Inland ship formation risk assessment method and system based on multi-source information fusion

Abstract

The invention discloses an inland ship formation risk assessment method and system based on multi-source information fusion. The method comprises the following steps: acquiring surrounding environment information, ship state information and navigation situation information of each ship in a ship formation; the acquired surrounding environment information, ship state information and navigation situation information of each ship in the ship formation are preprocessed; constructing a ship formation risk assessment model for assessing the formation risk of each ship in the ship formation; training the ship formation risk assessment model to obtain a trained ship formation risk assessment model; and inputting the preprocessed surrounding environment information, ship state information and navigation situation information of each ship in the ship formation into the trained ship formation risk assessment model to assess the risk of each ship in the ship formation.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of ship formation, and relates to a risk assessment method and system for inland ship formation based on multi-source information fusion. BACKGROUND

[0002] With the intelligent development of inland shipping and ship control technology, the ship formation navigation mode has significant advantages in improving channel utilization rate, reducing energy consumption, and enhancing transportation efficiency, and has become a new inland transportation mode. However, the inland environment is complex and changeable, such as narrow and curved channels, variable hydrology and meteorology, and many bridge obstacles, and the formation navigation involves multi-ship cooperation, so the risk is much higher than single-ship navigation. The ship formation is different from the traditional inland ship, and the formation is composed of a leading ship and multiple following ships, which relies on a single or small number of information sources, and it is difficult to comprehensively and real-time obtain multi-dimensional dynamic information affecting the formation safety. The traditional system mainly alarms based on preset thresholds or simple rules, lacks fusion and intelligent analysis of multi-source heterogeneous information, and is difficult to identify potential complex risks in time. In addition, in addition to evaluating and identifying explicit risks such as collision and grounding, key risks such as formation shape stability, communication link reliability, and cooperative control robustness also need to be considered. The risk information sharing and cooperative handling mechanism among the shore-based center, the leading ship and the following ship is not perfect, and it is difficult to provide timely and consistent optimized risk avoidance strategies for the formation as a whole and individual ships. Therefore, an intelligent system and method capable of fusing multi-source information, real-time and dynamic evaluating the comprehensive risk of the formation, and effectively supporting cooperative decision-making is urgently needed. SUMMARY

[0003] To solve the above problems, the technical scheme adopted by the application is: a risk assessment method for inland ship formation based on multi-source information fusion, comprising the following steps:

[0004] Obtain the surrounding environment information, ship state information and navigation situation information of each ship in the ship formation;

[0005] Preprocess the obtained surrounding environment information, ship state information and navigation situation information of each ship in the ship formation;

[0006] Construct a ship formation risk assessment model for evaluating the formation risk of each ship in the ship formation;

[0007] Train the ship formation risk assessment model to obtain a trained ship formation risk assessment model;

[0008] Input the preprocessed surrounding environment information, ship state information and navigation situation information of each ship in the ship formation into the trained ship formation risk assessment model to evaluate the risk of each ship in the ship formation.

[0009] The environmental information includes real-time hydro-meteorological information, channel information, and traffic situation.

[0010] The ship state information includes the position, heading, speed, bow direction, main engine / steering engine working condition, key equipment state information of the ship in the formation, and real-time water depth and wind speed and direction of the surrounding environment, relative position, safety distance, formation speed, and inter-ship communication quality of the formation.

[0011] The navigation situation information includes the meeting situation between ships, traffic flow density, and the state of special water areas containing bridges and intersection areas.

[0012] Further, the ship formation risk assessment model comprises:

[0013] A fusion module for fusing the data of the position sources of multiple ships to obtain more accurate self and following ship state data information;

[0014] A feature extraction module for extracting target features based on the self and following ship state data information transmitted by the fusion module, and further extracting risk features from the environmental data;

[0015] A fuzzy comprehensive evaluation model module for fuzzifying the risk features extracted from the feature extraction module, inferring using a rule base, obtaining fuzzy evaluation results of collision, grounding, loss of control, and formation stability risk, obtaining risk values in each dimension, calculating the individual risk value of the ship and the overall comprehensive risk value of the formation by a preset weight, and dividing the risk level.

[0016] Further, the process of fuzzifying the features from different data sources, inferring using a rule base, obtaining fuzzy evaluation results of collision, grounding, loss of control, and formation stability risk, obtaining risk values in each dimension, is as follows:

[0017] Selecting key input variables, selecting core parameters from multi-source fusion data: visibility, wind speed, real-time water depth, distance to the nearest target, ship safety distance, speed, and communication delay;

[0018] Defining a risk semantic set, setting risk description levels for each variable: visibility {very poor, poor, medium, good}, safety distance {dangerous, critical, safe}, and speed {too large, slightly large, normal};

[0019] Fuzzy reasoning:

[0020] Constructing an expert rule base and designing "IF-condition-THEN-risk" rules,

[0021] Performing rule inference:

[0022] Matching activation rules, checking the conditions of the rules that the current data meet;

[0023] Determining the rule strength, taking the lowest matching degree in the condition as the rule confidence;

[0024] Output fuzzy results, generate risk description according to confidence.

[0025] Convert fuzzy evaluation to numerical value, and quantify risk value.

[0026] Further, the extracted target features include position information of the ship, speed of the ship, size of the ship, and type of the ship;

[0027] The extracted risk features include visibility level, wind speed level, water flow intensity, and shallow point distance.

[0028] Further, the fuzzy comprehensive evaluation model module defines the input variables to include: the distance of the nearest target, visibility, wind speed, ship safety distance, and sailing speed.

[0029] The fuzzy sets of each variable are defined to include: distance: near / medium / far, and pre-warning prompt: dangerous / attention / safe.

[0030] Further, the method for preprocessing and sampling the acquired surrounding environment information, ship state information, and navigation situation information of each ship in the ship formation includes time-space alignment and filtering and noise reduction.

[0031] An inland river ship formation risk assessment system based on multi-source information fusion, comprising:

[0032] The shore-based command and monitoring center is used for global monitoring and emergency command, is interconnected with the leading ship and the maritime agency, and shares information;

[0033] The following ship data acquisition module is used for following ship state and environment perception, risk information transmission, receiving and executing control instructions, and information interaction with the leading ship;

[0034] The leading ship decision module is used for local situation awareness of the formation, refinement of formation risk assessment, generation and distribution of collaborative control instructions based on the following ship state and environment perception and risk information collected by the following ship data acquisition module, and is connected with the shore-based center and communicates with the following ship through the internal communication network of the formation.

[0035] The application provides a risk assessment system and method for inland ship formation based on multi-source information fusion, which constructs an intelligent risk assessment system by fusing multi-source heterogeneous information (environment, ship state, navigation situation). The application breaks through the limitation of traditional single threshold alarm, dynamically calculates the multi-dimensional risks of ship individuals and the whole formation by using multi-level fusion and fuzzy comprehensive evaluation model, improves the accuracy and timeliness of risk identification, establishes a three-level cooperative mechanism of "shore base-leader ship-follower ship", realizes real-time data sharing and closed-loop control, provides precise intervention guidance for crew members by combining visual early warning and traceability function, and enhances the global control ability of the shore base and improves the navigation safety of the inland ship formation. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings described below are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without any creative labor.

[0037] Figure 1 The risk assessment flowchart of the present application; DETAILED DESCRIPTION

[0038] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict, and the present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0039] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings of the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. The description of the at least one exemplary embodiment is actually only illustrative, but not as any limitation on the present application and its application or use. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative labor are within the scope of protection of the present application.

[0040] A risk assessment method for inland ship formation based on multi-source information fusion, comprising the following steps:

[0041] S1: obtaining the surrounding environment information, ship state information and navigation situation information of each ship in the ship formation;

[0042] S2: preprocessing the obtained surrounding environment information, ship state information and navigation situation information of each ship in the ship formation;

[0043] S3: Construct a ship formation risk assessment model for assessing the formation risk of each ship in the ship formation;

[0044] S4: Train the ship formation risk assessment model to obtain a trained ship formation risk assessment model;

[0045] S5: Input the preprocessed environmental information, ship state information, and navigation situation information around each ship in the ship formation into the trained ship formation risk assessment model to assess the risk of each ship in the ship formation.

[0046] The steps S1 / S2 / S3 / S4 / S5 are sequentially executed;

[0047] The environmental information includes real-time hydro-meteorological information, channel information, and traffic situation; the hydro-meteorological information includes flow rate, water depth, visibility, wind speed, wind direction, and precipitation;

[0048] The channel information includes electronic charts, beacon status, and navigation hazards;

[0049] The traffic situation includes AIS targets and radar targets;

[0050] The ship state information includes the position, heading, speed, bow direction, main engine / steering engine working condition, key equipment state information of the ship in the formation, and real-time water depth and wind speed and direction of the surrounding environment, relative position, safety distance, formation speed, and inter-ship communication quality of the formation;

[0051] The navigation situation information includes ship-to-ship encounter situation, traffic flow density, and special water area status containing bridges and intersection areas.

[0052] The method for preprocessing and sampling the acquired environmental information, ship state information, and navigation situation information around each ship in the ship formation includes time-space alignment and filtering and noise reduction.

[0053] The ship formation risk assessment model includes:

[0054] A fusion module for fusing data from multiple ship position sources to obtain more accurate self and following ship state data information;

[0055] A feature extraction module for extracting target features based on the self and following ship state data information transmitted by the fusion module, and further extracting risk features from environmental data;

[0056] Fuzzy comprehensive evaluation model module: based on the fused feature set, fuzzy comprehensive evaluation is used to calculate the confidence of each risk dimension; it is also used to extract risk features from the feature extraction module, to fuzz the features from different data sources, to use the rule base for reasoning, to obtain the fuzzy evaluation results of collision, grounding, loss of control, and formation stability risk, to obtain the risk values of each dimension, to calculate the individual risk value of the ship and the overall comprehensive risk value of the formation by the preset weight, and to divide the risk level, the specific process is as follows:

[0057] S1: Fuzzy processing:

[0058] Select key input variables, select core parameters from multi-source fusion data: visibility, wind speed, real-time water depth, distance to the nearest target, ship safety distance, speed, communication delay;

[0059] Define risk semantic set, set risk description level for each variable: visibility {very poor, poor, medium, good}, safety distance {dangerous, critical, safe}, speed {too large, slightly large, normal};

[0060] S2. Fuzzy reasoning:

[0061] Construct expert rule base, design "IF-condition-THEN-risk" rules, such as:

[0062] RULE 1: IF [visibility = very poor] AND [safety distance = dangerous] THEN [collision risk = very high];

[0063] RULE 2: IF [water depth < draft + 0.5m] AND [speed = too large] THEN [grounding risk = high];

[0064] RULE 3: IF [communication delay > 200ms] THEN [formation instability risk = medium];

[0065] 33. Execute rule reasoning:

[0066] Match active rules, check which rules the current data meets the conditions (such as visibility 500m + safety distance 50m, activate RULE 1);

[0067] Determine the strength of the rule, take the lowest matching degree in the condition as the rule confidence (such as visibility "very poor" matching degree 100% + safety distance "dangerous" matching degree 80%, RULE 1 confidence = 80%);

[0068] Output fuzzy results, generate risk description according to confidence (such as collision risk = "very high" (80% confidence)).

[0069] 34. Risk value quantification (convert fuzzy evaluation to numerical value):

[0070] Single risk score:

[0071] Define score intervals for each risk dimension (collision / grounding / loss of control / formation instability):

[0072] "Very high": 80-100 points, "High": 60-79 points, "Medium": 30-59 points, "Low": 0-29 points;

[0073] Identify key risk sources:

[0074] Label input variables with a confidence score >60% as key causes (e.g. "extreme poor visibility is the main cause of collision");

[0075] Integrated risk calculation and classification:

[0076] Ship individual risk value:

[0077] Assign weights: collision risk (40%), grounding risk (30%), formation instability (20%), equipment loss of control (10%);

[0078] Weighted calculation: individual risk value = collision score x 0.4 + grounding score x 0.3 + instability score x 0.2 + loss of control score x 0.1;

[0079] Formation overall risk value: take the highest score of all following ship individual risk values;

[0080] Risk classification:

[0081]

[0082] Through neural network model, calculate ship individual risk value and formation overall risk value, and dynamically classify risk levels (low, medium, high, very high). Identify the main factors and mutual relations that lead to high risk, and provide basis for precise intervention.

[0083] The neural network model structure includes: input layer, shared feature extraction, individual risk, individual risk weight distribution, ship individual risk value, formation risk, formation risk weight distribution, formation overall risk value, risk level classifier. The fuzzy comprehensive evaluation model module defines input variables including: nearest target distance, visibility, wind speed, ship safety distance, and speed;

[0084] Define fuzzy sets for each variable, including distance: near / medium / remote, warning prompt: danger / attention / safety.

[0085] Processed hydro-meteorological information, channel information, and traffic situation data information are shared to the shore-based center, visualizing the formation overall risk situation, high-risk areas, and key risk sources, and providing recommendations based on risk assessment. In case of emergency, emergency plans can be activated.

[0086] The leading ship receives the shore-based information, combines local evaluation to generate specific collision avoidance, formation adjustment, route planning and other collaborative control instructions, and sends risk early warning to the following ship and the shore.

[0087] The following ship receives the instructions of the leading ship and executes them, reports its own state risk and environmental perception abnormalities, and performs local early warning according to the results of its own ship risk evaluation.

[0088] A river ship formation risk assessment system based on multi-source information fusion, comprising:

[0089] The shore-based command and monitoring center is used for global monitoring and emergency command, is interconnected with the leading ship and the maritime agency, and shares information; the shore-based command and monitoring center is composed of a global information fusion center, a formation risk assessment, a collaborative decision support system, a man-machine interaction and visualization platform;

[0090] The following ship data acquisition module is used for the following ship's own state and environmental perception, risk information transmission, receiving and executing control instructions, and information interaction with the leading ship; the leading ship decision module includes a multi-source information fusion node, a formation local risk assessment, a formation collaborative control system, and a man-machine interaction terminal;

[0091] A computing unit, a multi-source information fusion node system, a formation collaborative control system, and a communication device are installed on the leading ship for connecting the shore and the following ship.

[0092] The leading ship decision module is used for local situation awareness of the formation, refinement of formation risk assessment, generation and distribution of collaborative control instructions based on the following ship's own state and environmental perception, risk information collected by the following ship data acquisition module, while maintaining connection with the shore center and communicating with the following ship through the internal communication network of the formation. The following ship data acquisition module includes an AIS system, a navigation radar device, a camera, a depth sounder, a wind speed and direction instrument, and other ship-borne sensor integrated units;

[0093] The formation navigation risk is evaluated by monitoring and fusing the environmental information around the formation, the ship state information, and the navigation situation information.

[0094] Embodiment 1:

[0095] A server cluster is deployed in the shore-based command center for storing information fusion, risk assessment, decision support, and visualization data.

[0096] A computing unit, a multi-source information fusion node system, a formation collaborative control system, and a communication device are installed on the leading ship for connecting the shore and the following ship.

[0097] Install shipborne sensor integration unit including integrated GNSS / INS, navigation radar equipment, AIS, camera, depth sounder, anemometer, etc., following ship state risk assessment module, instruction receiving and executing module, formation internal communication terminal on each following ship.

[0098] Establish and test the stability of the communication network between the shore base-leader ship and the leader ship-following ship. Load high-precision electronic navigation charts of the relevant waters, configure risk assessment model parameters (risk indicator weight, confidence interval, early warning threshold).

[0099] S1: Data collection and uploading

[0100] The following ship continuously collects its own state including position, speed, heading, draft, engine speed, rudder angle, key equipment state code, and real-time water depth and wind speed and direction of the surrounding environment.

[0101] The following ship preliminarily calculates the collision risk of the ship, the safe distance between ships, and the risk of grounding.

[0102] The following ship transmits the collected raw data, preprocessed feature data, and preliminary risk assessment results to the leader ship through the formation internal network periodically or event-triggered.

[0103] The leader ship collects rich environmental and state data, and receives information including regional weather warning, traffic control information, and updated navigation hazard information issued by the shore base center through the shore base network.

[0104] S2: Information fusion and risk assessment of leader ship

[0105] The information fusion node of the leader ship receives data from each following ship, self-collected data, and information issued by the shore base. Time and space registration is performed to eliminate the inconsistency of data from different sources in time and space.

[0106] Perform multi-level fusion processing:

[0107] Data level: fuse data from multiple position sources to obtain more accurate state data information of the ship and the following ship.

[0108] Feature level: extract target features including position, speed, size, and type from radar and AIS, and extract risk features including visibility level, wind speed level, water flow intensity, and shallow point distance from environmental data.

[0109] Visibility level: very high risk, serious impact (visibility < 500 m), high risk, greater impact (500 m < visibility < 1000 m), higher risk, some impact (1000 < visibility < 1500 m), some risk, less impact (1500 m < visibility < 2000 m); wind speed level: very high risk, serious impact (wind force > 8), high risk, greater impact (7 < wind force < 8), higher risk, some impact (6 < wind force < 7), some risk, less impact (5 < wind force < 6).

[0110] Decision level: use fuzzy comprehensive evaluation model:

[0111] Define input variables: "recent target distance", "visibility", "wind speed", "ship safety distance", "speed", etc.

[0112] Define fuzzy sets for each variable ("distance: near / medium / remote", "early warning prompt: dangerous / attention / safe").

[0113] Fuzzify features from different data sources, use rule base for reasoning, get fuzzy evaluation results of collision, grounding, loss of control, formation stability risk, get risk values in each dimension. Calculate the individual risk value of the ship and the overall comprehensive risk value of the formation by the preset weight, and divide the risk level.

[0114] S3: Risk warning and collaborative decision making

[0115] The lead ship will immediately send an emergency alarm to the ship's driver and the shore-based center through sound and light, text information according to the risk assessment results, if high risk level (comprehensive risk "high" or single risk "extremely high") or key risk events (loss of control of the following ship, detection of emergency collision avoidance situation) are detected. It contains risk type, level, ship position, traceability information. For low risk, generate early warning prompt. The lead ship will generate collision avoidance actions, speed adjustment, formation adjustment, special operation instructions and accurately and timely send them to the following ship through the formation internal network. At the same time, the key risk assessment results, alarm information and measures taken / suggested are reported to the shore-based center.

[0116] S4: Global monitoring and macro decision making of shore-based center

[0117] The shore-based center receives the formation state, risk information, alarm and instruction information from the lead ship.

[0118] Fusion regional traffic flow, future weather trend, navigation plan information, re-evaluate the risk and predict the situation at the formation level and regional level. Monitor the formation dynamics, alarm information on the visualization platform. Provide macro decision support for the lead ship.

[0119] S5: Follow-ship executes and feedbacks the instructions

[0120] Follow-ship receives instructions from lead-ship. The status of instruction execution, new sensor data, and updated risk assessment of the follow-ship are fed back to the lead-ship in real time, forming a closed-loop control.

[0121] Specific examples:

[0122] Visibility = 600m, match "poor" (match degree 70%)

[0123] Safety distance = 40m, match "dangerous" (match degree 90%)

[0124] Trigger rule: IF Visibility = poor AND Safety distance = dangerous THEN Collision risk = high

[0125] Rule confidence = min(70%, 90%) = 70%

[0126] Collision risk score = 70% * 70% = 49 points

[0127] Individual risk value = 49 * 0.4 (weight) + other risk points, total 52 points

[0128] Formation risk value = highest individual score 52 + communication risk 0, medium warning

[0129] System output:

[0130] Warning information: "Formation collision risk medium (52 points), main cause: insufficient visibility + too small safety distance"

[0131] Instruction suggestion: "Lead-ship reduce speed by 10%, follow-ship reduce distance to safety value"

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for part or all of the technical features; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A risk assessment method for inland waterway ship formation based on multi-source information fusion, characterized in that: The method comprises the following steps: Obtain the surrounding environment information, ship state information and navigation situation information of each ship in the ship formation; Preprocess the obtained surrounding environment information, ship state information and navigation situation information of each ship in the ship formation; Construct a ship formation risk assessment model for assessing the formation risk of each ship in the ship formation; Train the ship formation risk assessment model to obtain a trained ship formation risk assessment model; Input the preprocessed surrounding environment information, ship state information and navigation situation information of each ship in the ship formation into the trained ship formation risk assessment model to assess the risk of each ship in the ship formation.

2. The method according to claim 1, wherein the environment information comprises real-time hydrology and meteorology, channel information and traffic situation; The ship state information comprises the position, heading, speed, bow direction, main engine / steering gear working condition and key equipment state information of the ship in the formation, and the real-time water depth and wind speed and direction of the surrounding environment, the relative position, safety distance, formation speed and inter-ship communication quality of the formation; The navigation situation information comprises the meeting situation between ships, traffic flow density, and the state of special water areas containing bridges and intersection areas. The ship formation risk assessment model comprises:

3. The risk assessment method for inland ship formation based on multi-source information fusion according to claim 1, characterized in that: A fusion module for fusing the data of multiple ship position sources to obtain more accurate self and following ship state data information; A feature extraction module for extracting target features based on the self and following ship state data information transmitted by the fusion module, and further extracting risk features from the environment data; A fuzzy comprehensive evaluation model module for fuzzifying the risk features extracted from the feature extraction module, reasoning using a rule base, obtaining fuzzy evaluation results of collision, grounding, loss of control and formation stability risk, obtaining risk values in each dimension, calculating the individual ship risk value and the overall formation comprehensive risk value by a preset weight, and dividing the risk level. The process of fuzzifying the features from different data sources, reasoning using the rule base, obtaining the fuzzy evaluation results of collision, grounding, loss of control and formation stability risk, obtaining the risk values in each dimension, is as follows:

4. The risk assessment method for inland ship formation based on multi-source information fusion according to claim 3, characterized in that: Selecting key input variables, selecting core parameters from the multi-source fusion data: visibility, wind speed, real-time water depth, distance to the nearest target, ship safety distance, speed and communication delay; Defining a risk semantic set, setting risk description levels for each variable: visibility {extremely poor, poor, moderate, good}, safety distance {dangerous, critical, safe}, speed {too large, slightly large, normal}; 2. Fuzzy reasoning: Constructing an expert rule base, designing "IF-condition-THEN-risk" rules, Executing rule reasoning: Matching and activating rules, checking the conditions of the rules satisfied by the current data; Determining the rule strength, taking the lowest matching degree in the conditions as the rule confidence; Outputting fuzzy results, generating risk descriptions according to the confidence. Converting the fuzzy evaluation to a numerical value for risk value quantification. ​ 5. The risk assessment method for inland ship formation based on multi-source information fusion according to claim 1, characterized in that: The extracted target features include position information of the ship, speed of the ship, size of the ship, and type of the ship. The extracted risk features include visibility level, wind speed level, water flow intensity, and shallow point distance.

6. The risk assessment method for inland ship formation based on multi-source information fusion according to claim 1, characterized in that: The fuzzy comprehensive evaluation model module defines input variables, including the distance to the nearest target, visibility, wind speed, safe distance between ships, and sailing speed. The fuzzy sets of each variable are defined as follows: distance: near / medium / far, early warning prompt: dangerous / attention / safe.

7. The risk assessment method for inland ship formation based on multi-source information fusion according to claim 1, characterized in that: The method for preprocessing and sampling the acquired surrounding environment information, ship state information, and sailing situation information of each ship in the ship formation includes time-space alignment and filtering and noise reduction.

8. An inland river ship formation risk assessment system based on multi-source information fusion, characterized in that: The method includes: A shore-based command and monitoring center for global monitoring and emergency command, interconnected with a leading ship and a maritime agency for information sharing; A following ship data acquisition module for self-state and environment perception, risk information transmission, reception and execution of control instructions, and information interaction with the leading ship; A leading ship decision module for local situation awareness of the formation, refined risk assessment of the formation, generation and distribution of collaborative control instructions based on the self-state and environment perception and risk information collected by the following ship data acquisition module, while maintaining connection with the shore-based center and communicating with the following ship through an internal communication network of the formation.

Images