Information interactive inland river ferryboat navigation collision avoidance decision-making system and method

Abstract

The invention relates to an information interactive inland river ferry navigation collision avoidance decision system and method. The system comprises a data storage module, a data processing and analysis module and a data visualization module. The data storage module is used for storing dynamic data, static data and ship information; the data processing and analyzing module is used for intelligently cleaning, screening and preprocessing the stored data; and the data visualization module is used for presenting the ship navigation data to a user through a real-time map interface. According to the invention, accurate simulation and efficient control of ship behaviors can be realized, more reliable and visual driving guidance and decision support can be provided for sailors, and the safety and efficiency of ferry navigation are further improved.

Description

Technical Field

[0001] The present invention relates to the field of shipping safety and intelligent transportation, and more specifically, to an information interactive inland river ferry navigation collision avoidance decision-making system and method. Background Art

[0002] Existing technologies have achieved the development of ship navigation systems to a certain extent, but lack specific analysis of specific application scenarios of inland ferries.

[0003] In terms of simulation system construction and implementation, Chinese patent CN116610125A solves the problem of autonomous collision avoidance decision-making and collaborative processing between the ship and the cooperative obstacle ship to a certain extent; Chinese patent CN110175186A can realize data collection and target perception through shipborne equipment. This method can better realize the simulation between the ship and the target ship, and between the ship and the ship, but it does not take into account the complex encounter scenarios between multiple ships and present them intuitively, nor does it consider the mutual influence between ships (intelligent bodies), and the analysis of the application scenarios of inland ferries is shallow.

[0004] Based on the ship collision avoidance decision, the velocity obstacle method has attracted attention because it can realize the combination of risk and avoidance decision. The velocity obstacle (VO) model was first proposed by Degré et al., and was initially applied to surface unmanned boats, and was later introduced into ship collision avoidance decision. Hernandez et al. combined the velocity obstacle method with the kinematic model, transformed the local avoidance problem into a multi-objective optimization problem, and then combined the particle swarm optimization algorithm for path planning and collision avoidance decision. Yu et al. combined the velocity obstacle method with the A* algorithm, and proposed a hybrid collision avoidance path planning method based on COLREG, which can realize global and local path planning at the same time. Zhang et al. proposed a ship dynamic path planning method based on uncertain speed obstacles, which expanded the relative cone angle of traditional speed obstacles using the robustness idea, and divided the ship speed set into three feasible subsets to achieve path planning that complies with COLREG. Cheng et al. combined speed obstacles with the ship field and proposed a new collision risk detection method for multi-ship collisions. Zhang et al. used an improved speed barrier algorithm to construct a collision avoidance method for a single ship in a tight encounter situation, but this method only considers the ship as an independent individual and does not consider the mutual influence between ships. The existing system does not refine the scenario of multiple ferries crossing the channel in the inland river scenario and the data display to assist decision-making. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide an information interactive inland ferry navigation collision avoidance decision-making system and method, which significantly improves the navigation safety and decision-making efficiency of the ferry in complex waterway scenarios by efficiently integrating data processing, intelligent algorithm application and real-time environmental interaction.

[0006] The technical solution adopted by the present invention to solve the technical problem is: constructing an information interactive inland river ferry navigation collision avoidance decision-making system, including a data storage module, a data processing and analysis module and a data visualization module;

[0007] The data storage module is used to store dynamic data, static data and ship information;

[0008] The data processing and analysis module is used to intelligently clean, screen and preprocess the stored data;

[0009] The data visualization module is used to present the ship navigation data to the user through a real-time map interface.

[0010] According to the above scheme, the dynamic data includes the ship's position, speed, heading and acceleration, and the static data includes the ship's type, load, size and navigation history.

[0011] The present invention also provides an information interactive inland river ferry navigation collision avoidance decision-making method, comprising the following steps:

[0012] S1. Build the main system architecture;

[0013] S2, construct an integrated risk characterization algorithm for ferry crossing navigation as the core decision algorithm;

[0014] S3. Complete the hull modeling and build a closed-loop control model framework for the ship model to achieve seamless connection between the ship model and the remote driving system.

[0015] According to the above scheme, in step S1, a comprehensive Web application is developed based on the Django framework, the MySQL database is integrated for data storage and management, the Three.js library is used to realize 3D graphics display on the front end, and WebSocket communication is realized through Django Channels.

[0016] According to the above scheme, WebSocket communication is implemented through the following methods:

[0017] In the models.py file of the application, after defining the database model using Django's ORM object-relational mapping technology, generate a migration file through the manage.py makemigrations command. The migration file records the changes in the model and is used to create or modify the table structure in the database;

[0018] In the settings.py configuration file of the Django project, connect to the MySQL database by setting the DATABASES configuration item, configure the INSTALLED_APPS list, and configure the ASGI asynchronous server gateway interface application of Django Channels;

[0019] WebSocket routing defines the endpoints of WebSocket connections and their corresponding consumers;

[0020] Use WebSocket to establish a persistent connection between the front-end and the back-end to achieve real-time data transmission, and receive data in the Three.js environment to dynamically render the trajectory effect.

[0021] According to the above scheme, the front-end and back-end data transmission is realized by the following methods:

[0022] Use WebSocket to establish a persistent connection between the front-end and the back-end to achieve real-time data transmission, dynamically receive the information of the ship's plane coordinates, acceleration, and speed, and receive the information in the Three.js environment to dynamically render the ship's trajectory effect. The back-end sets a WebSocket server, which can monitor the connection request from the front-end and send JSON format data containing trajectory information in real time after the connection is established;

[0023] The front end uses requestAnimationFrame to create an animation loop, which continuously calls the render method of the renderer to update and render the scene. In each loop, it checks whether there is new data arriving from WebSocket, and updates the status of the track points and track lines according to the new data.

[0024] Start the development server with Django’s manage.py runserver command.

[0025] According to the above scheme, in step S2, the construction of the core decision algorithm includes four core cost functions, and the core cost functions are as follows:

[0026] (1) The cost function of navigation economy is:

[0027] U eco =k1·f(x t ,y t ,x goal ,y goal ) (1)

[0028] Among them, (x t ,y t ) is the position coordinate of the ferry at time t, (xgoal, y goal ) is the coordinate of the target point, k1 is the weight coefficient of the utility function;

[0029] (2) The crossing risk cost is:

[0030]

[0031] Among them, t0 is the current time, Δt is the predicted time, CSR t is the crossing risk predicted at time t0, k2 is the utility function U risk The weight coefficient of

[0032] (3) The cost of heading keeping is:

[0033] U heading =k3·f(θ max ,θ current ) (3)

[0034] Among them, k3 is the utility function U heading Weight coefficient, θ max is the maximum steering angle, θ current is the current heading angle;

[0035] (4) Rule Constraint Cost Function

[0036]

[0037] According to the above scheme, in step S3, the hull modeling is completed by the following method to build a closed-loop control model framework for the ship model:

[0038] S301. Use computer-aided design to design the response characteristics of the ship under different working conditions. The hull modeling includes the structural characteristics, mass distribution, hydrodynamic characteristics and maneuverability of the ship;

[0039] S302. Based on the hull modeling results, a closed-loop control model framework is designed and implemented, wherein the framework integrates multiple modules of sensor simulation, control algorithm, and actuator simulation to form a closed-loop feedback system.

[0040] According to the above scheme, in step S302, the control algorithm module calculates the optimal ship maneuvering instructions based on the ship status information and the surrounding environment information, combined with the preset collision avoidance rules and path planning strategies, and the actuator simulation module converts the ship maneuvering instructions into the actual motion response of the ship, completing the entire closed-loop control process.

[0041] The information interactive inland river ferry navigation collision avoidance decision system and method of the present invention has the following beneficial effects:

[0042] 1. The present invention improves navigation safety and intelligence level. Based on the improved speed barrier algorithm and dynamic window method, it realizes the optimization of collision avoidance decision-making in multi-ship encounter scenarios. It can dynamically evaluate navigation risks in real time during the ferry crossing process, and automatically adjust the speed and heading to effectively avoid the occurrence of collision accidents. The high-precision risk quantification and collision avoidance scheme are particularly suitable for complex multi-ship intersection scenarios in inland waterways, greatly improving the safety and intelligence level of navigation;

[0043] 2. The real-time data interaction and visualization display of the present invention enables the driver to fully grasp the navigation environment of the ferry and the dynamic information of surrounding ships through the real-time display of three-dimensional simulation scenes and ship navigation data. With the help of the information interaction platform, the driver can track the risk changes in real time and adjust the operation strategy in time. This function not only improves the decision-making efficiency of the driver, but also enhances the adaptability and stability of the system in complex environments;

[0044] 3. The commercial prospects of this invention are broad. It can be widely used in the fields of inland waterway management, ferry dispatching and intelligent navigation, meeting the needs of future smart transportation development. Its intelligent collision avoidance decision-making ability and flexible risk assessment mechanism will help promote the transformation of the inland waterway shipping industry towards a more efficient, safe and green direction. It has huge market demand, especially in the context of increasing shipping volume. It can effectively improve waterway utilization, reduce accident rates, and bring significant economic benefits.

[0045] 4. The low cost and high efficiency of the present invention reduces the dependence on expensive hardware equipment through the optimization of intelligent algorithms, and has high economy in terms of energy consumption. The efficient path planning function can shorten the voyage, save fuel consumption, and reduce operating costs. It can be flexibly deployed through miniaturized sensors and communication equipment, and is suitable for large-scale promotion and application. It is not only technologically innovative and can significantly improve the ferry's collision avoidance capability and safety, but also has broad market application prospects, providing efficient and reliable technical guarantees for the future intelligent navigation of inland ferries. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0047] Figure 1 This is a system overall architecture diagram of the information interactive inland river ferry navigation collision avoidance decision system of the present invention;

[0048] Figure 2 It is a navigation environment real-time simulation interface diagram of the present invention;

[0049] Figure 3 It is a trajectory display diagram of the present invention;

[0050] Figure 4It is a side view of the structural design of the present invention;

[0051] Figure 5 It is a top view of the structural design of the present invention;

[0052] Figure 6 It is a simulation interface diagram of a ship navigation encounter scene of the present invention;

[0053] Figure 7 It is a simulation interface diagram of the system of the present invention for the ship navigation cross-crossing scene;

[0054] Figure 8 It is a simulation interface diagram of the present invention for a complex scene encountered by multiple ships during navigation;

[0055] Fig. 9 Invention information System architecture diagram of interactive inland ferry navigation collision avoidance decision system;

[0056] Fig.10 Appearance diagram of the invented ship model. DETAILED DESCRIPTION

[0057] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0058] like Figure 1-10 As shown, the information interactive inland ferry navigation collision avoidance decision-making system of the present invention includes a data storage module, a data processing and analysis module and a data visualization module.

[0059] The data storage module is used to efficiently and reliably store all data related to inland ferry navigation. The data storage module includes dynamic data, dynamic data and basic transmission information. The dynamic data includes ship position, speed, heading, acceleration, etc., and the static data includes ship type, load, size, navigation history, etc. The data storage module adopts efficient data structure and database technology to ensure the real-time update and persistent preservation of data, and provide accurate and complete basic data for subsequent data processing and analysis. The data processing and analysis module is used to intelligently clean, screen and preprocess the stored data. Through the built-in algorithm model, the data processing and analysis module conducts in-depth analysis of the dynamic behavior, navigation environment, potential risks, etc. of the ferry, and evaluates the collision avoidance risk in real time. Combined with the ship's navigation path, surrounding environment and dynamic data of other ships, it automatically generates risk and navigation data, and performs collision avoidance path planning based on this. The data visualization module is used to present complex ship navigation data to users in an intuitive and easy-to-understand way. Through the real-time updated map interface, the module displays the current position, speed, navigation trajectory and other key data of the ferry, and clearly marks the specific risk value of the current ferry, providing decision makers with accurate visual reference.

[0060] The present invention also provides an information interactive inland river ferry navigation collision avoidance decision-making method, designs the overall architecture of the inland river ferry navigation collision avoidance system, including built-in algorithm application and three-dimensional scene display, so as to realize real-time monitoring of ferry action status, timely risk prediction and optimal path display, provide a concise ship front-end interactive interface, and assist the crew in driving decision-making, including the following steps:

[0061] S1. Build the main system architecture

[0062] The front-end interface of the ship navigation system visualization has two parts: one is the real-time calculation results of the algorithm, that is, the algorithm's optimal action state solution and predicted trajectory; the other is the real-time simulation of the navigation situation in the current waters, including the navigation data information of the ship and the real-time simulation results of the navigation trajectories of surrounding ships. The function of this visualization module is to monitor the ship's status and the current water environment in real time, allowing the crew to interact with the surrounding ferry environment in real time, and assisting the crew in driving. The front-end interface displays Figure 2 shown.

[0063] This system is a comprehensive Web application developed based on the Django framework. It deeply integrates the MySQL database for data storage and management, uses the Three.js library to achieve rich 3D graphics display on the front end, and implements WebSocket communication through Django Channels to provide users with real-time and dynamic data interaction experience. The entire system follows the development principles of efficiency, scalability and ease of maintenance from environment construction, project creation, model definition, routing configuration, consumer writing to the implementation of front-end pages and 3D scenes. It is tested and verified through Django's development server to ensure that after the functions are perfected, they can be seamlessly deployed to the production environment to provide users with stable and reliable services.

[0064] Start a new project through Django's command line tool django-admin, which generates the basic structure of the project, including management commands, configuration files, etc. In the project directory, use the manage.py startapp command to create a Django application, which contains logical components such as models, views, and templates.

[0065] In the models.py file of the application, the database models are defined using Django's ORM (object-relational mapping) technology. These models inherit Django's Model class and use class attributes to declare the fields of the database table. Subsequently, the migration files are generated by the manage.py makemigrations command, which records the changes of the model and can be used to create or modify the table structure in the database. Use the manage.py migrate command to apply these migrations to the database.

[0066] In the Django project's settings.py configuration file, connect to the MySQL database by setting the DATABASES configuration item and configure the INSTALLED_APPS list. Also configure the Django Channels ASGI (Asynchronous Server Gateway Interface) application, which usually involves modifying the asgi.py file to use the Channels Application instance and registering the WebSocket route in it.

[0067] WebSocket routing defines the endpoints of a WebSocket connection and its corresponding consumer. In Django Channels, a consumer is an asynchronous Python class that handles events such as the establishment of a WebSocket connection, the reception and sending of messages, etc. Define the consumer class in the application's consumers.py file and use the Channels routing system to associate it with a specific URL pattern.

[0068] Use WebSocket to establish a persistent connection between the front-end and the back-end to achieve real-time data transmission, and receive this data in the Three.js environment to dynamically render the trajectory effect. First, set up a WebSocket server on the back-end. The WebSocket server can listen to the connection request from the front-end and send JSON format data containing trajectory information in real time after the connection is established. The front-end creates a WebSocket object through JavaScript and connects to the back-end server, while listening to the onmessage event to receive data.

[0069] The transmission methods of front-end data and back-end data are as follows:

[0070] Use WebSocket to establish a persistent connection between the front-end and the back-end to achieve real-time data transmission, dynamically receive the ship's plane coordinates, acceleration, speed and other information, and receive these data in the Three.js environment to dynamically render the ship's trajectory effect. The back-end needs to set up a WebSocket server, which can listen to the connection request from the front-end and send JSON format data containing trajectory information in real time after the connection is established. The front-end creates a WebSocket object through JavaScript and connects to the back-end server, while listening to the onmessage event to receive data. Then, in the Three.js scene, use this information to dynamically update the position of the trajectory point. If you need to draw a trajectory line, you can create a corresponding line object and dynamically add new points to the line as new data arrives.

[0071] In order to keep the track real-time, the front end uses requestAnimationFrame to create an animation loop, which continuously calls the render method of the renderer to update and render the scene. In each loop, it checks whether there is new data arriving from WebSocket, and updates the status of the track points and track lines according to the new data, such as Figure 3 shown.

[0072] In order to optimize performance and user experience, strategies such as data compression, reducing rendering load, and controlling animation frame rate are adopted. At the same time, developer tools and performance analysis tools are used during the development process to monitor WebSocket connections, data transmission, and rendering performance to ensure the stability and efficiency of the application.

[0073] Finally, start the development server with Django's manage.py runserver command. The development server will listen to a local port (8000 by default) and handle HTTP and WebSocket requests from the browser. Open the application URL in the browser to see the loading of the front-end page and the 3D ship model, as well as the real-time communication effect of the WebSocket connection. Once the development is complete and fully tested, you can use server software such as Nginx, Gunicorn, etc. to deploy the application to the production environment, and use Channels' daphne server or other ASGI-compatible servers to handle WebSocket connections.

[0074] S2. Construct an integrated risk characterization algorithm for ferry crossing navigation as the core decision-making algorithm; the algorithm comprehensively considers ship maneuverability and environmental factors to provide real-time risk quantification warning and path planning for ship collision avoidance.

[0075] It is proposed to abstract the navigation decision of ferry crossing the waterway into the process of iterative selection of speed and heading in the feasible speed field and under dynamic constraints, and the key point is to solve the problem of constructing iterative selection criteria. The main research is: 1) In view of the needs of ferry collision avoidance algorithm for real-time, low complexity and flexibility, it is proposed to establish multiple cost functions to evaluate multiple trajectories under the speed obstacle model. The function integrates the key influencing factors of ferry crossing navigation decision, including but not limited to crossing risk, crossing intention, navigation economy, etc.; 2) Introduce utility function to ensure that each decision is made under the framework of utility maximization. The optimal state of each selection output will be used to update the next round of path planning and risk quantification.

[0076] The construction of the core decision algorithm includes four core cost functions, which are as follows:

[0077] (1) Navigation economic cost function:

[0078] U eco =k1·f(x t ,y t ,x goal ,y goal ) (1)

[0079] Among them, (x t ,y t ) is the position coordinate of the ferry at time t, (x goal, y goal ) is the coordinate of the target point, and k1 is the weight coefficient of the utility function.

[0080] (2) Crossing risk cost:

[0081]

[0082] Among them, t0 is the current time, Δt is the predicted time, CSR t is the crossing risk predicted at time t0, k2 is the utility function U risk The weight coefficient of .

[0083] (3) Course keeping cost:

[0084] U heading =k3·f(θ max ,θ current ) (3)

[0085] Among them, k3 is the utility function U heading Weight coefficient, θ max is the maximum steering angle, θ current is the current heading angle.

[0086] (4) Rule constraint cost function:

[0087]

[0088] In order to ensure that the ferry can safely and effectively avoid the target ship and reach the target point, a quantitative evaluation is performed through CSR based on four cost functions. The economy and course keeping functions ensure that the ship can sail to the target point quickly, stably and economically. The risk cost and collision avoidance rules enable the ship to quickly and effectively take safe avoidance actions that comply with COLREGs when there are other ships around the ship and there is a risk of collision. The total cost function of a single action is the superposition of the sub-cost functions. When avoiding collisions, the algorithm evaluates all the action states of the ship at the next moment, and selects the action state with the highest score to update as the action decision at the next moment.

[0089] S3. Complete the hull modeling and build a closed-loop control model framework for the ship model to achieve seamless connection between the ship model and the remote driving system.

[0090] During this process, the dynamic behavior of the hull is constructed through a high-precision mathematical model based on the physical characteristics and dynamic principles of the ship, thereby achieving seamless connection between the ship model and the remote driving system.

[0091] First of all, hull modeling covers the description of the main structural features, mass distribution, hydrodynamic characteristics and maneuverability of the ship. Using advanced computer-aided design (CAD, Fusion) technology, the response characteristics of the ship under different working conditions are accurately designed. These data provide a solid foundation for the subsequent construction of a closed-loop control model. Figure 4-5 As shown, the ship model structure design diagram

[0092] Subsequently, based on the hull modeling results, a closed-loop control model framework was designed and implemented. The closed-loop control model framework integrates multiple modules such as sensor simulation, control algorithm, and actuator simulation to form a complete closed-loop feedback system. In the sensor simulation module, the output data of the communication device is simulated to provide the control algorithm with real-time and accurate ship status information and surrounding environment information. The control algorithm module calculates the optimal ship maneuvering instructions based on this information, combined with the preset collision avoidance rules and path planning strategies. Finally, the actuator simulation module converts these instructions into the actual motion response of the ship to complete the entire closed-loop control process. By integrating the Arduino Uno R3 development board and the 1838 infrared receiving module, a highly sensitive infrared communication system is realized, which not only improves the signal receiving ability of the ship model in complex environments, but also enhances its obstacle avoidance and path planning flexibility. The stability of the hull structure is significantly improved by optimizing the center of gravity and weight distribution. In particular, the narrower hull design not only improves the lateral stability and avoids the risk of capsizing during high-speed driving, but also makes the ship model more flexible and agile when turning and changing directions. In addition, the streamlined design of the hull effectively reduces water resistance, improves speed and fuel efficiency, and extends battery life; in terms of power supply, the design adopts a multi-way parallel power supply system to provide independent power supply for the steering gear, Arduino development board and motor, ensuring the independence and stability of the power demand of each functional module, while facilitating system maintenance and upgrades; the environmentally friendly design of this ship is reflected in many aspects. First, in terms of energy consumption optimization, the small ship model uses four 1.5V dry batteries in parallel to power the ship model, which extends the life of the ship model; secondly, the hull structure is designed to be detachable, which is convenient for the maintenance of internal circuits and equipment, reducing maintenance costs; finally, lightweight and high-strength materials are selected to manufacture the hull. This material is not only high in strength and durability, but also can effectively reduce the weight of the hull, improve the sailing speed and endurance, thereby achieving efficient energy utilization while taking into account the environmental performance and economic benefits of the ship model.

[0093] Completing the hull modeling and building a closed-loop control model framework for the ship model is an important part of building a ship collision avoidance and path planning system based on remote driving technology. It can not only achieve accurate simulation and efficient control of ship behavior, but also provide more reliable and intuitive driving guidance and decision support for the crew, further improving the safety and efficiency of ferry navigation.

[0094] In the preferred implementation of the present invention, the target point cost function is introduced based on the improved speed barrier algorithm, and basic path planning can be realized while realizing collision avoidance decision-making. At the same time, the quantification of safety and economy can be used to build an intelligent collision avoidance decision-making system for ferries, which can provide scientific navigation guidance to crew members and assist crew members in driving ferries. On the other hand, it can make autonomous decisions according to the situation, guide the ferry to navigate autonomously, and formulate safer and more efficient decision-making plans for the ferry, thereby improving the safety of the ferry during actual navigation, and providing a more efficient navigation path, shortening the actual navigation distance of the ferry, shortening the voyage, and saving fuel consumption.

[0095] In the preferred implementation of the present invention, the front end displays the navigation water environment simulation, algorithm calculation results, simulated navigation trajectory, etc., and provides the driver with a comprehensive understanding of the ferry navigation environment through an intuitive real-time simulation interface, so that the driver can quickly understand the current navigation status, interact with the navigation environment in real time, and take necessary measures to ensure the safety and stability of the ferry; the ferry data includes speed, acceleration, steering angle and position information, etc., providing the driver with real-time navigation reference, helping the driver to better understand the algorithm decision logic, and helping the driver to make accurate decisions in a complex navigation environment, so as to ensure the safe navigation of the ferry and reduce the driver's pressure.

[0096] In the preferred implementation of the present invention, a real small ship model is used for algorithm verification, which has further verification compared with traditional computer simulation and ensures the authenticity and accuracy of the algorithm. The improved VO algorithm is used in the obstacle avoidance algorithm to achieve efficient collision avoidance and decision-making of the ferry. In the collision avoidance algorithm, the action amplitude estimation model, simulated annealing method, particle swarm algorithm, genetic algorithm and other algorithms can be selected for model construction; in terms of physical ship model data transmission, other communication methods such as optical communication can be considered to achieve the connection between the ship model and the front and back ends.

[0097] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. An information interactive inland ferry navigation collision avoidance decision system, characterized in that: It includes data storage module, data processing and analysis module and data visualization module; The data storage module is used to store dynamic data, static data and ship information; The data processing and analysis module is used to intelligently clean, screen and preprocess the stored data; The data visualization module is used to present the ship navigation data to the user through a real-time map interface.

2. The information interactive inland ferry navigation collision avoidance decision system according to claim 1 is characterized in that: The dynamic data includes the ship's position, speed, heading and acceleration, and the static data includes the ship's type, load, size and navigation history.

3. An information interactive inland river ferry navigation collision avoidance decision-making method, characterized in that: The following steps are involved: S1. Build the main system architecture; S2, construct an integrated risk characterization algorithm for ferry crossing navigation as the core decision algorithm; S3. Complete the hull modeling and build a closed-loop control model framework for the ship model to achieve seamless connection between the ship model and the remote driving system.

4. The information interactive inland ferry navigation collision avoidance decision method according to claim 3 is characterized in that: In step S1, a comprehensive Web application is developed based on the Django framework, a MySQL database is integrated for data storage and management, a Three.js library is used to implement 3D graphics display on the front end, and WebSocket communication is implemented through Django Channels.

5. The information interactive inland river ferry navigation collision avoidance decision method according to claim 4 is characterized in that: WebSocket communication is achieved through the following methods: In the models.py file of the application, after defining the database model using Django's ORM object-relational mapping technology, generate a migration file through the manage.py makemigrations command. The migration file records the changes in the model and is used to create or modify the table structure in the database; In the settings.py configuration file of the Django project, connect to the MySQL database by setting the DATABASES configuration item, configure the INSTALLED_APPS list, and configure the ASGI asynchronous server gateway interface application of Django Channels; WebSocket routing defines the endpoints of WebSocket connections and their corresponding consumers; Use WebSocket to establish a persistent connection between the front-end and the back-end to achieve real-time data transmission, and receive data in the Three.js environment to dynamically render the trajectory effect.

6. The information interactive inland ferry navigation collision avoidance decision-making method according to claim 5 is characterized in that: The front-end and back-end data transmission is achieved through the following methods: Use WebSocket to establish a persistent connection between the front-end and the back-end to achieve real-time data transmission, dynamically receive the information of the ship's plane coordinates, acceleration, and speed, and receive the information in the Three.js environment to dynamically render the ship's trajectory effect. The back-end sets a WebSocket server, which can monitor the connection request from the front-end and send JSON format data containing trajectory information in real time after the connection is established; The front end uses requestAnimationFrame to create an animation loop, which continuously calls the render method of the renderer to update and render the scene. In each loop, it checks whether there is new data arriving from WebSocket, and updates the status of the track points and track lines according to the new data. Start the development server with Django’s manage.py runserver command.

7. The information interactive inland ferry navigation collision avoidance decision-making method according to claim 3 is characterized in that: In step S2, the construction of the core decision algorithm includes four core cost functions, and the core cost functions are as follows: (1) The cost function of navigation economy is: U eco =k1·f(x t ,y t ,x goal ,y goal ) (1) Among them, (x t ,y t ) is the position coordinate of the ferry at time t, (x goal, y goal ) is the coordinate of the target point, k1 is the weight coefficient of the utility function; (2) The crossing risk cost is: Among them, t0 is the current time, Δt is the predicted time, CSR t is the crossing risk predicted at time t0, k2 is the utility function U risk The weight coefficient of (3) The cost of heading keeping is: U heading =k3·f(θ max ,θ current ) (3) Among them, k3 is the utility function U heading Weight coefficient, θ max is the maximum steering angle, θ current is the current heading angle; (4) Rule Constraint Cost Function 8. The information interactive inland ferry navigation collision avoidance decision-making method according to claim 3 is characterized in that: In step S3, the hull modeling is completed by the following method to build a closed-loop control model framework for the ship model: S301. Use computer-aided design to design the response characteristics of the ship under different working conditions. The hull modeling includes the structural characteristics, mass distribution, hydrodynamic characteristics and maneuverability of the ship; S302. Based on the hull modeling results, a closed-loop control model framework is designed and implemented, wherein the framework integrates multiple modules of sensor simulation, control algorithm, and actuator simulation to form a closed-loop feedback system.

9. The information interactive inland river ferry navigation collision avoidance decision method according to claim 8, characterized in that: In step S302, the control algorithm module calculates the optimal ship maneuvering instructions based on the ship state information and the surrounding environment information, combined with the preset collision avoidance rules and path planning strategies, and the actuator simulation module converts the ship maneuvering instructions into the actual motion response of the ship to complete the entire closed-loop control process.

Images