primary concern inherent in the development of autonomous ships is compliance with the current International Regulations for Preventing Collisions at Sea (COLREGS) 1972. This paper uses an interdisciplinary approach to examine autonomous vessel seaborne interactions. The results show that we should actively support the modernization of the maritime industry and integrate it with other autonomous industries in the world. [ABSTRACT FROM AUTHOR]

In order to detect multi-ship encounter situations and improve the safety of navigation, this paper proposed a model which was able to mine multi-ship encounter situations from Automatic identification system (AIS) data and analyze the encounter spatial-temporal process and make collision avoidance decisions. Pairwise encounters identification results and ship motion index were combined into a ship encounter graph network which can use the complex network theory to describe the encounter spatial-temporal process. Network average degree, network average distance and network average clustering coefficient were selected. Based on the recognition results of pairwise encounter identification results, a discrete multi-ship encounter network is constructed. The process of multi-ship encounters from simple to complex to simple is mined based on the process of average network degree from 0 to 0 to obtain a continuous spatial-temporal process. The results can be used for multi-ship encounter situation awareness, multi-ship collision avoidance decision-making and channel navigation evaluation, and also provide data for machine learning. Quaternary dynamic ship domain, fuzzy logic and the weighted PageRank algorithm were used to rank the whole network risk, which is critical to "key ship collision avoidance." This method overcame the problem that the traditional collision risk evaluation method is only applicable to the difference between two ships and ship perception. The risk rank combined with the artificial potential field method was used. Compared with the traditional artificial potential field method, this method has fewer turns and a smoother trajectory. [ABSTRACT FROM AUTHOR]

The congestion of waterways can easily lead to traffic hazards. Moreover, according to the data, the majority of sea collisions are caused by human error and the failure to comply with the Convention on the International Regulation for the preventing Collision at Sea (COLREGs). To avoid this situation, ship automatic collision avoidance has become one of the most important research issues in the field of marine engineering. In this study, an efficient method is proposed to solve multi-ship collision avoidance problems based on the multi-agent reinforcement learning (MARL) algorithm. Firstly, the COLREGs and ship maneuverability are considered for achieving multi-ship collision avoidance. Subsequently, the Optimal Reciprocal Collision Avoidance (ORCA) algorithm is utilized to detect and reduce the risk of collision. Ships can operate at the safe velocity computed by the ORCA algorithm to avoid collisions. Finally, the Nomoto three-degrees-of-freedom (3-DOF) model is used to simulate the maneuvers of ships. According to the above information and algorithms, this study designs and improves the state space, action space and reward function. For validating the effectiveness of the method, this study designs various simulation scenarios with thorough performance evaluations. The simulation results indicate that the proposed method is flexible and scalable in solving multi-ship collision avoidance, complying with COLREGs in various scenarios. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Unmanned surface vehicle (USV) path planning is a crucial technology for achieving USV autonomous navigation. Under global path planning, dynamic local obstacle avoidance has become the primary focus for safe USV navigation. In this study, a USV autonomous dynamic obstacle avoidance method based on the enhanced velocity obstacle method is proposed in order to achieve path replanning. Through further analysis of obstacles, the obstacle geometric model set in the conventional velocity obstacle method was redefined. A special triangular obstacle geometric model was proposed to reconstruct the velocity obstacle region. The collision time was predicted by fitting the previously gathered data to the detected obstacle's distance, azimuth, and other relevant data. Then, it is combined with the collision risk to determine when obstacle avoidance should begin and end. In order to ensure safe driving between path points, the international maritime collision avoidance rules (COLREGs) are incorporated to ensure the accuracy of obstacle avoidance. Finally, through numerical simulations of various collision scenarios, it was determined that, under the assumption of ensuring a safe encounter distance, the maximum change rates of USV heading angle are optimized by 17.54%, 58.16%, and 28.63% when crossing, head-on, and overtaking, respectively. The results indicate that, by optimizing the heading angle, the enhanced velocity obstacle method can avoid the risk of ship rollover caused by an excessive heading angle during high-speed movement and achieve more accurate obstacle avoidance action in the event of a safety encounter. [ABSTRACT FROM AUTHOR]

In this study, an intelligent hybrid algorithm based on deep-reinforcement learning (DRL) is proposed to achieve autonomous navigation and intelligent collision avoidance for a smart autonomous marine surface vessel (SMASV). First, the kinematic model of the SMASV is used, and clauses 13 to 17 of the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) are introduced. Then, the electronic chart is rasterized and used for path planning. Next, states, actions, and reward functions are designed, and collision avoidance strategies are formulated. In addition, a temperature factor and a constrained loss function are used to improve the soft actor–critic (SAC) algorithm. This improvement reduces the challenges of hyperparameter adjustment and improves sampling efficiency. By comparing the improved SAC algorithm with other deep-reinforcement learning (DRL) algorithms based on strategy learning, it is proved that the improved SAC algorithm converges faster than the other algorithms. During the experiment, some unknown obstacles are added to the simulation environment to verify the collision-avoidance ability of the trained SMASV. Moreover, eight sea areas are randomly selected to verify the generalization ability of the intelligent-navigation system. The results show that the proposed method can plan a path for the SMASV accurately and effectively, and the SMASV decision-making behavior in the collision-avoidance process conforms to the COLREGs in both unknown and dynamic environments.

According to The International Regulations for Preventing Collisions at Sea, 1972, ships can only determine their collision avoidance responsibilities in accordance with the rules of “Conduct of Vessels in Sight of One Another” if the dynamic and category of the target ship is identified to be using lights and/or shapes during encounters at sea. Then, appropriate actions can be taken, and the effectiveness of the collision avoidance actions can be checked during the subsequent maneuvering process. In order to analyze and solve the problems related to lights and shapes and to adapt to the development of ship size, speed, and intelligence, this paper firstly reviews the development history and revision process of lights and shapes. Furthermore, it explains the collision avoidance responsibility of ships in sight of one another, analyzes the role of lights and shapes in the collision avoidance process, and summarizes the lights and shapes displayed by different categories of ships. Next, through qualitative and quantitative analysis, the relationship between the visibility distance of lights and shapes and the timing of ship avoidance actions is examined. Finally, the paper points out current problems related to lights and shapes, including: (1) non-uniform visibility distance of lights, (2) insufficient visibility distance of lights, and (3) small size of shapes, and proposes solutions to these problems from theoretical and practical perspectives, including: (1) unifying the visibility distance of masthead light, sidelights, and sternlight to 6 nautical miles, (2) unifying the visibility distance of the sternlight to 3 nautical miles, and (3) unifying the diameter size of shapes and the vertical distance between shapes to 1.8 m.

In this paper, combined with the improved artificial potential field (IAPF) method and the nonlinear model predictive control (NMPC) algorithm, a collision avoidance decision-making support scheme considering ship maneuverability and the International Regulations for Preventing Collisions at Sea (COLREGs) is proposed. First, to comply with the requirements of COLREGs, an improved repulsive potential field is presented for different encounter scenarios when the ship detects the risk of collision, and the coordinated ship domain is applied to provide safety criteria for collision avoidance. Then, by transforming the MMG model to a discrete-time nonlinear system, the NMPC is utilized to predict the future state of the ship according to the current state, and the IAPF method is incorporated to calculate the potential field in each future state as the objective function. Following this approach, the action taken to avoid collision is more effective, the ship motion in avoiding collision is more accurate, and the collision avoidance decision making is more reasonable. Finally, two simulation examples of multi-ship encounter scenarios are applied to illustrate the merits and effectiveness of the proposed collision avoidance decision-making support scheme.

In crowded waters with unknown obstacle motion information, traditional methods often fail to ensure safe and autonomous collision avoidance. To address the challenges of information acquisition and decision delay, this study proposes an optimized autonomous navigation strategy that combines deep reinforcement learning with internal and external rewards. By incorporating random network distillation (RND) with proximal policy optimization (PPO), the interest of autonomous ships in exploring unknown environments is enhanced. Additionally, the proposed approach enables the autonomous generation of intrinsic reward signals for actions. For multi-ship collision avoidance scenarios, an environmental reward is designed based on the International Regulations for Preventing Collision at Sea (COLREGs). This reward system categorizes dynamic obstacles into four collision avoidance situations. The experimental results demonstrate that the proposed algorithm outperforms the popular PPO algorithm by achieving more efficient and safe collision avoidance decision-making in crowded ocean environments with unknown motion information. This research provides a theoretical foundation and serves as a methodological reference for the route deployment of autonomous ships.

Navigation safety is one of the primary operational requirements for unmanned surface vehicles (USVs) in a complex marine environment, mainly guaranteed by a reliable path planning system for collision avoidance. This work proposes a novel weighted sum multi-objective optimisation strategy for USV collision avoidance path planning in restricted waters. In particular, the coefficients of different objectives could be tuned to emphasise the most critical design consideration under varying navigation scenarios. Moreover, in addition to the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs), the terrain and weather constraints were also considered in the path planning system. The proposed USV collision avoidance path planning framework's effectiveness was demonstrated through numerical simulations and hardware-in-the-loop (HIL) tests. The numerical simulation results indicate that the proposed method could avoid collision with dynamic and static obstacles, and it is also adaptive to different navigation restrictions and preferences. Moreover, a USV navigation platform was established by incorporating true Automatic Identification System (AIS) signals, and HIL tests were performed with real-time AIS data in a water channel in the Zhoushan archipelago. The results demonstrate that the proposed USV path planning strategy is applicable in restricted waters with complex terrains and weather constraints. [ABSTRACT FROM AUTHOR]