Intelligent fleet simulation navigation system based on remote control

Abstract

The application discloses a kind of intelligent fleet simulation navigation systems based on remote control.The abnormal path segment and environment data are extracted based on historical navigation data by setting navigation task and simulating multiple ship paths based on A* algorithm, and compared with real-time data of fleet to judge potential control abnormal risk, and if abnormal control is determined, shared mechanism is started for coordinated deviation analysis and decision-making of multiple ships, thereby effectively improving control abnormal analysis of overall fleet and improving fleet coordinated control capability and fleet intelligent level.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent ships, more particularly, to an intelligent fleet simulation navigation system based on remote control. BACKGROUND

[0002] With the rapid development of global shipping industry, intelligent ships and unmanned fleet technology gradually become a research hotspot, based on the fleet's perception analysis of the target environment, related water area and fleet cooperative control, which can be applied in water area monitoring, resource exploration, search and rescue analysis, object transportation and other related fields. And the remote control of intelligent fleet can improve the navigation efficiency, reduce the operating cost, and enhance the safety in complex water environment, through the cooperative analysis and environmental perception of the fleet, combined with remote control, the fleet can be efficiently planned.

[0003] But in the prior art, especially for the remote control of multiple ships, affected by communication fluctuations, complex water environment, ship hardware, etc., it is difficult to cooperatively control multiple ships to complete path navigation, and there are often one or more ships in some water areas or some navigation paths that have control abnormalities, navigation deviations, etc. In this case, manual intervention control is often needed, it is difficult to achieve effective synchronous control of multiple ships and complete execution of fleet tasks, and it is difficult to improve the automation and intelligence level of the fleet. SUMMARY

[0004] The present application overcomes the defects of the prior art and provides an intelligent fleet simulation navigation system based on remote control.

[0005] The present application provides an intelligent fleet simulation navigation method based on remote control, comprising:

[0006] S102: In the target water area, set the navigation task of the intelligent fleet, according to the navigation task, simulate the path by A* algorithm, and generate a multi-ship path;

[0007] S104: Set a remote control scheme based on the multi-ship path;

[0008] S106: Locate the abnormal control path and time node according to the historical remote control parameters of each ship, extract the corresponding environmental features and path features from the historical environmental data and historical path data of each ship based on the abnormal control path and time node, and obtain abnormal path features and abnormal environmental features;

[0009] S108: Based on the remote control scheme, the fleet navigation control is carried out, and for each ship, environmental features and path features are collected in real time. Based on each preset path length, the real-time environmental features, real-time path features, abnormal path features, and abnormal environmental features are vectorized and the average difference of the feature vectors is compared. The average difference is linearly fitted, and abnormal control prediction is carried out through linear fitting.

[0010] S110: If an abnormal control judgment occurs, the data sharing mechanism is activated for the target vessel. Through the data sharing mechanism, the target vessel and nearby vessels at a preset distance are used to share positioning, perception and navigation assessment, and the assessment data is sent to the control center for decision analysis.

[0011] In this solution, S102 specifically refers to:

[0012] The intelligent fleet consists of multiple vessels, each of which includes a control terminal, a communication terminal, and a display terminal;

[0013] The navigation task includes the navigation distance, navigation position, and navigation time for each vessel;

[0014] Based on the navigation mission, the waypoints of each ship are set. Based on the A* algorithm, the shortest path is planned for each ship, and multi-ship paths are generated.

[0015] In this solution, S104 specifically refers to:

[0016] Multiple vessel paths are sent to the control center for navigation control analysis. Based on the target waters, control parameter commands for multiple vessels are set, and a remote control scheme is generated.

[0017] In this solution, S106 specifically refers to:

[0018] Obtain historical remote control parameters for each vessel;

[0019] By using historical remote control parameters, locate the path segments and time points where abnormal operation occurs, and mark them as abnormal control paths and time nodes;

[0020] Based on the abnormal control path, path features are extracted from historical path data. The path features include path length, path turning angle, path straight distance, path width, and traffic density.

[0021] Based on time nodes, water environment characteristics for the corresponding time period are extracted from historical environmental data. These water environment characteristics include water temperature, water flow, wind speed, wind direction, and meteorological information.

[0022] Through feature extraction, abnormal path features and abnormal environment features are obtained.

[0023] In the scheme, the S108, specifically:

[0024] Performing ship fleet navigation control based on a remote control scheme;

[0025] Taking a ship as an analysis unit, real-time collection of environmental characteristics and path characteristics of the ship, marked as real-time environmental characteristics and real-time path characteristics;

[0026] Feature vectorization of real-time environmental characteristics and abnormal environmental characteristics, and generation of multi-dimensional first environmental feature vectors and second environmental feature vectors;

[0027] Calculate the difference between the first environmental feature vector and the second environmental feature vector based on the Euclidean distance, marked as the first difference degree;

[0028] Vectorization and difference degree calculation based on real-time path characteristics and abnormal path characteristics to obtain a second difference degree;

[0029] Mean calculation of the first difference degree and the second difference degree to obtain an average difference degree;

[0030] Based on the multiple preset path lengths that have been navigated, multiple average difference degrees are calculated, and linear fitting is performed on the multiple average difference degrees to obtain a prediction fitting curve;

[0031] Predict the average difference degree in the next preset path length through the prediction fitting curve to obtain a prediction value;

[0032] If the prediction value is greater than the preset abnormal value, set an abnormal control judgment and mark the abnormal ship.

[0033] In the scheme, the S110, specifically:

[0034] When the shared data mechanism is started, the abnormal ship and the neighboring ship within the preset distance construct a dedicated shared network;

[0035] Generate first navigation data based on the current positioning and navigation state of the abnormal ship;

[0036] The neighboring ship performs positioning and navigation state evaluation on the abnormal ship through the environmental detection device to generate second navigation data;

[0037] Through the shared network, the neighboring ship evaluates the positioning deviation and navigation anomaly of the abnormal ship based on the first navigation data and the second navigation data to generate real-time navigation evaluation data;

[0038] Send the first navigation data, the second navigation data, and the real-time navigation evaluation data to the control center, and the control center performs real-time matching analysis on the current navigation state and the expected navigation state of the abnormal ship and sets a navigation decision.

[0039] The second aspect of the application also provides a remote control-based intelligent fleet simulation navigation system, comprising a memory and a processor, the memory comprising a remote control-based intelligent fleet simulation navigation program, and the remote control-based intelligent fleet simulation navigation program being executed by the processor to implement the following steps:

[0040] S102: In the target water area, a navigation task of the intelligent fleet is set, and a path simulation is performed through an A* algorithm according to the navigation task to generate a multi-ship path;

[0041] S104: A remote control scheme is set based on the multi-ship path;

[0042] S106: An abnormal control path and a time node are located according to historical remote control parameters of each ship, and corresponding environmental features and path features are extracted from historical environmental data and historical path data of each ship based on the abnormal control path and the time node to obtain abnormal path features and abnormal environmental features;

[0043] S108: The fleet navigation control is performed based on the remote control scheme, and for each ship, environmental features and path features are collected in real time, the real-time environmental features, the real-time path features, the abnormal path features and the abnormal environmental features are vectorized based on each preset path length, and the average difference degree of the feature vectors is compared, the average difference degree is linearly fitted, and the abnormal control prediction is performed through the linear fitting;

[0044] S110: If an abnormal control is determined, a shared data mechanism is started for the target ship, and through the shared data mechanism, the target ship and the neighboring ships within a preset distance are positioned, shared sensing and navigation evaluation are performed, and the evaluation data is sent to a control center for decision analysis.

[0045] The third aspect of the application also provides a computer readable storage medium, the computer readable storage medium comprising a remote control-based intelligent fleet simulation navigation program, and the remote control-based intelligent fleet simulation navigation program being executed by a processor to implement the steps of the remote control-based intelligent fleet simulation navigation method according to any one of the above.

[0046] The application discloses a remote control-based intelligent fleet simulation navigation system. By setting a navigation task and generating a multi-ship path based on an A* algorithm, abnormal path segments and environmental data are extracted from historical navigation data, compared with real-time data of the fleet, potential control abnormal risks are judged, if an abnormal control is determined, a shared mechanism is started for collaborative deviation analysis and decision judgment of multiple ships, thereby effectively improving control abnormal analysis of the whole fleet and improving collaborative control ability and intelligent level of the fleet. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 A flow chart of a method for simulating navigation of an intelligent fleet based on remote control is shown.

[0048] Figure 2 A block diagram of a system for simulating navigation of an intelligent fleet based on remote control is shown. DETAILED DESCRIPTION

[0049] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0050] In the following description, a large number of specific details are set forth in order to facilitate a thorough understanding of the present application, however, the present application can also be implemented in other ways different from those described herein, and therefore, the scope of protection of the present application is not limited by the specific embodiments disclosed below.

[0051] Figure 1 A flow chart of a method for simulating navigation of an intelligent fleet based on remote control is shown.

[0052] As Figure 1 shown, the first aspect of the present application provides a method for simulating navigation of an intelligent fleet based on remote control, comprising:

[0053] S102: In a target water area, a navigation task of an intelligent fleet is set, and a path simulation is performed through an A* algorithm according to the navigation task, to generate a multi-ship path;

[0054] S104: A remote control scheme is set based on the multi-ship path;

[0055] S106: An abnormal control path and a time node are located according to historical remote control parameters of each ship, and based on the abnormal control path and the time node, corresponding environmental features and path features are extracted from historical environmental data and historical path data of each ship, to obtain abnormal path features and abnormal environmental features;

[0056] S108: The fleet navigation control is performed based on the remote control scheme, and for each ship, environmental features and path features are collected in real time, the real-time environmental features, the real-time path features, the abnormal path features and the abnormal environmental features are vectorized based on each preset path length, and the average difference degree of the feature vectors is compared, the average difference degree is linearly fitted, and the abnormal control prediction is performed through linear fitting;

[0057] S110: If an abnormality occurs, the shared data mechanism is started for the target ship, the target ship and the preset distance adjacent ship are positioned, shared sensing and navigation evaluation are performed, and the evaluation data is sent to the control center for decision analysis.

[0058] It should be noted that the A* algorithm is a heuristic algorithm that searches for the shortest path by setting path points.

[0059] According to the embodiment of the present application, the S102 is specifically:

[0060] The intelligent ship fleet includes a plurality of ships, each of which includes a control terminal, a communication terminal and a display terminal.

[0061] The navigation task includes the navigation distance, the navigation position point and the navigation time of each ship.

[0062] According to the navigation task, the navigation passing points of each ship are set, the shortest path planning is performed for each ship based on the A* algorithm, and the multi-ship path is generated.

[0063] It should be noted that the control terminal is used to set the ship navigation control parameters, the communication terminal is used for remote control communication between the ship and the control center, and generally based on the Internet of Things for real-time communication, and the display terminal is used to display the ship state.

[0064] According to the embodiment of the present application, the S104 is specifically:

[0065] The multi-ship path is sent to the control center for navigation control analysis, the control parameter instructions of the multi-ship are set in combination with the target water area, and the remote control scheme is generated.

[0066] It should be noted that the remote control scheme is based on the overall operation control parameters of the ship fleet, including the control parameters based on each ship.

[0067] According to the embodiment of the present application, the S106 is specifically:

[0068] The historical remote control parameters of each ship are obtained.

[0069] The path segment and the time point of the abnormal operation are located through the historical remote control parameters, and are marked as an abnormal control path and a time node.

[0070] Based on the abnormal control path, path features are extracted from the historical path data, including path length, path turning angle, path straight distance, path width and traffic density.

[0071] Based on the time node, the water body environment features of the corresponding period are extracted from the historical environment data, and the water body environment features include water temperature, water flow, wind speed, wind direction and weather information.

[0072] Through feature extraction, abnormal path features and abnormal environment features are obtained.

[0073] It should be noted that the historical remote control parameters are historical control data, navigation path data and the like collected by the ship control terminal in the historical period, which are used to mine the state data of abnormal remote control, extract the corresponding abnormal control path and time node, and extract the environment features and path features for the abnormal path and time node. The path width can include the maximum, minimum and average width, and the path features can reflect the navigation complexity. The water body features can reflect the water body environment during navigation, and by analyzing the water body features, the correlation between the water body feature change and the abnormal control can be mined.

[0074] According to the embodiment of the application, the S108, specifically:

[0075] Based on the remote control scheme, the ship fleet navigation control is performed;

[0076] Taking one ship as an analysis unit, the environment features and path features of the ship are collected in real time, which are marked as real-time environment features and real-time path features;

[0077] The real-time environment features and the abnormal environment features are vectorized, and a first environment feature vector and a second environment feature vector of multiple dimensions are generated respectively;

[0078] The difference between the first environment feature vector and the second environment feature vector is calculated based on the Euclidean distance, which is marked as the first difference degree;

[0079] The real-time path features and the abnormal path features are vectorized and the difference degree is calculated, to obtain the second difference degree;

[0080] The first difference degree and the second difference degree are averaged to obtain the average difference degree;

[0081] Based on the multiple preset path lengths that have been navigated, multiple average difference degrees are calculated, and the multiple average difference degrees are linearly fitted to obtain a prediction fitting curve;

[0082] The average difference degree in the next preset path length is predicted through the prediction fitting curve to obtain a prediction value;

[0083] If the prediction value is greater than a preset abnormal value, an abnormal control determination is set and an abnormal ship is marked.

[0084] It should be noted that the preset path length is set for analysis, and the role is to segment and evaluate the entire navigation path in real time. The first difference and the second difference calculation method are consistent, and both use distance values as the difference. Through the prediction of the fitting curve, the abnormal control prediction can be effectively realized.

[0085] The Euclidean distance is calculated as follows:

[0086]

[0087] Wherein, d is the Euclidean distance, N is the vector dimension number, , respectively, the numerical value of the two calculation vectors of the i-th dimension.

[0088] According to the embodiment of the present application, the S110, specifically:

[0089] When the shared data mechanism is started, the abnormal ship and the adjacent ship within the preset distance construct a special shared network;

[0090] Based on the current positioning and navigation state of the abnormal ship, the first navigation data is generated;

[0091] The adjacent ship generates the second navigation data by positioning and navigation state evaluation of the abnormal ship through the environment detection device;

[0092] Through the shared network, the adjacent ship generates real-time navigation evaluation data by evaluating the positioning deviation and navigation anomaly of the abnormal ship based on the first navigation data and the second navigation data;

[0093] The first navigation data, the second navigation data and the real-time navigation evaluation data are sent to the control center, and the control center performs real-time matching analysis on the current navigation state and the expected navigation state of the abnormal ship and sets the navigation decision.

[0094] It should be noted that the environment detection device includes radar device, camera device and the like. The whole ship fleet navigation system includes a plurality of ships and a control center, and the control center and the plurality of ships establish a real-time communication network based on the Internet of Things. The shared network is established between the ships based on the demand.

[0095] ​It is worth noting here that in the unmanned fleet operation task (especially the remote control operation of the unmanned fleet), the navigation task content includes water area monitoring, resource exploration, search and rescue analysis, object transportation, etc., which has high navigation requirements for real-time, accuracy, safety, etc. of the ship. However, in the prior art, especially in the remote control of multiple ships, due to communication fluctuations, complex water environments, ship hardware, etc., it is difficult to cooperatively control multiple ships to navigate the complete path, and there are often one or more ships in some water areas or some navigation paths that have control abnormalities, navigation deviations, etc. In this case, manual intervention control is often needed, effective synchronization control of multiple ships and complete execution of the fleet task are difficult to achieve, and the automation and intelligence level of the fleet is difficult to improve.

[0096] Based on this, the application simulates a corresponding remote control scheme in the target water area, extracts the abnormal path segment and environment data based on historical navigation data, sets the corresponding abnormal path features and abnormal environment features, and in the real-time remote control process, the real-time environment and path features of each preset path segment are compared and analyzed in real time with the abnormal features, the average difference is calculated, the average difference is linearly fitted, and whether there is a potential abnormal control risk is reasonably predicted. The system effectively improves the control abnormality analysis of the overall fleet, improves the accurate deviation and control abnormality evaluation of the individual propagation, and uses a sharing mechanism in real time, through the cooperative navigation analysis of multiple ships to the target ship, collects the corresponding shared data and sends it to the control center for navigation decision evaluation, effectively improving the stability of the fleet in complex environments. Multi-ship cooperative operation.

[0097] In addition, starting the shared data mechanism often consumes certain computing resources and network resources, and continuous opening will affect the stable operation of the overall fleet, therefore, the application selectively starts based on real-time state, effectively improving the dynamic regulation and control capability of the ship.

[0098] According to the embodiment of the application, the shared data mechanism further comprises:

[0099] When the shared data mechanism is started, the abnormal ship is taken as the center to judge the ships within a preset distance range in real time, and the ships are marked as adjacent ships, and a dedicated shared network is constructed with the adjacent ships;

[0100] The first navigation data is generated based on the current positioning and navigation state of the abnormal ship;

[0101] The adjacent ships evaluate the positioning and navigation state of the abnormal ship through the environment detection device to generate the second navigation data;

[0102] In one adjacent ship, the navigation deviation and path deviation of the abnormal ship are analyzed through the first navigation data and the second navigation data to generate operation decision information;

[0103] Generate a plurality of running decision information based on a plurality of adjacent ships, and send the running decision information to the control center in real time;

[0104] In the real-time running cycle, the existing adjacent ships are judged cyclically, and if the adjacent ships exceed the preset distance range, the running decision information is stopped from being sent.

[0105] It should be noted that the running decision includes decision schemes such as termination of remote control, continuation of control, route adjustment, and ship navigation parameter adjustment. In the running of a multi-ship fleet, starting a shared network for collaborative anomaly analysis often consumes too much resource, and there is also a certain data analysis pressure on the control center. Based on this, the embodiment of the application judges the adjacent ships within the preset range in real time, performs network sharing and collaborative decision analysis on the adjacent ships, analyzes the running decision information with certain differences from different adjacent ship angles, sends the running decision information to the control center in real time, effectively improves the decision analysis capability of the control center, and distributes the decision analysis pressure to the multi-ship terminal, thereby improving the stability and feasibility of the comprehensive operation of the fleet.

[0106] According to the embodiment of the application, the method further comprises:

[0107] When the abnormal control determination occurs, a path segment of a preset path length corresponding to the current position of the abnormal ship is marked as an abnormal path segment;

[0108] In the decision evaluation process of the control center, a path cost is set for the abnormal path segment based on the control deviation degree of the abnormal ship;

[0109] A path constraint condition is generated based on the path cost, and in the path simulation process of the A* algorithm in the next navigation task, the path constraint condition is imported for path simulation.

[0110] It should be noted that the control deviation degree is obtained based on comprehensive analysis of the navigation deviation, the path deviation, and the running decision information of the adjacent ships, and is used to determine the deviation control degree of the abnormal ship. The path cost is proportional to the control deviation degree of the abnormal ship. By generating the path constraint condition, the path planning algorithm can be dynamically adjusted to adapt to the complex water area with abnormal control, and the comprehensive path planning capability is improved.

[0111] Figure 2 A block diagram of an intelligent fleet simulation navigation system based on remote control is shown.

[0112] The second aspect of the application also provides a remote control-based intelligent fleet simulation navigation system 2, comprising a memory 21 and a processor 22, the memory 21 comprising a remote control-based intelligent fleet simulation navigation program, and the remote control-based intelligent fleet simulation navigation program is executed by the processor 22 to implement the following steps:

[0113] S102: In the target water area, a navigation task of the intelligent fleet is set, and a path simulation is performed through an A* algorithm according to the navigation task to generate a multi-ship path;

[0114] S104: A remote control scheme is set based on the multi-ship path;

[0115] S106: An abnormal control path and a time node are located according to historical remote control parameters of each ship, and corresponding environmental features and path features are extracted from historical environmental data and historical path data of each ship based on the abnormal control path and the time node to obtain abnormal path features and abnormal environmental features;

[0116] S108: The fleet navigation control is performed based on the remote control scheme, and for each ship, environmental features and path features are collected in real time, the real-time environmental features, the real-time path features, the abnormal path features and the abnormal environmental features are vectorized based on each preset path length, and the average difference degree of the feature vectors is compared, the average difference degree is linearly fitted, and the abnormal control prediction is performed through the linear fitting;

[0117] S110: If an abnormal control is determined, a shared data mechanism is started for the target ship, the target ship and a ship within a preset distance are located through the shared data mechanism, shared perception and navigation evaluation are performed, and evaluation data is sent to a control center for decision analysis.

[0118] It should be noted that the A* algorithm is a heuristic algorithm for searching the shortest path by setting path points.

[0119] According to the embodiment of the application, the S102 specifically comprises:

[0120] The intelligent fleet comprises a plurality of ships, and each ship comprises a control terminal, a communication terminal and a display terminal;

[0121] The navigation task comprises a navigation distance, a navigation position point and a navigation time of each ship;

[0122] The navigation points of each ship are set according to the navigation task, the shortest path planning is performed for each ship based on the A* algorithm, and the multi-ship path is generated.

[0123] It should be noted that the control terminal is used for setting the ship navigation control parameter, the communication terminal is used for remote control communication between the ship and the control center, and real-time communication is generally based on the Internet of Things, and the display terminal is used for displaying the ship state.

[0124] According to the embodiment of the present application, the S104 is specifically:

[0125] The multi-ship path is sent to the control center, the ship path is analyzed for navigation control, the control parameter instruction of the multi-ship is set in combination with the target water area, and the remote control scheme is generated.

[0126] It should be noted that the remote control scheme is based on the overall operation control parameter of the ship fleet, including the control parameter based on each ship.

[0127] According to the embodiment of the present application, the S106 is specifically:

[0128] The historical remote control parameters of each ship are acquired;

[0129] The path segment and time point of abnormal operation are located through the historical remote control parameters, and are marked as abnormal control path and time node;

[0130] Based on the abnormal control path, path features are extracted from the historical path data, including path length, path turning angle, path straight distance, path width, and traffic density.

[0131] Based on the time node, water body environment features are extracted from the historical environment data in the corresponding period, including water temperature, water flow, wind speed, wind direction, and weather information.

[0132] Through feature extraction, abnormal path features and abnormal environment features are obtained.

[0133] It should be noted that the historical remote control parameters are historical control data, navigation path data, etc. collected by the ship control terminal in the historical period, which are used to mine the abnormal remote control state data, extract the corresponding abnormal control path and time node, and extract the environment features and path features for the abnormal path and time node. The path width can include the maximum, minimum and average width, and the path features can reflect the navigation complexity. The water body features can reflect the water body environment during navigation, and the correlation between the water body feature change and the abnormal control can be mined by analyzing the water body features.

[0134] According to the embodiment of the present application, the S108 is specifically:

[0135] Based on the remote control scheme, the ship fleet is navigated.

[0136] Taking a ship as an analysis unit, real-time collection of environmental characteristics and path characteristics of the ship is performed, and the environmental characteristics and the path characteristics are marked as real-time environmental characteristics and real-time path characteristics;

[0137] The real-time environmental characteristics and the abnormal environmental characteristics are vectorized, and a first environmental feature vector and a second environmental feature vector in multiple dimensions are generated respectively;

[0138] The first environmental feature vector and the second environmental feature vector are calculated based on the Euclidean distance, and are marked as a first difference degree;

[0139] The real-time path characteristics and the abnormal path characteristics are vectorized and the difference degree is calculated, and a second difference degree is obtained;

[0140] The first difference degree and the second difference degree are calculated by the mean value, and an average difference degree is obtained;

[0141] Based on a plurality of preset path lengths that have been sailed, a plurality of average difference degrees are calculated, and the plurality of average difference degrees are linearly fitted to obtain a prediction fitting curve;

[0142] The average difference degree in the next preset path length is predicted by the prediction fitting curve, and a prediction value is obtained;

[0143] If the prediction value is greater than a preset abnormal value, an abnormal control judgment is set and an abnormal ship is marked.

[0144] It should be noted that the preset path length is set for analysis, and the effect is to perform segmented real-time abnormal evaluation on the entire sailing path. The first difference degree and the second difference degree are calculated in the same way, and both use distance values as difference degrees. Through the prediction fitting curve, the abnormal control prediction can be effectively realized.

[0145] The Euclidean distance is calculated as follows:

[0146] ,

[0147] Wherein, d is the Euclidean distance, N is the number of vector dimensions, , respectively, are the values of the i-th dimension of the two calculation vectors.

[0148] According to the embodiment of the application, the S110, specifically:

[0149] When the shared data mechanism is started, the abnormal ship and the neighboring ship within the preset distance construct a special shared network;

[0150] The first sailing data is generated based on the current positioning and sailing state of the abnormal ship;

[0151] The neighboring ship performs positioning and sailing state evaluation on the abnormal ship through the environment detection device, and generates the second sailing data;

[0152] The abnormal ship positioning deviation and navigation anomaly evaluation is generated based on the first navigation data and the second navigation data by sharing the network by the adjacent ships;

[0153] The first navigation data, the second navigation data and the real-time navigation evaluation data are sent to the control center, and the control center performs real-time matching analysis on the current navigation state and the expected navigation state of the abnormal ship and sets the navigation decision.

[0154] It should be noted that the environment detection device includes a radar device, a camera device, etc. The fleet navigation system includes a plurality of ships and a control center, and the control center and the plurality of ships establish a real-time communication network based on the Internet of Things. The ships establish a shared network based on demand.

[0155] It is worth noting here that in the unmanned fleet operation task (especially the remote control operation of the unmanned fleet), the navigation task content includes water area monitoring, resource exploration, search and rescue analysis, object transportation, etc., which has high navigation requirements for real-time, accuracy, safety, etc. of the ship. However, in the prior art, especially in the remote control of multiple ships, due to communication fluctuations, complex water environments, ship hardware, etc., it is difficult to cooperatively control multiple ships to navigate the complete path, and there are often one or more ships in some water areas or some navigation paths that have control abnormalities, navigation deviations, etc. In this case, manual intervention control is often needed, it is difficult to achieve effective synchronous control of multiple ships and complete execution of the fleet task, and it is difficult to improve the automation and intelligence level of the fleet.

[0156] Based on this, the present application simulates a corresponding remote control scheme in the target water area, extracts the abnormal path segment and environment data based on historical navigation data, sets the corresponding abnormal path features and abnormal environment features, and in the real-time remote control process, the real-time environment and path features of each preset path segment are compared and analyzed in real time with the abnormal features, the average difference is calculated, the average difference is linearly fitted, and whether there is a potential abnormal control risk is reasonably predicted, the control abnormality analysis of the system to the whole fleet is effectively improved, the accurate deviation and control abnormality evaluation of the individual propagation are improved, and the sharing mechanism is used in real time, the cooperative navigation analysis of multiple ships to the target ship is performed, the corresponding shared data is collected and sent to the control center for navigation decision evaluation, and the stability of the fleet in complex environment is effectively improved. Multi-ship cooperative operation.

[0157] In addition, starting the shared data mechanism often consumes certain computing resources and network resources, and continuous opening will affect the stable operation of the whole fleet, therefore, the present application selectively starts based on the real-time state, effectively improving the dynamic regulation and control capability of the ship.

[0158] The third aspect of the present application also provides a computer readable storage medium, wherein a remote control based intelligent fleet simulation navigation program is included in the computer readable storage medium, and the remote control based intelligent fleet simulation navigation program, when executed by a processor, implements the steps of the remote control based intelligent fleet simulation navigation method according to any one of the above.

[0159] The present application discloses a remote control based intelligent fleet simulation navigation system. By setting a navigation task and generating a multi-ship path based on an A* algorithm, abnormal path segments and environment data are extracted based on historical navigation data, and compared with real-time fleet data to determine potential control abnormal risks. If an abnormal control determination occurs, a sharing mechanism is started to perform multi-ship collaborative deviation analysis and decision-making, thereby effectively improving control abnormal analysis of the overall fleet and improving fleet collaborative control capability and fleet intelligence level.

[0160] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above described device embodiments are only schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling, or direct coupling or communication connection between the components can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or in other forms.

[0161] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units; they can be located in one place, or distributed on multiple network units; and some or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0162] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware, or in the form of hardware plus software functional unit.

[0163] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware, the foregoing program can be stored in a computer readable storage medium, and the program executes the steps of the method embodiments when executed; and the foregoing storage medium includes a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disc or an optical disc, and various media that can store program codes.

[0164] Alternatively, the integrated unit of the present application can be stored in a computer readable storage medium if it is realized in the form of a software function module and sold or used as an independent product. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the methods described in the embodiments of the present application. The foregoing storage medium includes a mobile storage device, a ROM, a RAM, a magnetic disc or an optical disc, and various media that can store program codes.

[0165] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A method for simulating navigation of an intelligent fleet based on remote control, characterized in that, include: S102: In the target waters, set the navigation mission of the intelligent fleet, and generate multi-ship paths by simulating the path using the A* algorithm based on the navigation mission. S104: Remote control scheme based on multi-ship path setting; S106: Locate the abnormal control path and time node based on the historical remote control parameters of each ship, and extract the corresponding environmental features and path features from the historical environmental data and historical path data of each ship to obtain the abnormal path features and abnormal environmental features. S108: Based on the remote control scheme, the fleet navigation control is carried out, and for each ship, environmental features and path features are collected in real time. Based on each preset path length, the real-time environmental features, real-time path features, abnormal path features, and abnormal environmental features are vectorized and the average difference of the feature vectors is compared. The average difference is linearly fitted, and abnormal control prediction is carried out through linear fitting. S110: If an abnormal control judgment occurs, the data sharing mechanism is activated for the target vessel. Through the data sharing mechanism, the target vessel and nearby vessels at a preset distance are used to share positioning, perception and navigation assessment, and the assessment data is sent to the control center for decision analysis. Specifically, S102 is as follows: The intelligent fleet consists of multiple vessels, each of which includes a control terminal, a communication terminal, and a display terminal; The navigation task includes the navigation distance, navigation position, and navigation time for each vessel; Based on the navigation mission, the waypoints of each ship are set. Based on the A* algorithm, the shortest path is planned for each ship and multi-ship paths are generated. Specifically, S104 is as follows: Multiple vessel paths are sent to the control center for navigation control analysis. Based on the target waters, control parameter commands for multiple vessels are set, and a remote control scheme is generated. Specifically, S106 is as follows: Obtain historical remote control parameters for each vessel; By using historical remote control parameters, locate the path segments and time points where abnormal operation occurs, and mark them as abnormal control paths and time nodes; Based on the abnormal control path, path features are extracted from historical path data. The path features include path length, path turning angle, path straight distance, path width, and traffic density. Based on time nodes, water environment characteristics for the corresponding time period are extracted from historical environmental data. These water environment characteristics include water temperature, water flow, wind speed, wind direction, and meteorological information. Through feature extraction, abnormal path features and abnormal environment features are obtained; Specifically, S108 is as follows: Fleet navigation control based on remote control scheme; Using a single vessel as the unit of analysis, the environmental and path characteristics of the vessel are collected in real time and labeled as real-time environmental characteristics and real-time path characteristics. Real-time environmental features and abnormal environmental features are vectorized into feature vectors, and multi-dimensional first environmental feature vectors and second environmental feature vectors are generated respectively. The difference between the first environmental feature vector and the second environmental feature vector is calculated based on Euclidean distance and marked as the first difference degree. The second difference degree is obtained by vectorizing and calculating the difference degree based on real-time path features and abnormal path features; The average difference is obtained by averaging the first and second differences. Based on the lengths of multiple preset paths that have been navigated, multiple average differences are calculated, and linear fitting is performed on the multiple average differences to obtain the predicted fitting curve. By predicting the fitted curve, the average degree of difference in the next preset path length is predicted, and the predicted value is obtained. If the predicted value is greater than the preset abnormal value, then an abnormal control judgment is set and the abnormal vessel is marked; Specifically, S110 is as follows: When the data sharing mechanism is activated, abnormal vessels establish a dedicated shared network with nearby vessels at a preset distance; First navigation data is generated based on the current location and navigation status of the abnormal vessel; Nearby vessels use environmental monitoring devices to locate and assess the navigation status of abnormal vessels, generating secondary navigation data. Through a shared network, neighboring vessels assess abnormal vessel positioning deviations and navigation anomalies based on first and second navigation data, generating real-time navigation assessment data. The first navigation data, the second navigation data, and the real-time navigation assessment data are sent to the control center. The control center performs real-time matching analysis on the current navigation status and expected navigation status of the abnormal vessel and sets navigation decisions. The shared data mechanism further includes: When the data sharing mechanism is activated, vessels within a preset distance range are identified in real time, centered on abnormal vessels, and marked as nearby vessels, thus establishing a dedicated data sharing network with these nearby vessels. First navigation data is generated based on the current location and navigation status of the abnormal vessel; Nearby vessels use environmental monitoring devices to locate and assess the navigation status of abnormal vessels, generating secondary navigation data. In a neighboring vessel, the navigation deviation and path deviation of the abnormal vessel are analyzed by comparing the first navigation data and the second navigation data to generate operational decision information; Multiple operational decision information is generated based on multiple nearby vessels, and the operational decision information is sent to the control center in real time; During the real-time operation cycle, the system continuously checks for nearby vessels. If a nearby vessel exceeds the preset distance range, the system stops sending operation decision information. This also includes: When an abnormal control judgment is made, the path segment with a preset path length corresponding to the current position of the abnormal vessel is marked as an abnormal path segment. During the decision-making and evaluation process at the control center, path costs are set for abnormal path segments based on the degree of abnormal vessel control deviation. Based on the path cost, path constraints are generated. In the next navigation mission, during the path simulation process of the A* algorithm, the path constraints are imported to perform path simulation.

2. A remote-controlled intelligent fleet simulation navigation system, characterized in that, The system includes a memory and a processor. The memory includes a remote-controlled intelligent fleet simulation navigation program. When the remote-controlled intelligent fleet simulation navigation program is executed by the processor, it implements the steps of the remote-controlled intelligent fleet simulation navigation method as described in claim 1.

3. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a remotely controlled intelligent fleet simulation navigation program, which, when executed by a processor, implements the steps of the remotely controlled intelligent fleet simulation navigation method as described in claim 1.

Images