No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Intelligent Ocean Navigation and Fuzzy-Bayesian Decision/Action Formulation
Abstract
This paper focuses on the formulation of a deci-sion–action execution model that can facilitate intelligent collision avoidance features in ocean navigation systems, while respecting the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) rules and regulations of collision avoidance. The decision/action process in this work consists of a fuzzy-logic-based parallel decision-making (PDM) module whose decisions are formulated into sequential actions by a Bayesian-network-based module. Therefore, the paper presents a collision avoidance system (CAS) that is capable of making multiple parallel collision avoidance decisions regarding several target vessel collision conditions, and those decisions are executed as sequential actions to avoid complex collision situations in ocean navigation.
... Consequently, the systems that provide the capacities required in order to consider a vessel as autonomous have become a very active field of research [1][2][3]. These systems, which are shown in Figure 1, must: estimate the vessel's state vector [4,5], control its course and velocity through the actuators [4,5], process the sensor measurements to generate a model of the environment surrounding the USV [6][7][8][9][10][11] and carry out safe guidance of the vehicle towards its goal [3][4][5]7,9,[12][13][14][15][16][17][18][19][20][21][22]. Therefore, the autonomy of a USV is determined by the level of development of the estimation, control, obstacle detection and guidance systems, and by their integration in a hardware platform [1][2][3]. ...
... Once a path is established, the path following algorithms change the course and velocity of the USV to follow it [4,5,19,25]. Finally, due to the presence of unknown obstacles for the path planner, reactive algorithms use the information provided by the obstacle detection system (generated from sensors' measurements) to modify the course/velocity setpoints in order to avoid a collision [9,[12][13][14][15][16][26][27][28][29][30]. Of the systems shown in Figure 1, this work is focused on the obstacle avoidance (OA) systems applied to the USV. ...
... Today there are many reactive methods that provide a vessel with the capacity to avoid obstacles [9,11,[13][14][15][16][17]23,25,[32][33][34][35][36][37][38][39][40][41][42][43][44][45][46][47][48]. To illustrate this diversity, while the great majority of these methods have been designed for propulsion vessels, the approach proposed in [48] uses a potential reactive field to take into account the kinematic limitations of a sailboat due to wind direction. ...
This paper is centered on the guidance systems used to increase the autonomy of unmanned surface vehicles (USVs). The new Robust Reactive Static Obstacle Avoidance System (RRSOAS) has been specifically designed for USVs. This algorithm is easily applicable, since previous knowledge of the USV mathematical model and its controllers is not needed. Instead, a new estimated closed-loop model (ECLM) is proposed and used to estimate possible future trajectories. Furthermore, the prediction errors (due to the uncertainty present in the ECLM) are taken into account by modeling the USV's shape as a time-varying ellipse. Additionally, in order to decrease the computation time, we propose to use a variable prediction horizon and an exponential resolution to discretize the decision space. As environmental model an occupancy probability grid is used, which is updated with the measurements generated by a LIDAR sensor model. Finally, the new RRSOAS is compared with other SOA (static obstacle avoidance) methods. In addition, a robustness study was carried out over a set of random scenarios. The results obtained through numerical simulations indicate that RRSOAS is robust to unknown and congested scenarios in the presence of disturbances, while offering competitive performance with respect to other SOA methods.
... Once the state of the vehicle is known, the detection system processes the information received by the surrounding sensors in order to generate a model of the environment in which the USV is located [6][7][8][9][10]. Using this model of the environment, the guidance system (composed by algorithms of: obstacle avoidance [8,[11][12][13][14][15][16], path following [4,5,17,18] and path planning [3,7,17,19,20]) demands the course and speed setpoints which guide the vessel safely to its goal. With the aim of ensuring that the vehicle reaches these setpoints, the control system commands the vessel's actuators (propulsion system and steering machine) [4,5]. ...
... In this way, the degree of autonomy of the USV is determined by the level of development of each subsystem, as well as by the integration of the set [1][2][3]. From the subsystems shown in Figure 1, this work is focused on the obstacle avoidance systems applied to USVs [8,10,[12][13][14][15][16][21][22][23][24][25][26][27][28][29][30][31]. Most of this work is focussed on the avoidance of dynamic obstacles in open sea situations [8,[12][13][14][15][21][22][23][24][25][26][27][28]. ...
... From the subsystems shown in Figure 1, this work is focused on the obstacle avoidance systems applied to USVs [8,10,[12][13][14][15][16][21][22][23][24][25][26][27][28][29][30][31]. Most of this work is focussed on the avoidance of dynamic obstacles in open sea situations [8,[12][13][14][15][21][22][23][24][25][26][27][28]. And, although some of All these obstacle avoidance methods have a common requirement, they need a simulation environment for their design, development and evaluation. ...
This work is focused on reactive Static Obstacle Avoidance (SOA) methods used to increase the autonomy of Unmanned Surface Vehicles (USVs). Currently, there are multiple approaches to avoid obstacles, which can be applied to different types of USV. In order to assist in the choice of the SOA method for a particular vessel and to accelerate the pretuning process necessary for its implementation, this paper proposes a new AutoTuning Environment for Static Obstacle Avoidance (ATESOA) methods applied to USVs. In this environment, a new simplified modelling of a LIDAR (Laser Imaging Detection and Ranging) sensor is proposed based on numerical simulations. This sensor model provides a realistic environment for the tuning of SOA methods that, due to its low load computation, is used by evolutionary algorithms for the autotuning. In order to analyze the proposed ATESOA, three SOA methods were adapted and implemented to consider the measurements given by the LIDAR model. Furthermore, a mathematical model is proposed and evaluated for using as USV in the simulation enviroment. The results obtained in numerical simulations show how the new ATESOA is able to adjust the SOA methods in scenarios with different obstacle distributions.
... A widely used way is incorporating International Regulations for Preventing Collisions at Sea" (COLREGs) and good seamanship in the rule system. This system is expected to suggest rule-compliant actions for the OS in various scenarios, which is usually based on Neural networks (Praczyk, 2015), Fuzzy logic and Bayesian network (Perera, Carvalho, & Soares, 2012). Since the enumeration of rules for all scenarios is impossible, this method does not guarantee collision-free. ...
... In recent year, researchers introduce part of navigation rules in collision avoidance, e.g., (Johansen et al., 2016;Kuwata et al., 2014;H. Lyu & Yin, 2018;Perera et al., 2012), etc. Some popular rules are frequently used in finding a rule-compliant collision-free solution, i.e., Rule 6, 8, 13-19 from COLREGs. ...
... (Fang et al., 2017; Multiplerule NA Single One maneuver (u and ) -Simple, but might not figure out all the possible scenarios. (Perera et al., 2012) Virtual Vector APF NA Multiple One maneuver ( ) -Simple, but easy goes to a local minimum, not for a dynamic environment, and ignore dynamics. ...
Collision prevention is critical for navigation safety at sea. At early ages, researchers aimed at developing navigational assistance systems for enhancing situational awareness of human operators as human is at the core of collision avoidance. Recently, autonomous vehicles have gained a remarkable amount of attention with a focus on solving collision problems by machines. This results in two groups of studies, both working on preventing collisions but with different focuses: one aims at conflict detection, and the other focuses on conflict resolution. This paper offers a comprehensive overview of collision prevention techniques based on the three basic processes of determining evasive solutions, namely, motion prediction, conflict detection, and conflict resolution. The strengths and weaknesses of different methods for these three fundamental processes are discussed. Limitations and new challenges are highlighted. Moreover, this review points out the differences between the research for manned and unmanned ships and how the research in the two domains can learn from each other. A potential roadmap for the transition from existing manned ships to fully unmanned ships is provided in the end.
... Meanwhile, collisions and groundings sometimes bring serious casualties, property loss and environmental pollution [10,11], and most of them are caused by decision making failures and human errors under complex navigation environment and ship encounter scenarios [8,[12][13][14]. Therefore, to improve the ship navigation safety, one effective strategy is to construct intelligent and autonomous decision support systems for ship route planning [15][16][17][18]. ...
... Although the global motion planning can ignore the real-time performance, the computational efficiency of PTA is not satisfactory. In addition, heuristic algorithms are widely applied to finding feasible paths, and algorithms include Artificial Neural Network (ANN) [37], Evolution Algorithm (EA) [38], Fuzzy Logic (FL) [17,39] and A* Algorithm [19]. The heuristic path planning methods are usually realized in a random mode, and the path can be obtained by iterative convergence or mapping between input and output. ...
A two-stage ship path planning method is proposed, based on the Rapid-exploring Random Tree (RRT) algorithm, which is composed of global path planning and local path planning, addressing the important problem of finding an economical and safe path from start to destination for ships under dynamic environment, especially in waters with multiple obstacles and multiple target ships. The global path planning takes into consideration the ship draft and Under Keel Clearance to find navigable water using RRT, and reduces the path length and waypoints based on elliptic sampling and smoothing. In the local path planning, a dynamic collision risk detection model is constructed by introducing the Quaternion Ship Domain under a dynamic environment, and the restrictions of ship manoeuvrability and COLREGs are also involved. The simulation results show that the proposed model can find a satisfactory path within a few iterations, and keep clear of both static obstacles and dynamic ships. The research can be used to make and verify planned ship routes before sailing and to guide officers to make decisions regarding collision avoidance.
... Scholars at home and abroad have done a lot of research work. The vast majority of scholars mainly focus on the geometric characteristics between own ship and other encounter ships to determine the hazard level, using DCPA and TCPA as the input variables without causality [1]- [3],using fuzzy theory [4]- [6], evidence theory [7]- [9], integrated consideration of ship domain [10]- [12] and other methods to calculate the collision hazard of ships, which cannot accurately grasp the weight relationship between TCPA and DCPA in nautical practice, and different criteria exist for their quantification, and their results are more subjective and The deviation is large. Fiorini et al. put forward the concept of velocity obstacle [13] in 1998, where, by calculating and controlling velocity, the velocity obstacle method is combined with ship dynamics [14], the influence of external environment such as wind, waves, currents and ship dynamics is comprehensively considered [15], and nonlinear velocity obstacle is adopted [16], [17] for ship anti-collision, etc. ...
... The relative distance S in Euclidean space is transformed by projection into S, in non-Euclidean space, which is the norm of the vector − → OQ, and the coordinates of the point Q can be found by formula (6). Thus the projected relative distance between the two ships is ...
With the continuous development of the shipping industry, the shipping traffic density is increasing day by day, and the ship collision accidents are increasing year by year. As the collision of ships will lead to serious losses, people pay more attention to how ships perceive the encounter risks and adopt safer navigation strategies. In order to quantify the risks in the process of ship encounter, this paper proposes a ship encounter risk perception model based on Riemann sphere projection transformation, which projects the relative motion trajectory of Ship as the relative curve motion on the Riemann sphere, constructs the encounter risk model by using the relative velocity and relative distance of the ship on Riemann sphere, and simulates it based on three encounter situations and actual accident cases, and compares the reliability of the model with the traditional fuzzy comprehensive evaluation model based on cases. The results show that the model proposed in this paper can effectively assess the ship encounter risks and creates a more intuitive real-time visual output, which is convenient to assist Ship Anti-collision decision-making. At the same time, it can provide theoretical basis for the inversion of ship collision accidents and the identification of responsibilities.
... In recent years, some existing navigation rules have been used to find a rule-compliant collision-free solution; for example [14], [25]- [29]. Among these, [14] and [29] use APF and suffer from local minima. ...
... However, it also neglects the dynamics and kinetics constraints of ships. In [25] and [27], rule-compliant actions are generated by neural networks. The limitation is that collision-free solutions are not guaranteed. ...
Autonomous marine vessels are expected to avoid inter-vessel collisions and comply with the international regulations for safe voyages. This paper presents a stepwise path planning method using stream functions. The dynamic flow of fluids is used as a guidance model, where the collision avoidance in static environments is achieved by applying the circular theorem in the sink flow. We extend this method to dynamic environments by adding vortex flows in the flow field. The stream function is recursively updated to enable "on the fly" waypoint decisions. The vessel avoids collisions and also complies with several rules of the Convention on the International Regulations for Preventing Collisions at Sea. The method is conceptually and computationally simple and convenient to tune, and yet versatile to handle complex and dense marine traffic with multiple dynamic obstacles. The ship dynamics are taken into account, by using Bezier curves to generate a sufficiently smooth path with feasible curvature. Numerical simulations are conducted to verify the proposed method.
... Besides, to integrate available information from multiple data sources, fuzzy logic-based regressions are frequently used in constructivist models (Perera et al., 2010(Perera et al., , 2012Bukhari et al., 2013;Goerlandt and Montewka, 2015b). One of the main advantages of these approaches is their ability to handle complex and discretised inputs in a relatively simple manner. ...
... Moreover, the used parameters and the assumption in the fuzzy regression model refer to the previous studies (Ahn et al., 2012;Perera et al., 2012;Goerlandt et al., 2015). The outcomes of the three approaches are compared to validate the proposed framework (see Video 2). ...
The paper proposes an integrated multi-criteria framework for assessing dynamically the ship collision risk under different scenarios. The framework identifies collision candidates, evaluates collision parameters and weights the importance of each collision parameter in different conditions, according to the ship officers’ experience. The information is aggregated using the evidential reasoning approach allowing real-time collision risk evaluations of collision scenarios. The framework is used to assess the collision risk in Portuguese continental coastal waters to illustrate its applicability. Moreover, the rationality of the proposed framework is assessed through a comparative analysis with other aggregating approaches such as the linear regression and the fuzzy regression models.
... Collision Avoidance System. As defined by [10], a generalized CAS should at least contain collision risk assessment, action decision-making, and action execution modules, in which the decision selection is the core of the CAS as it is essential for safe navigation of MASS [11]. ...
... suggested a quantitative evaluation approach to analyse the collision risk. e second group covers the knowledgebased marine collision avoidance system to improve the stability and comprehensibility of the models [15]. is type of CAS selects the optimal collision avoidance scheme through various ship dynamic parameters, e.g., course [16], relative speed [10], and ship trajectories [17]. e applied approaches in the CAS include fuzzy logic [4] and Bayesian network [18]. ...
Maritime Autonomous Surface Ships (MASSs) are attracting increasing attention in recent years as it brings new opportunities for water transportation. Previous studies aim to propose fully autonomous system on collision avoidance decisions and operations, either focus on supporting conflict detection or providing with collision avoidance decisions. However, the human-machine cooperation is essential in practice at the first stage of automation. An optimized collision avoidance decision-making system is proposed in this paper, which involves risk appetite (RA) as the orientation. The RA oriented collision avoidance decision-making system (RA-CADMS) is developed based on human-machine interaction during ship collision avoidance, while being consistent with the International Regulations for Preventing Collisions at Sea (COLREGS) and Ordinary Practice of Seamen (OPS). It facilitates automatic collision avoidance and safeguards the MASS remote control. Moreover, the proposed RA-CADMS are used in several encounter situations to demonstrate the preference. The results show that the RA-CADMS is capable of providing accurate collision avoidance decisions, while ensuring efficiency of MASS maneuvering under different RA.
... In this section, the representative algorithms regarding the demand of HMIs addressed in Section 2.1 are compared and shown in Table 2. "Rule-based" methods usually offer one feasible solution to operators or MASS controllers. The feasible solution could be a course , a speed (Perera et al., 2012), or a pattern (enlarge rudder angle until it is collision-free) (Fang et al., 2017), etc. In these studies, Fuzzy logic based methods are popular (Perera et al., 2012;Wu et al., 2020). ...
... The feasible solution could be a course , a speed (Perera et al., 2012), or a pattern (enlarge rudder angle until it is collision-free) (Fang et al., 2017), etc. In these studies, Fuzzy logic based methods are popular (Perera et al., 2012;Wu et al., 2020). Nevertheless, since the collision check is not inclusive, some algorithms might not guarantee that the solution is collision-free. ...
Maritime Autonomous Surface Ships (MASS) attract increasing attention in recent years. Researchers aim at developing fully autonomous systems that replace the role of human operators. Studies either focus on supporting conflict/collision detection (for manned ships) or solving conflict automatically (for unmanned ships). The cooperation between human and machine has been less focused on in existing studies. However, this type of cooperation is essential both in practice and in the future: firstly, demands on navigational assistance are still strong for supporting navigators in manned ships; secondly, MASS with different autonomy levels require increasing cooperation between human operators and machines, e.g. monitoring automation, remotely controlling the ship, etc.; thirdly, the intelligence of human and the machines is highly complementary. Moreover, fully autonomous ships cannot replace all the manual ships overnight. Therefore, the future waterborne transport system will be a system in which both human-operated vessels and autonomous vessels exist.
In this article, we firstly provide an overview of existing modes of human-machine interaction (HMI) during ship collision avoidance. Then, we propose a framework of HMI oriented Collision Avoidance System (HMI-CAS) whose decision-making process is interpretable and interactive for human operators. The HMI-CAS facilitates automatic collision avoidance and enables the human operators to take over the control of the MASS safely. Moreover, the proposed framework acknowledges the under-actuated feature of ships. Simulations are carried out to demonstrate the proposed HMI-CAS. The results show that the proposed HMI-CAS can not only control the under-actuated MASS to avoid collision automatically but also share the decision-making with human operators and support the operators to control the MASS.
... Ship collision avoidance has been always a hot topic in maritime safety area (Zhao, 1996), which has attracted a lot of attention in the maritime industry recently with the introduction of the concept of the intelligent ship (Yun and Wei, 2017;Thieme et al., 2018). Advanced theories and methods such as expert system (Sosnin, 2009;Lee and Rhee, 2001), fuzzy control (Zhao et al., 1995;Hong et al., 1999b,a;Perera et al., 2012), line-of-sight guidance (Wilson et al., 2003), genetic algorithm (Kim et al., 2017;, evidence reasoning (Zhao et al., 2016), neural network (Simsir et al., 2014;Ahn et al., 2012), artificial potential field (Mousazadeh et al., 2018;Xue et al., 2011), and swarm intelligence optimization algorithm (Ma et al., 2018;Lazarowska, 2015;Tsou and Hsueh, 2010), have been applied in the studies of automatic collision avoidance in the past decades. ...
... In further researches (Hara and Hammer, 1993), the subjective feelings of the crew are also considered in fuzzy classification. In aspect of fuzzy reasoning, Perera et al. (2011) uses fuzzy maximum first (FMF) for reasoning, and several representative achievements are achieved (Perera et al., 2014(Perera et al., , 2012. In Park et al. (2007) a case-based Reasoning (CBR) fuzzy mathematical method is also used for collision avoidance and obtained reliable results (Park and Kim, 2011;Park et al., 2007). ...
To enhance the real-time performance and reliability of existing ship collision avoidance methods by collision risk prediction, a predictive collision avoidance method based on an improved beetle antennae search (BAS) algorithm for underactuated surface vessels is proposed. Firstly, a simplified 3-DOF hydrodynamic model based on Abkowitz model is proposed, which provides a model basis for real-time prediction of ship states and collision risks. Referring to the idea of model predictive control (MPC), a predictive optimization strategy for real-time collision avoidance is established by minimizing the safety cost and the economic cost, i.e., collision risk and control changes at the same time. Specifically, the proposed simplified 3-DOF model is used as the state predictive model and the International Regulations for Preventing Collisions at Sea (COLREGs) is considered as the control constraints. To solve the optimization problem, an improved BAS algorithm is proposed to enhance the optimization performance of the original BAS algorithm under the known constraints, which is applied to solve the predictive collision avoidance problem. Simulation experiments under several typical encounter scenarios are carried out based on KVLCC2 ship model, and the effectiveness of the improved BAS based predictive collision avoidance method is verified.
... To realize medium and strong cooperation, variations of the algorithms with extra information exchange settings are needed. [1,17,44,52,71] SI / [40] SI, OC, VO / [10] SI, VO / [24] SI, ES / [68] SI, APF, VO / [49] OC, PSO / [27] OC, MPC, RRT / [30,31] OC, GT / [3,35,37,51,79] DL / [21] DL, FC / [72] DL, MPC / [55,77] MPC / [29] MPC, VO / [16,52,64] ES / [23] ES, FC / [84] FC, Other / [20,22,26,56,58,69] FC / [45] FC, APF / [5,15,54,59,68,70,74,76] VO / [2,34,38,47,60,65,81,82] APF / [46,48,53] RRT / [25,18,28,39,42,50,63,66,73,80,83] Other / [19] SI, FC Visibility [36,41,75] OC Visibility [43] FC, Other Current [62] Other Current [33] RRT Waves, current [67,78] DL Wind, waves, current [61] DL, VO Wind, waves, current [32] MPC Wind, waves, current Notes: / stands for no consideration in the related paper(s). The abbreviation of collision avoidance methods is shown in Table AⅠ. ...
Communication among the ships can provide additional information that assists ships in negotiating and collaborating with others to take effective actions. This paper provides a review on ship collision avoidance methods proposed during the last decade from the perspectives of communication and cooperation. Two innovatively indices are defined, i.e., the communication index and the cooperation index. The overview of the existing research shows that collision risks are the most often exchanged information, while weak cooperation based on predefined protocols or rules, like COLREGs, is the majority. Competition and high-level cooperation are rarely studied in the past, but these topics have attracted increasing attention. Moreover, the analysis of the two indices reveals that communication is the premise of cooperation. Higher-level cooperation requires detailed information, which means higher communication requirements. The main challenges for future research are identified, including cooperation among heterogeneous ships considering various autonomous levels and cooperation levels, the stability of the communication network and the reliability of the exchanged information, methods for obtaining the required information, and quantitative interpretations of COLREGs and seamanship.
... Ahn et al. (2012) proposed a collision risk model that uses an adaptive network-based fuzzy inference system and multilayer perceptron. Perera et al. (2012) presented a collision risk model that comprises a decision-making module combining fuzzy logic and a Bayesian network. Wu et al. (2019) proposed a ship-bridge collision alert system that considers the ship parameters, bridge parameters, and natural environment. ...
Rule 17 of the COLREGS states that a stand-on ship should take cooperative action to avoid a collision when the action of the give-way ship will not be sufficient to avoid a collision. However, most studies on collision avoidance have focused on the action of the give-way ship and not on what the stand-on ship should do. In this study, a novel criterion was developed for assessing when a stand-on ship should take action for collision avoidance that is called the computed distance at collision (CDC). Simulations were performed of the maneuvering motions of two ships in various situations to assess whether or not a collision would occur. The results of the collision assessment were assessed by the CDC, which is calculated from the ship's parameters such as the ship's heading, length, and collision angle between the two ships. Meanwhile, the actual distance (AD) between the two ships can be calculated according to their coordinates. When the CDC is greater than the AD, this means that a collision is inevitable. In other words, the stand-on ship should take action to avoid a collision while the CDC is still less than the AD. Of course, this study may have the following limitations: The study was conducted on the same model ship under calm water conditions. The interactions of hull-propeller-rudder-engine of ship and interaction of hull-hull between the two ships was not considered, and uncertainty of MMG (Maneuvering Modeling Group) model may exist. However, this study should help determine the timing of actions by the stand-on ship for collision avoidance, whether manned or unmanned.
... In recent years, researchers began to introduce artificial intelligence technology into the field of collision avoidance, using neural network, fuzzy theory and genetic algorithm to study the problem of collision avoidance, and then opened the research field of software computing automatic collision avoidance, which is different from the pure mathematical model. At the same time, some scholars put forward the development analysis of collision avoidance technology and path planning for ships in close encounter at sea, and used multi-objective optimization algorithm to search for the route planning of the best route [11][12][13]. ...
... Fuzzy logic methods are used for collision avoidance path optimization. Aiming at the problem of collision avoidance in complex multi-ship encounter situations, ref. [11] proposed a Fuzzy-Bayesian ship intelligent collision avoidance decision-making model to achieve continuous collision avoidance actions. In addition, this method was upgraded in ref. [12], but the action changes of the target ship were not considered. ...
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.
... The ocean environment is full of complexities and vagaries, so the AUV should autonomously plan its path to avoid collisions and save the battery energy by utilizing the ocean current. It is challenging for an AUV to reach a satisfactory path in the mission region with the existence of dynamic obstacles and time-varying current, which may seriously endanger driving safety and impact AUV's duration [2]. ...
Energy-efficient path planning is essential for the autonomous underwater vehicle (AUV)-based ocean exploration. Existing static environment-based AUV path planners do not work well in dynamic ocean environments. A novel onboard sensing system-based AUV path planning strategy is proposed, and it is suitable for a regional dynamic environment to improve the energy utilization efficiency of an AUV working in a small-scale and dynamic mission area. Firstly, unlike the existing methods, the onboard sensing system including horizontal acoustic doppler current profile and detecting sonar is used to obtain environmental information, and the probabilistic multiple hypothesis tracker and Kalman filter are employed to carry out multi-step prediction of the environment. After that, the differential evolution algorithm is introduced as the optimizer, and a novel prediction-based path evaluator is designed to evaluate the fitness of possible paths. Besides, a novel prediction-based online re-planning strategy is designed, which is beneficial to reduce the impact of forecast error and the planning is thus closed-loop. Finally, multiple simulation experiments are designed to verify the effectiveness and superiority of the path planner, and the results show that the proposed planning strategy can reduce the AUV energy consumption by at least 4.6% compared with static environment-based planners.
... Multiple collision avoidance controllers have been proposed that fulfil the aforementioned specifications; in [5], a hierarchical multiobjective optimization problem is formulated, which generates an intermediate waypoint for the controlled vessel while accounting for the good seamanship rules. In [6], a fuzzy-Bayesian collision avoidance controller is formulated capable of addressing multiple obstacle vessels at once. In [7], optimal trajectories for the collision avoidance problem are generated using a B-Spline-based search algorithm. ...
The field of automatic collision avoidance for surface vessels has been an active field of research in recent years, aiming for the decision support of officers in conventional vessels, or for the creation of autonomous vessel controllers. In this paper, the multi-ship control problem is addressed using a model predictive controller (MPC) that makes use of obstacle ship trajectory prediction models built on the RBF framework and is trained on real AIS data sourced from an open-source database. The usage of such sophisticated trajectory prediction models enables the controller to correctly infer the existence of a collision risk and apply evasive control actions in a timely manner, thus accounting for the slow dynamics of a large vessel, such as container ships, and enhancing the cooperation between controlled vessels. The proposed method is evaluated on a real-life case from the Miami port area, and its generated trajectories are assessed in terms of safety, economy, and COLREG compliance by comparison with an identical MPC controller utilizing straight-line predictions for the obstacle vessel.
... Moreover, model uncertainties are also a pervasive problem in most engineering fields. Based on universal approximation theorem [13], fuzzy logic system [4], or NN (Neural Network) control [5] has been widely used to solve the control issues for nonlinear uncertain systems, and some significant results have been published in [14][15][16][17][18]. In reference [14], for an input-output linearization applied in nonlinear vessel steering system, the system was divided into a system with linear dynamics and a system with internal dynamics. ...
Traffic engineering control is a major challenge in marine transportation. Cost efficiency and high performance demand advanced technologies for the ship control systems. This paper develops an autopilot heading control scheme based on a fuzzy state observer for an intelligent ship on this subject to track the prescribed function while calling for performance limitation and order execution time. A fuzzy logic system (FLS) is adopted to approximate the unknown uncertainties caused by the changes in water depth, wind, wave, ship loading, and speed in navigation. State observer is required to obtain unknown yaw rate. By adopting performance function and tracking error transformation techniques, the heading tracking error can converge to prescribed performance bounds. Taking settling time into account, the finite-time adaptive prescribed performance control algorithm can save more resources effectively. Based on the Lyapunov stability theory, the observer-based adaptive fuzzy control approach does not cause any unbounded signal, the system remains stable. Meanwhile, the autopilot heading control system with an unknown yaw rate and constraint state can benefit from the given design.
... Naeem et al. [16] and Tam and Bucknall [17] used pre-set course change method, while Fang et al. [18] proposed to enlarge rudder angle until the trajectory is collision-free. Praczyk [19] mentioned Neural Network (NN) as a suggestion tool for rule-complaint actions, while Perera et al. [20] suggested Bayesian network for the same. The main advantage of this rule-based method is the COLREGs rules, and good seamanship can be treated in the rule system explicitly. ...
As the number of ships for marine transportation increases with the advancement of global trade, encountering multiple ships in marine traffic becomes common. This situation raises the risk of collision of the ships; hence, this paper proposes a novel Fuzzy-logic based intelligent conflict detection and resolution algorithm, where the collision courses and possible avoiding actions are analysed by considering ship motion dynamics and the input and output fuzzy membership functions are derived. As a conflict detection module, the Collision Risk (CR) is measured for each ship by using a scaled nondimensional Distance to the Closest Point of Approach (DCPA) and Time to the Closest Point of Approach (TCPA) as inputs. Afterwards, the decisions for collision avoidance are made based on the calculated CR, encountering angle and relative angle of each ship measured from others. In this regard, the rules for the Fuzzy interface system are defined in accordance with the COLREGs, and the whole system is implemented on the MATLAB Simulink platform. In addition, to deal with the multiple ship encounters, the paper proposes a unique maximum-course and minimum-speed change approach for decision making, which has been found to be efficient to solve Imazu problems, and other complicated multiple-ship encounters.
... The collision circle zone generator is built up using the fuzzy interference system. Input variables are assigned as the relative bearing (RB) and the historical data from experienced captains [18]. The inferred results of ζ and p are shown as Figures 10 and 11, respectively. ...
In this investigation, a smart collision avoidance control design, which integrates a collision avoidance navigation and a nonlinear optimal control method, is developed for unmanned surface vessels (USVs) under randomly incoming ships and fixed obstacle encounter situations. For achieving collision avoidance navigation, a fuzzy collision risk indicator and a fuzzy collision avoidance acting timing indicator are developed. These two risk indicators can offer effective pre-alarms for making the controlled USVs to perform dodge actions in time when obstacles appear. As to nonlinear optimal control law, it provides a precise trajectory tracking ability for the controlled USVs to follow a collision avoidance trajectory, which is generated via a smart collision avoidance trajectory generator. Finally, a power allocation method is used to transform the desired control law into available actuator outputs to guide the USVs to follow a desired collision avoidance trajectory. From simulation results, the proposed collision avoidance strategy reveals a promising collision avoidance performance and an accurate trajectory tracking ability with respect to fixed objects and randomly moving ships under the effect of environmental ocean disturbances.
... Naeem et al. [22] and Tam and Bucknall [23] used pre-set course change method, while Fang et al. [24] proposed to enlarge rudder angle until trajectory is collision-free. Praczyk [25] mentioned Neural Network (NN) as a suggestion tool for rule-complaint actions, while Perera et al. [26] suggested Bayesian network for the same. The main advantage of this rule-based method is the COLREGs rules, and good seamanship can be treated in the rule system explicitly. ...
As the number of ships for marine transportation increases with the advancement of global trade, encountering multiple ships in marine traffic becomes common. This situation raises the risk of collision of the ships; hence this paper proposes a novel Fuzzy-logic based intelligent conflict detection and resolution algorithm, where the collision courses and possible avoiding actions are analyzed by considering ship motion dynamics and the input and output fuzzy membership functions are derived. As a conflict detection module, the Collision Risk (CR) is measured for each ship by using a scaled nondimensional Distance to the Closest Point of Approach (DCPA) and Time to the Closest Point of Approach (TCPA) as inputs. Afterwards, the decisions for collision avoidance are made based on the calculated CR, encountering angle and relative angle of each ship measured from others. In this regard, the rules for the Fuzzy interface system are defined in accordance with the COLREGs, and the whole system is implemented on the MATLAB Simulink platform. In addition, to deal with the multiple ship encounters, the paper proposes a unique maximum-course and minimum-speed change approach for decision making, which has been found to be efficient to solve Imazu problems, and other complicated multiple-ship encounters.
... In recent years, some existing navigation rules have been used to find a rule-compliant collision-free solution; for example [14,[27][28][29][30][31]. Often, these methods have poor performance in congested waters and do not accurately take the vessel dynamics into account. ...
Autonomous marine vessels are expected to avoid inter-vessel collisions and comply with the international regulations for safe voyages. This paper presents a stepwise path planning method using stream functions. The dynamic flow of fluids is used as a guidance model, where the collision avoidance in static environments is achieved by applying the circular theorem in the sink flow. We extend this method to dynamic environments by adding vortex flows in the flow field. The stream function is recursively updated to enable on the fly waypoint decisions. The vessel avoids collisions and also complies with several rules of the Convention on the International Regulations for Preventing Collisions at Sea. The method is conceptually and computationally simple and convenient to tune, and yet versatile to handle complex and dense marine traffic with multiple dynamic obstacles. The ship dynamics are taken into account, by using Bezier curves to generate a sufficiently smooth path with feasible curvature. Numerical simulations are conducted to verify the proposed method.
... While initial efforts have focused on guidance and control of the vessels (Moreira et al. 2007;Hinostroza et al. 2019), as well as appropriate autonomous systems for collision avoidance (Perera et al. 2015;Zhang et al. 2015), other aspects such as the economy (Kretschmann et al. 2017;Santos and Guedes Soares, 2018) and safety (Zhang et al. 2016;Wu et al. 2020) are also of concern. It is generally accepted that the transition to autonomous shipping has to be done gradually starting with coastal and inland transportation and with intelligent (Perera et al. 2012) and remotecontrolled ships, before moving to fully autonomous oceangoing ships As part of the above-referred effort, a project targeting a 64 TEU inland container vessel in China is under development to transport goods and containers with trends of intelligent, remote, or autonomous control. This paper focuses on the hydrodynamic study of the vessel to ensure appropriate propulsion power installation in the vessel to ensure smooth operations with minimum environmental impact. ...
The paper presents simulation results of an inland container vessel designed to be operated in the inland waters of China. Initially, calm water simulations are performed in open water with varying draft and speed to determine the possible propulsion power required by the vessel for regular operations. Next, static drift simulations are performed with a heave and pitch-free motion at varying drift angles and drafts. Encountered hull resistance and linear derivatives are determined from the drift results to assess the vessel's maneuvering capabilities. Finally, simulations are performed in restricted water following possible operating channel geometry to assess the vessel's performance in restricted operating conditions. The required propulsion power of the vessel has been calculated for each case and compared. Cases that showed maximum resistance was re-stimulated in full scale to discard the scaling effect from predictions. The results show that a significant increase in resistance is observed when the vessel operates in shallow and narrow channels, which limits its possible operating speed. The study concludes that model-scale simulations are efficient for preliminary studies. However, for the required power prediction, full-scale simulations should be considered.
... Today, with the rapid progress of technology development in autonomous driving, collision avoidance techniques of ships at sea have been promoted significantly. Numerous studies used different kinds of path planning algorithms for ships at sea, such as Evolutionary Algorithms [1], Fuzzy Logic [2]- [4], A* Algorithm [5] , the Fast Marching Method [6], Ant Colony algorithm method [7], Artificial Potential Fields(APF) [8], and Velocity Obstacles [9]- [10]. Most of these approaches can be categorized into two kinds, including deterministic approaches and heuristic approaches. ...
Recent studies have made significant development in path planning for ships. However some studies blindly obey rules of COLREGS (International Regulations for Preventing Collisions at Sea) or only adopt turning to starboard ignoring actual practice, like, turning to port and considering deviation from the planned route when taking actions for collision avoidance. In view of the COLREGS and ordinary seamen practice, this paper proposes collision avoidance actions before encounter situation and collision avoidance actions in an encounter situation. Based on the different stages of the encounter situation, it will add more choices for ships when taking action. To specify different stages of encounter situation clearly and take proper collision avoidance actions, this paper makes a quantitative analysis of three primary encounter situations; velocity obstacles (VO) is employed to find allowed velocity space for own ship (OS); by making further analysis of the relationship among distance at the closest point of approach, bow cross, and COLREGS, the method gives a clear direction for OS to search the best velocity in allowed velocity space for three primary encounter situations; VO utility function is applied to search specific value of the best velocity and is useful for different encounter situations. Simulations show that the results are effective and deterministic for collision avoidance. This method not only prevents blindly obeying rules of COLREGS but also promotes reducing deviation from the planned route.
... However, uses of rule-based Bayesian reasoning in collision-related areas are new, few collision models from generic views can be found in previous studies (e.g. [35,44]) and fewer on the analysis the single ship collision from the geometric point of view. ...
Increasing human installations and vessel traffic in offshore waters render a collision risk between ships and offshore installations (SOI). Past decades have witnessed many accidents occurred in the offshore waters involving complex traffic networks. To safeguard offshore installations and improve water-bound transport safety, this paper proposes a novel Bayesian-based model to assess the SOI collision risk involving passing ships. It first identifies the relevant risk factors with the aid of a geometrical analysis concerning SOI collisions. The causal relationships between the risk factors are numerically defined by causal rules with a degree of belief structure, while a Bayesian network (BN) is constructed to aggregate the evaluated value of each risk factor and to assess the collision risks involving different navigational environments. To illustrate the new model, a real case on SOI collision risk in the Liverpool Burbo Bank offshore wind farm is investigated. The results provide empirical evidence for SOI collision risk analysis under complex water conditions and uncertain navigational environments and hence useful insights on SOI collision avoidance.
... Based on these parameters, the model decided on the need to change course or speed based on COLREG rules 13, 14, and 15. In the following article [11], they tried to solve the problem of avoiding multiple vessels by combining fuzzy logic and the graphical probability model-Bayesian networks. Later, fewer input parameters were used to find the appropriate avoidance manoeuvre for the fuzzy inference system: distance to the target vessel, azimuth, relative course, and speed of approach [12]. ...
The application of fuzzy logic is an effective approach to a variety of circumstances, including solutions to maritime anti-collision problems. The article presents an upgrade of the radar navigation system, in particular, its collision avoidance planning tool, using a decision model that combines dynamic parameters into one decision—the collision avoidance course. In this paper, a multi-parametric decision model based on fuzzy logic is proposed. The model calculates course alteration in a collision avoidance situation. First, the model collects input data of the target vessel and assesses the collision risk. Using time delay, four parameters are calculated for further processing as input variables for a fuzzy inference system. Then, the fuzzy logic method is used to calculate the course alteration, which considers the vessel’s safety domain and International Regulations for Preventing Collisions at Sea (COLREGs). The special feature of the decision model is its tuning with the results of the database of correct solutions obtained with the manual radar plotting method. The validation was carried out with six selected cases simulating encounters with the target vessel in the open sea from different angles and at any visibility. The results of the case studies have shown that the decision model computes well in situations where the own vessel is in a give-way position. In addition, the model provides good results in situations when the target vessel violates COLREG rules. The collision avoidance planning tool can be automated and serve as a basis for further implementation of a model that considers the manoeuvrability of the vessels, weather conditions, and multi-vessel encounter situations.
... often based on artificial intelligence algorithms where e.g. a collision-avoidance option may be implemented (Perera et al., 2012a(Perera et al., , 2012b(Perera et al., , 2013(Perera et al., , 2014. ...
... There are several models for evaluating ship collision risks, such as the ship domain model, the fuzzy logic model and the minimum distance to collision (MDTC) model that considers maneuverability [11,23,24]. With the introduction of COLREGs and the development of ship collision risk models, intelligent optimization methods have been investigated to achieve realtime and reliable ship collision avoidance [25], such as neural networks [26], fuzzy mathematics [27] and reinforcement learning [28]. Meanwhile, fuzzy mathematics can also be applied to fuzzy collision risk classification and fuzzy inference [29][30][31]. ...
Most maritime accidents are caused by human errors or failures. Providing early warning and decision support to the officer on watch (OOW) is one of the primary issues to reduce such errors and failures. In this paper, a quantitative real-time multi-ship collision risk analysis and collision avoidance decision-making model is proposed. Firstly, a multi-ship real-time collision risk analysis system was established under the overall requirements of the International Code for Collision Avoidance at Sea (COLREGs) and good seamanship, based on five collision risk influencing factors. Then, the fuzzy logic method is used to calculate the collision risk and analyze these elements in real time. Finally, decisions on changing course or changing speed are made to avoid collision. The results of collision avoidance decisions made at different collision risk thresholds are compared in a series of simulations. The results reflect that the multi-ship collision avoidance decision problem can be well-resolved using the proposed multi-ship collision risk evaluation method. In particular, the model can also make correct decisions when the collision risk thresholds of ships in the same scenario are different. The model can provide a good collision risk warning and decision support for the OOW in real-time mode.
... The primary objective of this concept was to boost the level of maritime safety. This enhancement could be achieved inter alia by utilizing navigational DSSs (Gil et al., 2020b;Perera et al., 2015Perera et al., , 2012Weintrit, 2013), especially for collision avoidance (Baldauf et al., 2014;Baldauf and Hong, 2016). Nevertheless, despite the progressive development of technological solutions implemented on merchant ships, a collision still remains one of the most common reasons for maritime disasters. ...
This paper introduces the concept of Collision Avoidance Dynamic Critical Area (CADCA) for onboard Decision Support Systems (DSS). The indicator proposed is derived via identification of a minimum required maneuvering zone in an encounter between two vessels. The CADCA model accounts for ship maneuvering dynamics and associated hydrodynamic actions emerging from different rudder angles and forward speed effects. The method presented is novel as it considers the variability of a critical area due to dynamic changes in operational parameters for both vessels. Results of the simulations carried out in negligible weather conditions confirm that computed zones may differ significantly in terms of shapes and limits. It is demonstrated that the size of the CADCA depends on the rudder angle, forward speed, as well as the dimensions of the vessels.
... CPA, including the time to the CPA (TCPA) and distance to the CPA (DCPA), is a well-used method with a clear principle and simple calculation in ship collision risk assessment. Perera et al. [9] presented a fuzzy logic CA decision support system for two ships encounter situation based on CPA, and then developed it into a collision risk detection and quantification system in [10]. These methods based on CPA can be used as a good measure of risk, but hard to be used to reveal the evolution mechanism and internal logic of ship collision accident. ...
A ship collision accident is one of the most dangerous and common types of maritime accidents. Traditional probabilistic risk assessment (PRA) of ship collision accidents is a methodology that can be adopted to ensure maritime safety. Nevertheless, a need for better approaches to model human behavior, such as risk identification, communication, and decision-making, has been identified. Such advanced PRA methods require a more explicit way of taking human factors into consideration than the traditional risk assessment methods. Hybrid causal logic (HCL) is an advanced PRA method due to its unique three-level framework that includes event sequence diagrams, fault trees, and Bayesian networks, which makes it suitable for modeling human behavior that is important to ship collision accidents. This paper discusses the applicability of the HCL methodology for the ship collision accident. Firstly, the event sequences of typical ship collision accidents are summarized based on the study of 50 accident investigation reports. Then, fault trees for mechanical failure events and the Bayesian networks for human error events are constructed to analyze the events in a structured way at a more detailed level. Finally, the three main end-state types of ship collision avoidance scenario have been quantified. The result of the probability of a ship collision accident is verified by estimating the annual frequency of collision accidents in the Singapore Strait. Comparing with the historical data, the estimation results are quite near to the real case. By taking advantage of the HCL methodology, the modeling of ship collision scenarios can be carried out at a deep logical level. At the same time, it is possible to combine a detailed analysis of various primary events with a comprehensive analysis at the system level.
... Further, an understanding about autonomous ship navigation for collision avoidance was provided by Statheros [4]. To solve the automatic collision avoidance problem, Perera's studies [5]- [7] are more systematic and prominent. The main research ideas are based on fuzzy theory, supplemented by expert systems, Bayesian networks and parallel decision-making methods that achieve a series of ingenuity. ...
Numerous researches have been done to develop ASV (Autonomous Surface Vessel) collision avoidance systems. Most of the systems used static methods but did not apply a knowledge base where solutions can be reused and adapted to solve a new case. In this paper, an algorithm of autonomous collision avoidance is proposed considering steering dynamic for ASV. The process of this learning method is to recall the FCBR (Fuzzy Case Base Reasoning) containing basic expert knowledge in the form of stored cases. The solutions will be retrieved from the knowledge base to find a NH (New Heading) command for collision avoidance. Moreover, to execute the NH, a design of adaptive fuzzy ASV heading control system based on command filter is conducted considering the input saturation constraints and external disturbances. T-S fuzzy logic is employed to approximate nonlinear uncertainties existing in the heading control system adopting the MLP (Minimal Learning Parameter) technique. Finally, simulations prove that the method is effective to retrieve the past similar cases for the new collision avoidance situation and give its solution for ASV to track adjusted heading.
... To develop a USV control algorithm, it is necessary to formalize the parameters and rules. The best formalized model of the vehicle was proposed by the authors [17]. Their fuzzy model consists of 4 premises, 2 consequences and 200 rules. ...
... (2) Consideration of the ship maneuverability and collision risk model: Compared with existing optimization methods (e.g., neutral networks (Simsir et al., 2014), fuzzy mathematics (Perera et al., 2012) and swarm intelligence (Liu et al., 2017), the proposed method considers ship maneuverability and collision risk model comprehensively and reduces the feedback delay by collision risk prediction. ...
Real-time collision avoidance with full consideration of ship maneuverability, collision risks and International Regulations for Preventing Collisions at Sea (COLREGs) is difficult in multi-ship encounters. To deal with this problem, a novel method is proposed based on model predictive control (MPC), an improved Q-learning beetle swarm antenna search (I-Q-BSAS) algorithm and neural networks. The main idea of this method is to use a neural network to approximate an inverse model based on decisions made with MPC for collision avoidance.
Firstly, the predictive collision avoidance strategy is established following the MPC concept incorporating an IQ-BSAS algorithm to solve the optimization problem. Meanwhile, the relative collision motion states in typical encounters are collected for training an inverse neural network model, which is used as an approximated optimal policy of MPC. Moreover, to deal with uncertain dynamics, the obtained policy is reinforced by longterm retraining based on an aggregation of on-policy and off-policy data. Ship collision avoidance in multi-ship encounters can be achieved by weighting the outputs of the neural network model with respect to different target ships. Simulation experiments under several typical and multi-ship encounters are carried out using the KVLCC2 ship model to verify the effectiveness of the proposed method.
A growing interest in developing autonomous surface vehicles (ASVs) has been witnessed during the past two decades, including COLREGs-compliant navigation to ensure safe autonomy of ASVs operating in complex waterways. This paper reviews the recent progress in COLREGs-compliant navigation of ASVs from traditional to learning-based approaches. It features a holistic viewpoint of ASV safe navigation, namely from collision detection to decision making and then to path replanning. The existing methods in all these three stages are classified according to various criteria. An in-time overview of the recently-developed learning-based methods in motion prediction and path replanning is provided, with a discussion on ASV navigation scenarios and tasks where learning-based methods may be needed. Finally, more general challenges and future directions of ASV navigation are highlighted.
Efficient identification of multi-ship encounter situation concerning action priority analysis is of vital significance for making effective and practical collision avoidance manoeuvres. However, action priority analysis is strongly involved in conflict urgency quantification, collision candidates relevance analysis as well as the contribution analysis within the encountering ships. In this paper, considering Maritime Autonomous Surface Ship, a deterministic collision avoidance decision-making system is established to estimate multi-MASS encounter situation. To this end, the approach index and asymmetrical Gaussian fitting method are deployed to assess collision risk, while the encountering ships are analytically distinguished into different clusters based on the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. By virtue of the improved Sharpley value method, the collision avoidance action priority is elaboratively sorted for different clusters. Accordingly, each individual collision avoidance manoeuvres are collaboratively generated by the modified velocity obstacle algorithm with certain time delay. Eventually, the proposed decision-making system is synthesized by functional modules including data-processing, conflict assessment detection, relevance analysis, action priority analysis, path planning and performance monitor. Simulation results demonstrate that this proposed decision-making system can perform significant superiority in various maritime environment in line with the practice of coordination and navigation.
In order to realize the autonomous collision avoidance of unmanned surface vehicles (USVs), an intelligent hybrid collision avoidance algorithm based on deep reinforcement learning is proposed. First, the navigation situation model of the USV is designed, the geometric model of the encounter between two ships is established based on navigation practice. According to static and dynamic obstacles, hybrid risk assessment and collision avoidance model are proposed, the risk factor is calculated. Then, for static obstacles, the collision cone is introduced, for dynamic ships, the COLREGS is observed, the encounter situation is quantified into five types. Collision avoidance strategy is formulated. Finally, the state, action, reward function and network structure are designed. Aiming at the problem of low utilization for samples in random sampling, this paper improves the original sampling mechanism of DDPG, and the priority sampling mechanism with cumulative pruning is proposed in this paper. Simulation experiments are carried out in several typical encounter scenarios. The results show that this algorithm can accurately judge the encounter situation, give reasonable collision avoidance actions, and realize effective collision avoidance in a complex environment with dynamic and static obstacles. The research can provide theoretical basis and method reference for autonomous navigation of USVs.
Dynamic collision avoidance between multiple vessels is a task full of challenges for unmanned surface vehicle (USV) movement, which has high requirements on real-time performance and safety. The difficulty of multi-obstacle collision avoidance is that it is hard to formulate the optimal obstacle avoidance strategy when encountering more than one obstacle threat at the same time; a good strategy to avoid one obstacle sometimes leads to threats from other obstacles. This paper presents a dynamic collision avoidance algorithm for USVs based on rolling obstacle classification and fuzzy rules. Firstly, potential collision probabilities between a USV and obstacles are calculated based on the time to the closest point of approach (TCPA). All obstacles are given different priorities based on potential collision probability, and the most urgent and secondary urgent ones will then be dynamically determined. Based on the velocity obstacle algorithm, four possible actions are defined to determine the basic domain in the collision avoidance strategy. After that, the Safety of Avoidance Strategy and Feasibility of Strategy Adjustment are calculated to determine the additional domain based on fuzzy rules. Fuzzy rules are used here to comprehensively consider the situation composed of multiple motion obstacles and the USV. Within the limited range of the basic domain and the additional domain, the optimal collision avoidance parameters of the USV can be calculated by the particle swarm optimization (PSO) algorithm. The PSO algorithm utilizes both the characteristic of pursuance for the population optimal and the characteristic of exploration for the individual optimal to avoid falling into the local optimal solution. Finally, numerical simulations are performed to certify the validity of the proposed method in complex traffic scenarios. The results illustrated that the proposed method could provide efficient collision avoidance actions.
The multi-ship encounter situation at sea is characterized by high complexity and uncertainty, which is a big challenge for both traditional ships and the new autonomous ships. In order to make reasonable navigation decisions and perform well under multi-ship encounter situation, it is necessary to grasp the current scenario correctly and intelligently. Therefore, in this paper, an adaptive understanding model for multi-ship encounter situation is proposed. The core function of this model is to infer the navigation intention of other target ships under the same situation. This model is mainly composed of two sub-models. One is the ship encounter situation analysis model, which realizes the cognition of the whole encounter scenario from the global perspective by maintaining the “double matrix”. The second is the ship navigation intention inference model, the key part of the model is a set of well-designed fuzzy inference system. The output of the encounter situation analysis model is the input of the intention inference model, and these two models are closely linked to form a unified whole. This model is verified by both simulation-based and real scenario-based experiments, the results show that this model can perform well under the complex multi-ship encounter situation. Moreover, some necessary discussion and analysis for this inference model are also stated at the end of this paper, in the future, we expect that this model can be applied in real situations.
This article presents a reasonable anti-collision path planning algorithm with the properties of strong practicability and high degree of automation for unmanned surface vehicles (USV) or Marine Autonomous Surface Ships (MASS) in dynamic environment situation. Based on the requirements of the International Regulations for Preventing Collisions at Sea (COLREGs), the qualitative provision about the apparent intention of anti-collision maneuver is quantified in the algorithm. Meanwhile, the Boolean expression technology is adopted to help determine the type of encounter situation and action manner automatically, which provides theoretical basis for the application of path-planning algorithm. In addition, the modified velocity obstacle approach and artificial potential fields are combined to improve the practicality and rationality of the optimization solution. Finally, simulation examples consisting different traffic scenarios are discussed to demonstrate the effectiveness and practicality of the proposed scheme.
The vessel handling times at container terminals can be inevitably affected by weather conditions. This study proposes a berth allocation problem (BAP) with vessel handling time uncertainty considering the impact of weather conditions, which is seldom considered in the previous studies on BAPs. A two-stage optimization method, which focuses on the evaluation of vessel handling time under different weather conditions, is developed for addressing our BAP. In stage I, we determine the vessel handling times considering the influence of weather conditions. Based on the vessel handling times obtained in stage I, stage II presents a mixed-integer programming (MIP) model for solving the BAP. Moreover, an efficient particle swarm optimization algorithm embedded with machine learning approach is devised for solving the BAP model in large-scale problem cases. Numerical experiments are carried out to assess the effectiveness of the proposed model and the efficiency of the proposed algorithm.
Purpose: To develop an algorithm of automatic abnormal situation recognition for autonomous vehicles using the deep learning methods and test it in the virtual simulation environment of World ship simulator and Ship Simulator Extremes. Design/methodology/approach: The authors use deep neural networks and classical methods of image processing as a pattern recognition algorithm. A fuzzy logic apparatus based on the International Regulations for Preventing Collisions at Sea (COLREG) is used to generate the control actions. The efficiency evaluation of the recognition algorithms is carried out using the universally accepted metrics: Accuracy, Recall, Precision, AUC. Findings: Application of the efficient (in terms of speed) neural network architecture based on the GhostNet models for computing on embedded devices is proposed. The suggested approach allows achieving up to 97% classification results in real-time mode. Simulation results using the Python language are presented. Simulation of the developed algorithms based on graphic simulation in a virtual gaming environment has been carried out. Originality/value: A characteristic feature of the proposed approach is a combined use of fuzzy logic and computer vision systems based on the deep learning algorithms to create an intelligent software and hardware complex for controlling an unmanned vessel in difficult sea conditions.
We propose a method for scenario-based testing of maritime collision avoidance systems. The goal is to test an autonomous agent in scenarios that can lead to an unacceptable risk of collision or may clearly not comply with the International Regulations for Preventing Collisions at Sea (COLREGs).Our method is based on the use of a discriminating artificial neural network that is trained online while performing the testing of the agents. Our experimental results show that the proposed algorithm generates test suits composed mostly of challenging scenarios. This allows us to validate quickly if the agent under test can perform the collision avoidance maneuvers safely while abiding the COLREGs.
This paper presents a multiobjective optimisation approach for path planning of autonomous surface vehicles (ASVs). A unique feature of the technique is the unification of the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) with good seamanship's practice alongwith hierarchical (rather than simultaneous) inclusion of objectives. The requirements of collision avoidance are formulated as mathematical inequalities and constraints in the optimisation framework and thus collision-free manoeuvres and COLREGs-compliant behaviours are provided in a seafarer-like way. Specific expert knowledge is also taken into account when designing the multiobjective optimisation algorithm. For example, good seamanship reveals that if allowed, an evasive manoeuvre with course changes is always preferred over one with speed changes in practical maritime navigation. As a result, a hierarchical sorting rule is designed to prioritize the objective of course/speed change preference over other objectives such as path length and path smoothness, and then incorporated into a specific evolutionary algorithm called hierarchical multiobjective particle swarm optimisation (H-MOPSO) algorithm. The H-MOPSO algorithm solves the real-time path planning problem through finding solutions of the formulated optimisation problem. The effectiveness of the proposed H-MOPSO algorithm is demonstrated through both desktop and high-fidelity networked bridge simulations.
The chapter presents two main streams of research in vessel control at sea: dynamic positioning (DP)Dynamic positioning of the vessel and decision support in case of collision at sea. The control structure and basic requirements for the DP system are defined. Selected issues of automatic control of a dynamically positioned vessel are discussed. A review of advanced methods of controlling a DP ship is carried out, taking into account the tasks of particular subsystems. In the scope of decision support, the issue of collision avoidanceCollision avoidance at sea is discussed. This problem is defined as a dynamic multi-criteria optimizationMulti-criteria optimisation task which consists in looking for effective solutions that meet specific criteria within a set of acceptable solutions. To solve this problem, the evolutionary method of path planning is used.
Maritime transport faces new safety-related challenges resulting from constantly increasing traffic density, along with increasing dimensions of ships. Consequently, the number of new concepts related to Decision Support Systems (DSSs) supporting safe shipborne operations in the presence of reduced ship manning is rapidly growing, both in academia and industry. However, there is a lack of a systematic description of the state-of-the-art in this field. Moreover, there is no comprehensive overview of the level of technology readiness of proposed concepts. Therefore, this paper presents an analysis aiming at (1) increasing the understanding of the structure and contents of the academic field concerned with this topic; (2) determining and mapping scientific networks in this domain; (3) analyzing and visualizing Technology Readiness Level (TRL) of analyzed systems. Bibliometric methods are utilized to depict the domain of onboard DSSs for operations focused on safety ensurance and accident prevention. The scientific literature is reviewed in a systematic way using a comparative analysis of existing tools. The results indicate that there are relatively many developments in selected DSS categories, such as collision avoidance and ship routing. However, even in these categories some issues and gaps still remain, so further improvements are needed. The analysis indicates a relatively low level of technology readiness of tools and concepts presented in academic literature. This signifies a need to move beyond the conceptual stages toward demonstration and validation in realistic, operating environments.
Collision risk assessment is essential for supporting collision avoidance, which is the core of various collision alert/avoidance systems. One main task of the systems is setting off alarms for taking evasive actions. The alarms need to be triggered before the conflict has no collision-free solution. However, most of existing collision risk measures are independent of conflict resolution. That means the collision alert does not indicate that the collision is avoidable or not. This article proposes an improved time-varying collision risk (TCR) measure, bringing in a new measure. The measurement of TCR reflects not only the dangerous level of the approaching ships but also the difficulty of avoiding collisions. By comparing with traditional measures, e.g., Collision Risk Index (CRI), we found that (1) the TCR can distinguish changes of risk that have identical CRI level, (2) the TCR measure offers a reasonable tool to evaluate the collision risk of entire traffic, and (3) it reflects the influence of maneuverability improvement on collision risk. Based on those results, this article reaches two conclusions: the collision risk is monotonically increasing when introducing more ships, and ignorance of ship maneuverability results in an underestimation of collision risk.
This paper proposes a topological analysis model of ship encounter space using a geographic information system (GIS) spatial analysis technology. Herein, the characteristics of the elements, organization, and structure of the ship encountered in the sea were studied to solve problems of ship collision risk analysis. In this model, it is necessary to construct the topological structure of the ship-encounter space based on the risk situation of the ship. The topological points and connection lines established in the encounter space were analyzed using the shape and geometric relationship of the ship's space topology, and the collision danger in the ship's navigation is, thus, analyzed. Moreover, information regarding the dangerous ship target and encounter characteristics were calculated and extracted. This study uses the model to conduct a simulation based on data from the collision between M/T Sanchi and M/V CF Crystal on January 06, 2018, and analyzes the collision risk characteristics during the two periods prior to the collision. Results show that the proposed model is effective and feasible for marine vessel safety analysis.
This study proposes a multi-ship collision avoidance and route generating algorithm based on the general requirements of the International Regulations for Preventing Collisions at Sea (COLREGs) and the artificial potential field (APF) method. The velocity potential field is used as the field function of APF method. The algorithm consists of two modes, the course-changing and the track-keeping modes based on the velocity potential of vortex and dipole, respectively. The course-changing mode guides the ship to turn away from the obstacles according to the vector field of vortex potential. The track-keeping mode steers the ship back to and along on a pre-designed track in accordance with the vector field of dipole potential. The data of distance to the closest point of approach (DCPA), time to the closest point of approach (TCPA) and bearing angle evaluated from a maneuvering simulation are the acquired parameters of the proposed collision avoidance algorithm. The algorithm is straightforward and very simple to implement, and is suitable for the real time and distributed intelligent collision avoidance system. Simulation results indicate that the anti-collision formulation can avoid collision safely with the desired distance and indicate that the algorithm proposed can work effectively.
The article presents an attempt to apply an artificial neural network in anti-collision systems at sea. Such systems determine safe trajectory for a ship by, most frequently, processing the information sourced from an automatic radar plotting aids (ARPA) type arrangement. In this research work the use of neural classifier has been proposed as an element supporting a navigator in the process of determining the ship’s domain, i.e., the area around a ship which, for safety reasons, should remain free from navigational obstacles. Neural classifier has a form of a multilayer feed-forward network of a perceptronic nature. It has been assigned a task to represent the evaluation of a navigational situation provided by an experienced navigator functioning as a teacher in the process of the network learning phase. Programs designed in the MATLAB language have been applied for the simulation of the network and also for the illustration of a navigational situation. Testing of the correctness of classification of the collision situations by the network have been also conducted. In the final part of the article conclusions have been formulated with regard to the application of the neural classifier in the process of determining a safe trajectory of a ship.
This paper presents a Recursive Neural Network (RNN) manoeuvring simulation model for surface ships. Inputs to the simulation are the orders of rudder angle and ship’s speed and also the recursive outputs velocities of sway and yaw. This model is used to test the capabilities of artificial neural networks in manoeuvring simulation of ships. Two manoeuvres are simulated: tactical circles and zigzags. The results between both simulations are compared in order to analyse the accuracy of the RNN. The simulations are performed for the Mariner hull. The data generated to train the network are obtained from a manoeuvrability model performing the simulation of different manoeuvring tests. The RNN proved to be a robust and accurate tool for manoeuvring simulation.
This paper proposes a methodology to overcome failures on Mamdani rule based fuzzy inferences in navigation. The fuzzy inference failures are observed in three situations: Intersected contradictory decision boundaries, improper transition region between the inference boundaries of non-intersected contradictory decisions and contradictory decision accumulation. In order to solve the problems, it is proposed to insert a smooth transition region between intersected contradictory decision inference boundaries, to determine the size limitations between non-intersected contradictory decisions inference regions, and finally to integrate a "multi-level" process. The proposed solutions are applied to a decision making process of ocean navigation and successful simulation results are shown in this study.
In this paper the stochastic parameters describing the nonlinear ocean vessel steering model are identified, resorting to an Extended Kalman Filter. The proposed method is applied to a second order modified Nomoto model for the vessel navigation that is derived from first physics principles. The results obtained resorting to a realistic numerical simulator for the nonlinear vessel steering model considered are illustrated in this study.
Maneuvering vessel detection and tracking in cooperation with vessel state estimation and navigational trajectory prediction are important tasks for the Vessel Traffic Monitoring and Information Systems (VTMIS) to improve maritime safety and security in ocean navigation. In this study, collaborated and constrained Neural-EKF algorithm is proposed for the above purpose. The proposed methodology consists of two main units: an Artificial Neural Network based Vessel Detection and Tracking Unit and an Extended Kalman Filter based State Estimation and Trajectory Prediction Unit. Finally, the proposed algorithm, is implemented on the MATLAB software platform, and successfully illustrate the results attainable in respect to vessel detection and tracking, vessel state estimation and navigational trajectory prediction in ocean navigation is also presented in this study.
This paper focuses on a study of the sequential action execution module for a collision avoidance system in ocean navigation. The overall decision-action process of collision avoidance consists on a Fuzzy logic based parallel decision making module and those decisions are formulated into collision avoidance actions by a Bayesian network based sequential action execution module. The presented collision avoidance system is capable of making multiple sequential actions to avoid complicated collision situations involving multiple vessels in ocean navigation while still respecting the COLREGs rules and regulations.
This paper focuses on a Fuzzy-logic based parallel decision formulation that aims to improve the safety of marine vessels by avoiding collision situations in ocean navigation. The collision avoidance of the Target vessel with respect to the vessel domain of the Own vessel has been analyzed and input and output Fuzzy Membership Functions are derived in this study. The If-Then rule based decision making process and the integrated novel Fuzzy Inference System are formulated and implemented on MATLAB software platform. Simulations are presented regarding several collision avoidance situations. Furthermore, the decision rules are formulated in accordance with the International Maritime Organization Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) and expert knowledge in navigation, to avoid conflict that might occur during the ocean navigation.
This paper proposes a method to overcome the failures on a fuzzy logic based Decision Making (DM) process applied to collision avoidance in ocean navigation when contradictory decisions result from the inference on boundaries of the represented fuzzy membership functions. The method consists in the insertion of a smooth transition region. Further a decision making process of ocean navigation is analyzed, input and output Fuzzy Membership Functions are derived, If-Then rule based Fuzzy Inference System (FIS) are formulated and simulation results are presented regarding several intercepted decision boundary regions.
Autonomous Guidance and Navigation (AGN) is meant to be an important part of the future
ocean navigation due to the associated navigational cost reduction and maritime safety. Furthermore intelligent decision making capabilities should be an integrated part of the future AGN system in order to improve autonomous ocean navigational facilities. This paper is focused on an overview of the AGN systems with respect to the collision avoidance in ocean navigation. In addition, a case study of a fuzzy logic based decision making process accordance with the International Maritime Organization (IMO) Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) has been illustrated.
This study provides both a spherical understanding about autonomous ship navigation for collision avoidance (CA) and a theoretical background of the reviewed work. Additionally, the human cognitive abilities and the collision avoidance regulations (COLREGs) for ship navigation are examined together with water based collision avoidance algorithms. The requirements for autonomous ship navigation are addressed in conjunction with the factors influencing ship collision avoidance. Humans are able to appreciate these factors and also perform ship navigation at a satisfactory level, but their critical decisions are highly subjective and can lead to error and potentially, to ship collision. The research for autonomous ship navigation may be grouped into the classical and soft computing based categories. Classical techniques are based on mathematical models and algorithms while soft-computing techniques are based on Artificial Intelligence (AI). The areas of AI for autonomous ship collision avoidance are examined in this paper are evolutionary algorithms, fuzzy logic, expert systems, and neural networks (NN), as well as a combination of them (hybrid system).
An autonomous navigation algorithm for marine vehicles is proposed in this paper us-ing fuzzy logic under COLREG guidelines. The VFF (Virtual Force Field) method, which is widely used in the field of mobile robotics, is modified for application to the autonomous navi-gation of marine vehicles. This Modified Virtual Force Field (MVFF) method can be used in ei-ther track-keeping or collision avoidance modes. Moreover, the operator can select a track-keeping pattern mode in the proposed algorithm. The collision avoidance algorithm has the abil-ity to handle static and/or moving obstacles. The fuzzy expert rules are designed deliberately un-der COLREG guidelines. An extensive simulation study is used to verify the proposed method.
This paper is concerned with the in-field autonomous operation of unmanned marine vehicles in accordance with convention for safe and proper collision avoidance as prescribed by the coast guard collision regulations (COLREGS). These rules are written to train and guide safe human operation of marine vehicles and are heavily dependent on human common sense in determining rule applicability as well as rule execution, especially when multiple rules apply simultaneously. To capture the flexibility exploited by humans, this work applies a novel method of multi-objective optimization, interval programming, in a behavior-based control framework for representing the navigation rules, as well as task behaviors, in a way that achieves simultaneous optimal satisfaction. We present experimental validation of this approach using multiple autonomous surface craft. This work represents the first in-field demonstration of multiobjective optimization applied to autonomous COLREGS-based marine vehicle navigation
To provide a novel intelligent anti-collision decision-making support system it is necessary to facilitate a precise anti-collision information capability. In the reported research an innovative self-learning neurofuzzy network is proposed and applied to learn new information adaptively without forgetting old knowledge. To handle imprecise information a fuzzy set interpretation facility is incorporated into the network design. Additionally neural network architecture is used to train the parameters of the fuzzy inference system (FIS). The learning process is based on a hybrid learning algorithm and off-line training data. The training data is obtained from trial manoeuvres. This support system has been developed to help ship operators make a precise anti-collision decision, whilst simultaneously reducing the burden of bridge data processing.
Marine accidents such as collision, running aground and striking a reef not only bring on personnel casualty, but also make great threat to ocean environment. For making "the safer the vessel sail, the cleaner the ocean is", the problem of vessel automatic anti-collision should be resolved as soon as possible. Automatic generation of intelligent decision-making is one of the key technologies to realize automatic collision avoidance for vessel at sea. How to utilize the present ship- handling simulator's technology to check up the present research production is a valuable research work. The authors firstly described the basic idea of intelligent automatic method for vessel collision avoidance according to its researching actualities. And then discussed the construction of Simulation and Testing Platform for Navigation Safety and Automatic Collision Avoidance(NSACA for short), which was based on the ship's maneuvering mathematic model and Electronic Chart Display and Information System(ECDIS for short), and also dissertated the test method. Finally gave some typical examples from a great deal of simulating tests and analyzed them. The results indicated that this kind of simulating approach possessed the excellence on the flexibility, efficiency, safety and economy compared to the sea test on real ship.
This paper addresses the issue of autonomous control and safe navigation in an unmanned marine vehicle. Primarily it is concerned with the issue of effective collision avoidance. The first part of the paper examines known legal issues regarding autonomous marine vehicles, and the second part addresses how to provide an autonomous COLREGS capability in an autonomous marine vehicle.
This paper presents the results of the research on modelling the variation in human decision making. The relationship between the uncertainty introduced to the membership functions (mfs) of a fuzzy logic system (FLS) and the variation in FLS's decision making is explored using two separate methods. Initially uncertainty is introduced to a type-1 FLS by adding noise to its mfs and the effect on decision making is examined. Secondly an interval type-2 FLS is developed by representing the terms used in the FLS with interval type-2 fuzzy sets and the variation in decision making is studied using the FLS's interval outputs. The variations in ranking of umbilical acid-base assessments by six experts are compared to the simulation results from the developed FLSs. It is shown that there is a direct relationship between the variation in decision making and the uncertainty in the linguistic terms used, and the level of variation is proportional to the magnitude of uncertainty.
Recently, the avoidance from ship collisions becomes a mandatory problem in the viewpoint of maneuvering ships safety in crowded or crossing areas. Today, information for the steering is mainly limited to pilot's eye measurement and radar information.As for radar information, the detecting the course direction or turning of a target vessel urgently and accurately with an accuracy is difficult. Moreover, information on the bigness and the altering course of a target vessel obtained by eye measurement is regarded as seriously important for the avoidance. Then, the authors have studied on the collision avoidance systems that make use of image information instead of eye measurement.In this study, they obtain a method for measuring course of a target vessel and evaluation of the collision risk by the extracted image of target from IR image.As the result of this study;(1) The image of the vessel is extracted from IR image base on the threshold set method by using area information.(2) The course and the length of a target vessel are obtained from the number of the pixels corresponding to horizontal length of the vessel. And the altering course of a target vessel is detected on real time.(3) As for the direction of the prow of the target vessel, it is done from the specified centroid of the vessel image.(4) The amount of the altering course necessary for avoidance is obtained from the meeting condition predicted from radar and the image. And effect is evaluated.It is demonstrated and evaluated that the effective and simultaneous use of radar and the image can improve the performance of collision avoidance.
The moment at which in a two-ship encounter a collision avoidance manoeuvre should be initiated in order to achieve a specific distance at the closest point of approach has been calculated. The calculations were based on the kinematics of encounter and simplified equations of motion. Mathematical equations which relate the maneouvring distance, the turning direction and the extent of course change for any desired passing distance and any given turning rate are determined. Knowledge of these quantities is essential for the safe conduct of the ship with automatic, computer-assisted navigation as well as with ordinary, manual navigation if the navigator no longer contents himself with estimates but wishes to know precisely in advance the outcome of any specific manoeuvre he chooses.
The problem of simulating the ship manoeuvring motion is studied mainly in connection with manoeuvring simulators. Several possible levels of solution to the problem with different degrees of complexity and accuracy are discussed. It is shown that the structure of the generic manoeuvring mathematical model leads naturally to two basic approaches based respectively on dynamic and purely kinematic prediction models. A simplified but fast dynamic manoeuvring model is proposed as well as two new advances in kinematic prediction methods: a prediction based on current values of velocities and accelerations and a method of anticipating the ship's trajectory in a course changing manoeuvre.
Recently, the avoidance of ship collisions is becoming essential from the viewpoint of maneuvering ships safely in crowded or crossing areas. The information needed for safe navigation is currently obtained by combining radar data with information obtained visually. However, misjudgments accompanying visual observations comprise a major cause of ship collisions. For this reason, the authors have been pursuing a study of ship collision-avoidance systems, including the use of radar and infrared imaging. In this study, they have obtained a method for measuring the course of a target vessel, and for the evaluation of the risk of a collision by extracting images of a target ship from an infrared image. As a result of this study, this paper demonstrates and asserts that the effective and simultaneous use of radar and such images can improve performance in terms of collision avoidance.
A comprehensive and extensive study of the latest research in control systems for marine vehicles. Demonstrates how the implementation of mathematical models and modern control theory can reduce fuel consumption and improve reliability and performance. Coverage includes ocean vehicle modeling, environmental disturbances, the dynamics and stability of ships, sensor and navigation systems. Numerous examples and exercises facilitate understanding.
One of the basic tasks in shipping is to ensure safe navigation of vessels. The concept of the ship domain is of major importance in the assessment of a navigational situation and the avoidance of ship collisions. It is difficult to determine a ship domain as its shape and size depend on a number of factors. One question to be answered before the determination of the ship domain is which method to use: statistical, analytic, or expert method using artificial intelligence tools; other questions are connected with domain interpretation. The authors have analyzed the ship domain as a criterion for the assessment of ship navigational safety in an encounter situation in the open sea. The research results are used to answer some of the questions.
Part 2 includes definitions of the ship domain and ship fuzzy domain. Part 3, in turn, presents methods of their determination as well as relevant questions. The results of the authors' research, described in Part 4, make up a basis for the determination of the domain and ship fuzzy domain. These have been determined with the so-called dynamic domains as a point of departure. The criteria of ship domain and closest point of approach are compared and discussed. Encounters of various size ships are considered in Part 5. The research and its results are described. Both ship domains and ship fuzzy domains of encountering ships are analyzed. Then, conclusions have been formulated in relation to the effect of the sizes of encountering ships on the shapes and sizes of their domains. Final conclusions are given in Part 6.
This paper focuses on a fuzzy logic based intelligent decision making system that aims to improve the safety of marine vessels
by avoiding collision situations. It can be implemented in a decision support system of an oceangoing vessel or included in
the process of autonomous ocean navigation. Although Autonomous Guidance and Navigation (AGN) is meant to be an important
part of future ocean navigation due to the associated cost reduction and improved maritime safety, intelligent decision making
capabilities should be an integrated part of the future AGN system in order to improve autonomous ocean navigational facilities.
In this study, the collision avoidance of the Target vessel with respect to the vessel domain of the Own vessel has been analyzed
and input, and output fuzzy membership functions have been derived. The if–then rule based decision making process and the
integrated novel fuzzy inference system are formulated and implemented on the MATLAB software platform. Simulation results
are presented regarding several critical collision conditions where the Target vessel fails to take appropriate actions, as
the “Give way” vessel to avoid collision situations. In these situations, the Own vessel is able to take critical actions
to avoid collisions, even when being the “Stand on” vessel. Furthermore, all decision rules are formulated in accordance with
the International Maritime Organization Convention on the International Regulations for Preventing Collisions at Sea (COLREGs),
1972, to avoid conflicts that might occur during ocean navigation.
KeywordsAutonomous Guidance and Navigation–Collision avoidance–IMO rules and regulations–COLREGs–Fuzzy logic–Intelligent systems–Decision making process–Crash stopping
A learning method by recording cases based on an evaluation system for vessel collision avoidance is presented in this paper. The frame model is selected and defined as the case representation method. The basic structure and several processing modules of the evaluation system are discussed. Data fusion methods are used in the system. During processing of the learning case, fuzzy method is also adopted. And finally, the validity of the evaluation system and the learning method is proved by application instance
The safety of ships oceangoing or navigating in inland waterways has been increasingly concerned because it may cause great losses in human life and property and bring environmental pollution. Ship collision avoidance system is expected to reduce such maritime accident. How to find an optimum trajectory is crucial for the success of a ship collision avoidance system. As the basis of ship collision avoidance system, a mathematical model of ship maneuvering motion is first described. Then, optimization approach based on genetic algorithm is applied to seek the ship trajectory considering different navigational constraint conditions of a ship in inland waterways. In this approach, a fitness function is used to model the constraints including target ship and obstacles. The optimal results show that the present method is efficient and can be further applied to the ship-maneuvering simulator.
Concerns collision avoidance in ship navigation. Ships are usually
equipped with ARPA systems, which process radar information and announce
when other ships are near. An operator is still needed to watch the
situation, make judgements and control the ship. The criteria of
judgement are very complex, leading to misjudgements and mistakes. For a
precise judgement and operation, theoretical criteria are not useful and
a plenty of experience is required, but the captain or officer who has
this ability are decreasing and necessity of automatic collision
avoidance system is increasing. The authors adopt genetic algorithm (GA)
for this. It has wide adaptability with learning function. The collision
avoidance control system is constructed with following functions: 1) Get
the information of other ships from the ARPA system; 2) Decide the
navigating condition with GA 3) Control the ship direction with
autopilot and ship speed with engine control. To confirm the performance
of this system, the authors prepared three steps of experiment: 1) On
board test using the ship Shioji-maru with virtual objects; 2) Real time
simulation test with training simulator of Shioji-maru; 3) On board test
using Shioji-maru with real objects. Basic functioning has been
confirmed and various improvements for practical use are progressing
A review is presented of different approaches to quantify the risk in maritime transportation. The discussion of several accident statistics provides a global assessment of the risk levels and its differentiation in ship types and main types of ship losses. Early studies in the probability of ship loss by foundering and capsizing are reviewed. The approaches used to assess the risk of structural design are addressed. Finally a brief account is given of recent development of using formal safety assessments to support decision making on legislation applicable internationally to maritime transportation.
This paper aims at analysing decisions which are actually made by watch officers onboard ferries in the Dover Strait. More precisely, it aims at characterizing the generic situations in which several courses of actions are available and identifying the strategy underlying an action choice. Relying on the RPD model of Klein [Klein, G. (1997). The recognition-primed decision (RPD) model: Looking back, looking forward. In C. E. Zsambok & G. Klein (Eds.), Naturalistic decision making (pp. 285–292). Mahwah: Lawrence Erlbaum Associates], it points out the critical cues, the goals of actors and the rules they use.Two sets of data were processed: motions of vessels observed from the vessel traffic system and verbal protocols recorded onboard a ferry with three watch officers.Logistic regression models show that different types of ships do not act in the same way: the slowest vessels tend to keep their course and speed, even if they have to move. The faster cargo ships such as ferries alter their course in compliance with the regulations. In some situations, a ferry may nevertheless follow informal rules. Onboard a ‘give way’ ferry, a watch officer may – in some conditions – alter his course to port rather than to starboard to reduce the course alteration and the loss of time. On board the ‘stand on’ vessel, he may perform an action in order to master the situation, even if the rule requires him to keep his course and speed.
A ship has to move from a point A to a point B and has on its way to navigate through a narrow zigzag channel. Using a realistic model of a tanker ship, a method is proposed for computing feasible rudder command strategies for the navigation of the ship.
An analysis of 40 ocean-going commercial vessel accidents is compared with the study of a similar number of high-speed crafts (HSCs) accidents, using in both cases a methodology that highlights the sequence of events leading to the accident and identifies the associated latent or causal factors. The main objective of this study was to identify and understand the difference in the pattern of causal factors associated with HSC accidents, as compared with the more traditional ocean-going ships. From the analysis one can see that the HSC accidents are mainly related to bridge personnel and operations, where the human element is the key factor identified as being responsible for the majority of the accidents. When compared with ocean-going commercial vessels, it is clear that navigational equipment and procedures have a larger preponderance in terms of the occurrence of accidents of HSC and particular attention should be given to these issues.
The long-anticipated revision of this best-selling book offers the most comprehensive, up-to-date introduction to the theory and practice of artificial intelligence. Intelligent Agents. Solving Problems by Searching. Informed Search Methods. Game Playing. Agents that Reason Logically. First-order Logic. Building a Knowledge Base. Inference in First-Order Logic. Logical Reasoning Systems. Practical Planning. Planning and Acting. Uncertainty. Probabilistic Reasoning Systems. Making Simple Decisions. Making Complex Decisions. Learning from Observations. Learning with Neural Networks. Reinforcement Learning. Knowledge in Learning. Agents that Communicate. Practical Communication in English. Perception. Robotics. For those interested in artificial intelligence.