Intelligent ship autonomous decision-making system and method based on meta universe

Abstract

The invention relates to an intelligent ship autonomous decision-making system and method based on the meta universe, the system comprises a data acquisition module, a data processing module, a decision-making control module and a meta universe platform, the data acquisition module acquires dynamic information of a ship and physical information of the surrounding environment of the ship in real time through a sensor; the meta universe platform is used for performing simulation analysis according to the physical information of the surrounding environment of the ship to construct a real-time environment model, and performing simulation analysis according to the dynamic information of the ship to construct a three-dimensional dynamic model; the data processing module is used for fusing data in the real-time environment model and the three-dimensional dynamic model to construct a navigation environment model; and the decision control module is used for carrying out path planning and collision avoidance decision making on ship navigation in combination with an intelligent algorithm according to the navigation environment model and a preset navigation target. Compared with the prior art, the accuracy and adaptability of decision making are improved, and the sailing safety and reliability of the ship in the complex marine environment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent ships, and in particular to an intelligent ship autonomous decision-making system and method based on a metaverse. Background Art

[0002] With the rapid development of science and technology, smart ships, as an important development direction of the shipping industry, are gradually entering the R&D and testing stage from the theoretical conception stage. Smart ships integrate advanced sensor technology, artificial intelligence algorithms, autonomous control systems, etc. to achieve accurate perception of the surrounding environment, autonomous decision-making and efficient navigation. Among them, the intelligent ship autonomous decision-making system based on the Metaverse has pushed this field to a new height. Metaverse technology integrates cutting-edge technologies such as blockchain, Internet of Things, AI, VR / AR, etc., providing a richer data interaction and decision-making support platform for smart ships.

[0003] At present, the autonomous decision-making system of intelligent ships mainly relies on high-precision sensors (such as radar, infrared sensors, cameras, etc.) to collect environmental information, and uses integrated artificial intelligence algorithms to process and analyze data to achieve autonomous collision avoidance, path planning, navigation control and other functions. These systems have improved the navigation safety and efficiency of ships to a certain extent, but there are still many limitations.

[0004] Insufficient data fusion and processing capabilities: Although the existing intelligent ship autonomous decision-making system can collect a large amount of environmental data, it still has deficiencies in data fusion and processing. The redundancy and conflict problems between different sensor data have not been effectively solved, resulting in limited decision-making accuracy.

[0005] Limitations of autonomous decision-making algorithms: The decision-making capabilities of current artificial intelligence algorithms in complex environments still need to be improved. Faced with changing marine environments and emergencies, algorithms often find it difficult to make optimal decisions and may even make misjudgments.

[0006] Communication and network security risks: Smart ships have an increasing demand for high-connectivity and high-security communications, but existing communication technologies cannot fully meet this requirement. At the same time, the risks of cyber attacks and data leakage also threaten the safe operation of smart ships.

[0007] Insufficient energy management and optimization: Smart ships still have shortcomings in energy management, such as battery technology has not yet been fully commercialized, and emerging technologies such as supercapacitors are still in the early stages of development. This limits the further development of smart ships in terms of power energy. Summary of the invention

[0008] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and provide an intelligent ship autonomous decision-making system and method based on the metaverse.

[0009] The purpose of the present invention can be achieved by the following technical solutions:

[0010] An intelligent ship autonomous decision-making system based on Metaverse, characterized by comprising: a data acquisition module, a data processing module, a decision control module and a Metaverse platform, wherein:

[0011] The data acquisition module collects the ship's dynamic information and the physical information of the ship's surrounding environment in real time through sensors;

[0012] The Metaverse platform is used to simulate and analyze the physical information of the environment around the ship to build a real-time environment model, and simulate and analyze the dynamic information of the ship to build a three-dimensional dynamic model;

[0013] A data processing module, which fuses the data in the real-time environment model and the three-dimensional dynamic model to construct a navigation environment model;

[0014] The decision control module is used to perform path planning and collision avoidance decisions for ship navigation based on the navigation environment model and preset navigation goals in combination with intelligent algorithms.

[0015] Furthermore, the system realizes real-time data transmission and processing between various modules through a high-speed communication network.

[0016] Furthermore, the ship dynamic information includes multiple types of the ship's current position, speed and heading, and the physical information includes multiple types of water depth, weather and obstacle positions.

[0017] Furthermore, the data fusion is performed using a multi-source heterogeneous data fusion algorithm, and the steps include multiple steps of data preprocessing, feature extraction, data calibration, and de-duplication fusion.

[0018] Furthermore, the autonomous decision-making system also includes an intelligent energy management module for dynamically adjusting the energy distribution strategy according to the ship's dynamic information and physical information of the ship's surrounding environment.

[0019] Furthermore, the path planning includes global path planning and local path planning.

[0020] Furthermore, the step of global path planning includes:

[0021] According to the preset navigation target, determine the starting point and end point of the global path planning, and find multiple feasible paths from the starting point to the end point;

[0022] In combination with the navigation environment model, the multiple feasible paths are evaluated and optimized in terms of safety, economy and time efficiency, and the optimal path is selected as the global planning path.

[0023] Furthermore, the local path planning uses a local planning algorithm to calculate the optimal route at the next moment based on the global planning path, and the local planning algorithm includes a dynamic window method or a speed obstacle method.

[0024] Furthermore, the steps of making the collision avoidance decision are as follows:

[0025] Based on the environmental information collected in real time by the navigation environment model and the collision avoidance algorithm, potential collision risks are evaluated and predicted;

[0026] Based on the assessment results, a collision avoidance strategy is developed, including automatic steering, speed reduction to avoid, or seeking a course change.

[0027] According to another aspect of the present invention, a method for autonomous decision-making of an intelligent ship based on a metaverse is provided, comprising the following steps:

[0028] The data acquisition module collects the ship's dynamic information and the physical information of the ship's surrounding environment in real time;

[0029] Using the Metaverse platform to simulate and analyze the physical information of the environment surrounding the ship to build a real-time environmental model, and to simulate and analyze the dynamic information of the ship to build a three-dimensional dynamic model;

[0030] The data in the real-time environment model and the three-dimensional dynamic model are integrated through a data processing module to construct a navigation environment model;

[0031] The decision control module is used to perform path planning and collision avoidance decisions for the ship's navigation according to the navigation environment model and the preset navigation target.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. The present invention is based on the Metaverse platform, adopts a multi-source heterogeneous data fusion algorithm, efficiently integrates data from different sensors, constructs a navigation environment model, and combines intelligent algorithms to perform path planning and collision avoidance decisions for ship navigation, thereby improving the accuracy and adaptability of decision-making, ensuring that ships can make the best choice when facing a changing environment, and significantly improving the navigation safety and reliability of ships in complex marine environments.

[0034] 2. The present invention combines two advanced intelligent algorithms, deep learning and reinforcement learning, to construct an autonomous decision-making system. The system can dynamically generate and optimize autonomous decision-making plans based on real-time environmental information and historical navigation data, improve the adaptability and decision-making intelligence level of smart ships in complex marine environments, and effectively respond to various emergencies to ensure the smooth operation of ships and the safety of personnel.

[0035] 3. The present invention dynamically adjusts the energy allocation strategy according to the navigation status of the ship and external environmental conditions through the intelligent energy management module, realizes efficient utilization of energy, introduces new energy technology as auxiliary energy, and further improves the endurance and green environmental protection performance of the intelligent ship.

[0036] 4. The communication security protocol based on blockchain in the present invention has been designed to ensure the security and reliability of smart ships during data transmission. The protocol utilizes the characteristics of blockchain that cannot be tampered with and traceable to ensure the integrity and authenticity of data transmission, and effectively defend against security risks such as network attacks and data leakage. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a system structure diagram of a metaverse-based intelligent ship autonomous decision-making system proposed by the present invention;

[0038] Figure 2 This is a schematic diagram of the relationship between the shore-based command center, the actual sailing ship and the Metaverse simulated sailing ship in the autonomous decision-making process;

[0039] Figure 3 This is a decision flow chart of the autonomous decision-making system proposed in the present invention.

[0040] Legend: 1. System top-level module; 2. Data acquisition module; 3. Data processing module; 4. Metaverse platform; 5. Decision-making control module; 6. Feedback evaluation module; 7. User interaction module. DETAILED DESCRIPTION

[0041] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0042] Example 1

[0043] This embodiment provides an intelligent ship autonomous decision-making system based on the Metaverse. Figure 1 As shown, including:

[0044] Data collection module 2, data processing module 3, decision control module 5 and metaverse platform 4, among which,

[0045] Data acquisition module 2, which collects ship dynamic information and physical information of the ship's surrounding environment in real time through sensors;

[0046] Metaverse Platform 4 is used to simulate and analyze the physical information of the ship's surrounding environment to build a real-time environmental model, and simulate and analyze the dynamic information of the ship to build a three-dimensional dynamic model;

[0047] Data processing module 3, integrating the real-time environment model and the three-dimensional dynamic model to construct a navigation environment model;

[0048] The decision control module 5 is used to plan the path and make collision avoidance decisions for the ship's navigation based on the navigation environment model and the preset navigation target in combination with the intelligent algorithm.

[0049] The autonomous decision-making system realizes real-time data transmission and processing between various modules through a high-speed communication network.

[0050] The steps of fusion using multi-source heterogeneous data fusion algorithm include multiple ones of data input, data preprocessing, feature extraction, data calibration, de-duplication fusion and data output.

[0051] The autonomous decision-making system also includes the top-level module 1, which is responsible for the management and coordination of the entire system, including data exchange and task allocation between modules.

[0052] The autonomous decision-making system also includes an intelligent energy management module, which is used to dynamically adjust the energy distribution strategy based on the ship's dynamic information and the physical information of the ship's surrounding environment.

[0053] The autonomous decision-making system uses blockchain technology to build a secure communication protocol to ensure the immutability and traceability of data transmission. It integrates advanced encryption technology and intrusion detection systems to monitor and defend against network attacks in real time, ensuring the communication and network security of smart ships.

[0054] This embodiment takes a navigation mission as an example. The relationship between the shore-based command center, the actual navigation ship, and the Metaverse simulated navigation ship in the autonomous decision-making process is shown in the figure below. Figure 2 As shown, the actual navigation state ship will collect the navigation information data collected in real time by the data acquisition module 2 and feed it back to the shore-based command and control center. The shore-based command and control center will send the ship's real-time navigation data and various simulation analysis instructions to the Metaverse simulated navigation state ship. The Metaverse platform 4 simulates and analyzes the real-time navigation data and feeds back the analysis results to the shore-based command and control center in real time. The shore-based command and control center determines the feasibility of the simulation analysis results and sends execution / decision instructions to the actual navigation state ship. The Metaverse simulated navigation state ship and the actual navigation state ship are interactively and parallelly controlled by the Metaverse.

[0055] The intelligent ship autonomous decision-making system based on the metaverse proposed in this embodiment can be divided into the following important stages:

[0056] S1. Task reception and initialization

[0057] Mission reception: Smart ships receive navigation mission instructions, including key information such as the starting point, end point, estimated sailing time, cargo type and quantity, etc. This information may come from shipowners, freight forwarders or shipping management systems.

[0058] System initialization: The system is initialized according to the mission instructions, including checking the ship status (such as fuel, fresh water, food reserves, etc.), confirming the feasibility of the navigation plan, and starting the metaverse data interface to prepare for receiving virtual environment data.

[0059] S2. Environmental perception and data fusion

[0060] Environmental perception: Real-time environmental information and ship dynamic information around the ship are collected in real time through sensors such as radar, sonar, camera, weather station, etc. Real-time environmental information includes hydrological conditions, meteorological conditions, obstacle locations, etc. Ship dynamic information includes the ship's current position, speed, heading and other dynamic information.

[0061] Using real-time environmental data, a real-time environmental model is constructed by conducting virtual environmental simulation analysis through the Metaverse Platform 4. The virtual environmental data includes simulated sea conditions, predicted weather, virtual waterways, and other virtual ship dynamics.

[0062] Using the ship's dynamic information, the Metaverse Platform 4 conducts simulation analysis to construct a three-dimensional dynamic model.

[0063] The real-time environment model is integrated with the data of different formats and structures in the 3D dynamic model to form a more comprehensive and accurate navigation environment model. This process involves the application of data cleaning, calibration, association and fusion algorithms.

[0064] The construction process of the 3D dynamic model includes:

[0065] Obtain information on the ship's geometry, structure, performance parameters, etc. from multiple sources such as ship design documents, historical navigation data, and real-time sensor data. Clean, verify, and format the collected data to ensure data accuracy and consistency.

[0066] The 3D modeling tools provided by the Metaverse Platform 4, such as 3D modeling software, virtual reality (VR) technology, etc., are used to construct a 3D model of the ship based on the preprocessed data. In the model, various parts of the ship, such as the hull, deck, propulsion system, navigation equipment, etc., are represented in detail, and the accuracy and realism of the model are ensured.

[0067] On the basis of the 3D model, a physical engine and dynamic simulation algorithm are added to simulate the dynamic behavior of the ship under different sailing conditions, including the ship's sailing track, attitude changes, force conditions, etc., to achieve real-time prediction and simulation of the ship's motion state.

[0068] Optimize the 3D dynamic model to improve the model's calculation efficiency and accuracy. Verify and compare the model with actual navigation data to ensure its accuracy and reliability.

[0069] The construction process of the real-time environment model includes:

[0070] By using sensor networks, weather forecast systems, hydrological monitoring stations, etc., data on the ship's surrounding environment is collected in real time, including environmental parameters such as wind speed, wind direction, water flow speed, water temperature, and sea conditions.

[0071] Based on the collected environmental data, the environmental modeling tool of the Metaverse Platform 4 is used to build a real-time environmental model. The environmental model is dynamically updated according to the changes in the real-time environmental data, including the geometric shape, physical parameters and state of the environment, so as to achieve real-time perception and prediction of the environment.

[0072] S3. Autonomous decision-making and planning

[0073] The real-time environment model is integrated with the three-dimensional dynamic model to construct a navigation environment model, forming a complete metaverse environment. Based on the integrated navigation environment model, the virtual navigation process of the ship is simulated, and the risks that may be encountered during the navigation process are evaluated, including collision risk, grounding risk, bad weather risk, etc.

[0074] According to the risk assessment results and navigation mission requirements, the path planning algorithm (such as the improved A* algorithm, RRT algorithm, etc.) is used to generate the optimal navigation path. This path will comprehensively consider factors such as safety, efficiency and economy.

[0075] During the path planning process, collision avoidance strategies are developed to deal with dynamic obstacles that may be encountered (such as other ships, buoys, etc.). These strategies may include automatic steering, slowing down to avoid, or seeking channel changes.

[0076] The overall process and steps of the autonomous decision-making system for ship navigation path planning and collision avoidance decision-making are as follows: Figure 3 As shown:

[0077] According to the preset navigation target, the starting point and end point of the global path planning are determined, and intelligent algorithms (such as A* algorithm, Dijkstra algorithm, etc.) are used to search for paths to find multiple feasible paths from the starting point to the end point. Combined with the navigation environment model, multiple feasible paths are evaluated and optimized in terms of safety, economy and time efficiency, and the optimal path is selected as the global planning path.

[0078] During the navigation process of the ship, the dynamic environmental information around the ship is perceived in real time through the sensor network, including the position, speed, heading, etc. of other ships; based on the real-time perceived information, the global planning path is dynamically updated and adjusted.

[0079] On the basis of the global planning path, local planning algorithms (such as dynamic window method, speed obstacle method, etc.) are used to calculate the optimal route at the next moment to avoid collision with dynamic and static obstacles; the ship's maneuvering characteristics and navigation rules are considered to ensure the smoothness and continuity of the local path.

[0080] Based on real-time perception information and collision avoidance algorithms (such as PIDVCA algorithm, etc.), potential collision risks are evaluated and predicted; based on the evaluation results, collision avoidance strategies are formulated, including adjusting heading, speed, etc., to ensure the safe navigation of the ship.

[0081] S4. Instruction execution and feedback

[0082] The navigation strategy and collision avoidance instructions generated by autonomous decision-making are converted into specific control instructions and sent to the ship's execution control unit. These instructions may include heading adjustment, speed control, rudder angle adjustment, etc.

[0083] The ship's execution control unit receives the command and executes the corresponding operation, while the monitoring system provides real-time feedback on the execution status and effect. This includes real-time monitoring of parameters such as the ship's position, speed, and heading, as well as any abnormalities during the execution process.

[0084] The execution results and new environmental data are input into the data processing module 3 again to form a closed-loop feedback mechanism. The system continuously optimizes the decision-making algorithm and navigation strategy based on the feedback results to improve the accuracy and adaptability of autonomous decision-making.

[0085] S5. Safety and emergency response

[0086] Real-time monitoring of safety conditions during navigation, including ship status, environmental changes, and potential threats. Once an emergency is detected (such as a sharp increase in collision risk, equipment failure, etc.), the system immediately initiates an emergency response mechanism. This may include automatic collision avoidance operations, issuing an alarm to notify the crew or the shore control center, and adjusting navigation strategies to avoid danger.

[0087] S6. Mission completion and summary

[0088] When the ship successfully reaches the destination and completes all navigation tasks, the system records key data and performance indicators during the navigation process.

[0089] The feedback evaluation module 6 generates a navigation summary report, including navigation track, decision records, performance indicators, problems encountered and solutions, etc. This report is not only used to summarize and analyze this navigation mission, but also provides reference and reference for subsequent navigation missions.

[0090] The autonomous decision-making system also includes a user interaction module 7, which allows users to easily remotely control and monitor the intelligent ship to ensure the safe and efficient operation of the ship. The user interaction module 7 can display various information of the system, such as the basic information such as the current position, speed, and heading of the ship, as well as key information such as the system's operating status and decision results. At the same time, it can also provide real-time feedback, such as system alarms and abnormal prompts, to help users understand the system's operating status in a timely manner and take corresponding measures. In order to meet the needs and scenarios of different users, the user interaction module 7 usually supports multiple interaction methods, including: conventional input devices such as keyboards and mice and new interaction methods such as touch screens and voice recognition.

[0091] The specific steps of the autonomous decision-making system using advanced algorithms such as reinforcement learning and deep learning for path planning and collision avoidance decisions include:

[0092] (1) Data collection and preprocessing

[0093] Use shipboard sensors (such as radar, sonar, cameras, etc.) to perceive the navigation environment around the ship in real time, including waterways, obstacles, weather conditions, etc. Convert the perceived data into a format that the system can recognize, such as digital signals or images.

[0094] The sensed data is cleaned, denoised and calibrated to improve the accuracy and reliability of the data. The processed data is input into the deep learning model for feature extraction and classification.

[0095] (2) Deep learning model construction and training

[0096] Build deep learning models, such as convolutional neural networks (CNN) (for processing large images and efficient recognition) and recurrent neural networks (RNN) (for natural language processing), to extract key features in the navigation environment. Design the model’s input layer, hidden layer, and output layer, as well as the corresponding activation function and loss function, based on specific needs.

[0097] Use historical navigation data or simulation data to train the deep learning model so that it can accurately identify obstacles, waterways and other information in the navigation environment. By adjusting the parameters and structure of the model, the performance of the model is optimized to improve the accuracy and efficiency of recognition.

[0098] According to the specific application scenarios and requirements, select appropriate reinforcement learning algorithms, such as Q-learning, deep Q network (DQN), policy gradient method, etc. Design the state space, action space and reward function of reinforcement learning to reflect the complexity of the navigation environment and the autonomous decision-making needs of the ship.

[0099] By using the reinforcement learning algorithm, the intelligent ship can conduct multiple trial and error learning in the simulation environment and gradually optimize its navigation strategy. By continuously adjusting the reward function and strategy parameters, the intelligent ship can achieve the optimization of path planning while ensuring safety.

[0100] In the actual navigation process, the intelligent ship uses the reinforcement learning algorithm to formulate a navigation strategy based on the real-time perceived navigation environment and the output results of the deep learning model. According to the strategy, the optimal navigation path and collision avoidance measures are selected, such as adjusting the heading and speed, to achieve autonomous navigation and collision avoidance decisions.

[0101] (4) System verification and testing

[0102] The autonomous decision-making system of the intelligent ship is tested in a simulation environment to verify the effectiveness and accuracy of its path planning and collision avoidance decisions. Based on the test results, the system is optimized and improved to improve its performance and reliability.

[0103] The autonomous decision-making system of the smart ship is tested under actual navigation conditions to verify its adaptability and robustness in complex navigation environments. Based on the test results, the system is further adjusted and optimized to ensure its stability and reliability in actual applications.

[0104] In summary, the specific steps of using advanced algorithms such as reinforcement learning and deep learning for path planning and collision avoidance decision-making in the decision-making stage include data collection and preprocessing, deep learning model construction and training, reinforcement learning algorithm application and decision-making, and system verification and testing. These steps together constitute the core part of the intelligent ship autonomous decision-making system, providing strong technical support for the realization of autonomous navigation and collision avoidance decisions of intelligent ships.

[0105] The autonomous decision-making system also includes an intelligent energy management module, which is used to dynamically adjust the energy allocation strategy based on the ship's dynamic information and the physical information of the ship's surrounding environment to achieve efficient energy utilization and autonomous decision-making of the ship. The specific steps for this module to dynamically adjust the energy allocation strategy include:

[0106] (1) Data collection and preprocessing

[0107] Through sensors, GPS and other equipment, the ship's navigation status, speed, position, heading and other dynamic information are collected in real time. Meteorological sensors, hydrological sensors and other equipment are used to collect physical information about the ship's surrounding environment, such as wind speed, wind direction, water flow speed, water temperature, etc.

[0108] The collected data is cleaned, verified and formatted to ensure the accuracy and consistency of the data. The processed data is stored in the database for subsequent analysis and decision-making.

[0109] (2) Energy demand forecast

[0110] Use machine learning or deep learning algorithms to establish a ship energy demand prediction model. The model can predict future energy demand based on historical data and current ship dynamic information and environmental physical information. Use historical data to train the prediction model to optimize the model's prediction performance. Continuously collect new data and iteratively optimize the model to improve the accuracy and stability of the prediction.

[0111] (3) Adjustment of energy allocation strategy

[0112] Based on the results of the forecast model, analyze the energy demand of the ship in different sailing phases and environments. Identify the peaks and troughs of energy demand, as well as potential energy waste.

[0113] According to the analysis results of energy demand, a dynamic energy allocation strategy is formulated. The strategy should take into account factors such as ship navigation safety, energy efficiency optimization and environmental protection.

[0114] According to the formulated energy allocation strategy, the energy supply of each system of the ship can be adjusted in real time. For example, when the wind speed is high, the output of the wind power generation system can be increased; when the water flow is turbulent, the energy consumption of the propulsion system can be optimized.

[0115] (4) Monitoring and feedback

[0116] Through the intelligent energy management module, the ship's energy usage and the implementation effect of the allocation strategy can be monitored in real time. Abnormal situations can be discovered and handled in a timely manner to ensure the safe operation of the ship and the efficient use of energy.

[0117] The energy allocation strategy is continuously optimized and adjusted based on the monitoring results and the actual needs of ship operations. Through continuous learning and iteration, the autonomous decision-making ability and energy efficiency optimization effect of the intelligent energy management module are improved.

[0118] The autonomous decision-making system uses blockchain technology to ensure the authenticity, integrity and credibility of ship operation data. The specific steps to ensure the security and immutability of data include:

[0119] (1) Data collection and encryption

[0120] First, smart ships will collect various operating data in real time, such as navigation track, speed, fuel consumption, equipment status, etc. These data will be encrypted immediately after collection to ensure that they are not stolen or tampered with during transmission. The encryption process can use the hash function and public key encryption technology in the blockchain to convert the data into a secure hash value or encrypted form.

[0121] (2) Distributed Storage

[0122] The encrypted data will be stored on multiple nodes of the blockchain network, rather than being stored on a single centralized server. This distributed storage structure requires tampering with multiple nodes at the same time to tamper with the data on the blockchain, which greatly increases the difficulty of tampering.

[0123] (3) Consensus Mechanism

[0124] In a blockchain network, each node needs to reach a consensus on data changes through a consensus mechanism. Common consensus mechanisms include proof of work (PoW), proof of stake (PoS), etc. Autonomous decision-making systems can choose a consensus mechanism that suits their needs to ensure that the data stored by all nodes is consistent.

[0125] (4) Data immutability

[0126] Once data is written to the blockchain, it is difficult to change or delete. New data can only be updated by adding new blocks, while previous data is permanently stored in the blockchain. Each block in blockchain technology contains the hash value of the previous block, forming a chain structure. This structure makes it extremely difficult to modify data, because once a block is modified, the hash values ​​of all subsequent blocks will change, thus exposing the fact of tampering.

[0127] (5) Data Verification and Access Control

[0128] In autonomous decision-making systems, blockchain technology can also be used for data verification and access control. By verifying the hash value and digital signature of the data, the authenticity and integrity of the data can be ensured. At the same time, by setting access rights and encryption keys, it is possible to control which users or devices can access or modify the data.

[0129] (6) Integration with the Metaverse

[0130] Combining blockchain technology with the Metaverse can further enhance the security and credibility of the intelligent ship autonomous decision-making system. For example, a virtual ship operating environment is created in the Metaverse, and the actual ship's operating data is synchronized to the virtual environment in real time. Blockchain technology is used to ensure the security and non-tamperability of these data, thereby achieving real-time monitoring of the ship's operating status and autonomous decision-making.

[0131] Example 2

[0132] This embodiment provides a method for autonomous decision-making of an intelligent ship based on the Metaverse, comprising the following steps:

[0133] The data acquisition module 2 collects the ship's dynamic information and the physical information of the ship's surrounding environment in real time;

[0134] The Metaverse Platform 4 is used to simulate and analyze the physical information of the ship's surrounding environment to build a real-time environmental model, and to simulate and analyze the ship's dynamic information to build a three-dimensional dynamic model;

[0135] The data in the real-time environment model and the three-dimensional dynamic model are integrated through the data processing module 3 to construct a navigation environment model;

[0136] The decision control module 5 is used to perform path planning and collision avoidance decisions for the ship's navigation according to the navigation environment model and the preset navigation target.

[0137] The rest is the same as in Example 1.

[0138] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. An intelligent ship autonomous decision-making system based on the metaverse, characterized in that: include: A data acquisition module (2), a data processing module (3), a decision control module (5) and a metaverse platform (4), wherein: The data acquisition module (3) collects ship dynamic information and physical information of the ship's surrounding environment in real time through sensors; The metaverse platform (4) is used to simulate and analyze the physical information of the environment surrounding the ship to construct a real-time environment model, and to simulate and analyze the dynamic information of the ship to construct a three-dimensional dynamic model; The data processing module (3) fuses the data in the real-time environment model and the three-dimensional dynamic model to construct a navigation environment model; The decision control module (5) is used to perform path planning and collision avoidance decision-making for ship navigation based on the navigation environment model and the preset navigation target in combination with an intelligent algorithm.

2. The intelligent ship autonomous decision-making system based on the metaverse according to claim 1 is characterized in that: The autonomous decision-making system realizes real-time data transmission and processing between various modules through a high-speed communication network.

3. The intelligent ship autonomous decision-making system based on the metaverse according to claim 1 is characterized in that: The ship dynamic information includes multiple types of the ship's current position, speed and heading, and the physical information includes multiple types of water depth, weather and obstacle positions.

4. The intelligent ship autonomous decision-making system based on the metaverse according to claim 1 is characterized in that: The data fusion is performed using a multi-source heterogeneous data fusion algorithm, and the steps include multiple steps of data preprocessing, feature extraction, data calibration, and de-duplication fusion.

5. The intelligent ship autonomous decision-making system based on metaverse according to claim 1 is characterized in that: The autonomous decision-making system also includes an intelligent energy management module, which is used to dynamically adjust the energy distribution strategy according to the ship dynamic information and the physical information of the ship's surrounding environment.

6. The intelligent ship autonomous decision-making system based on the metaverse according to claim 1 is characterized in that: The path planning includes global path planning and local path planning.

7. The intelligent ship autonomous decision-making system based on the metaverse according to claim 6 is characterized in that: The steps of global path planning include: According to the preset navigation target, determine the starting point and end point of the global path planning, and find multiple feasible paths from the starting point to the end point; In combination with the navigation environment model, the multiple feasible paths are evaluated and optimized in terms of safety, economy and time efficiency, and the optimal path is selected as the global planning path.

8. The intelligent ship autonomous decision-making system based on the metaverse according to claim 7 is characterized in that: The local path planning uses a local planning algorithm to calculate the optimal route at the next moment based on the global planning path. The local planning algorithm includes a dynamic window method or a speed obstacle method.

9. The intelligent ship autonomous decision-making system based on the metaverse according to claim 1 is characterized in that: The steps of making the collision avoidance decision are as follows: Based on the environmental information collected in real time by the navigation environment model and the collision avoidance algorithm, potential collision risks are evaluated and predicted; Based on the assessment results, a collision avoidance strategy is developed, including automatic steering, speed reduction to avoid, or seeking a course change.

10. A method for autonomous decision-making of intelligent ships based on Metaverse, characterized in that: The following steps are involved: The data acquisition module (2) collects the dynamic information of the ship and the physical information of the surrounding environment of the ship in real time; Using the Metaverse platform (4) to simulate and analyze the physical information of the environment surrounding the ship to construct a real-time environment model, and to simulate and analyze the dynamic information of the ship to construct a three-dimensional dynamic model; The data in the real-time environment model and the three-dimensional dynamic model are integrated through a data processing module (3) to construct a navigation environment model; A decision control module (5) is used to perform path planning and collision avoidance decision-making for the ship's navigation according to the navigation environment model and the preset navigation target.

Images