A smart park vehicle navigation planning method and system based on digital twin

Abstract

The present invention relates to the field of navigation technology, and specifically to a vehicle navigation planning method and system for a smart park based on digital twins. The method comprises: constructing a monitoring area within the smart park, collecting dynamic data and static data within the monitoring area to generate processed data, and obtaining a digital twin model; analyzing and processing the data, comparing the monitoring area with the digital twin model, and updating obstacles within the monitoring area; generating a road topology map based on the monitoring area, abstracting video images within the monitoring area into nodes and edges, obtaining the monitoring range ratio of the edges, and judging whether there are monitoring blind spots within the monitoring area; calculating congestion coefficients according to whether there are monitoring blind spots, updating the digital twin model based on the congestion coefficients and obstacles, and adjusting the navigation path of the vehicle; preventing vehicle deviation caused by monitoring blind spots, realizing the positioning of physical entities in a dynamic environment, quickly responding to conditions such as congestion and obstacles, and improving the accuracy and real-time performance of vehicle navigation.

Description

Technical Field

[0001] The present invention relates to the field of navigation technology, and in particular to a vehicle navigation planning method and system for a smart park based on digital twins. Background Art

[0002] With the rapid development of smart cities and digital twin technology, smart parks, as an important component of intelligent urban management, are gradually introducing digital twin technology to achieve efficient management of equipment, environment, and personnel within the park. In particular, in the field of vehicle scheduling and navigation, by building digital twin models, it is possible to map the park's roads, traffic flow, and environmental changes in real time, improving the efficiency and safety of vehicle operations within the park. However, traditional digital twin navigation systems still have certain limitations in complex environments. In particular, when there are dynamic obstacles or blind spots in the park, the existing digital twin navigation system is difficult to respond in a timely manner, affecting the overall intelligence and reliability of transportation. In the context of smart parks, the application of digital twin technology is not limited to static environmental mapping. The key is to achieve dynamic, real-time management and control.

[0003] Traditional digital twin systems rely primarily on data collected by fixed-site monitoring systems and sensors for vehicle navigation planning. In smart campuses, monitoring systems cannot provide comprehensive coverage of all areas, especially in blind spots or signal-blocked areas. When obstacles or road congestion occur, the system cannot obtain relevant information in real time, leading to deviations in navigation planning and even misleading navigation. Furthermore, the types of obstacles within the campus are complex and diverse, including temporarily parked vehicles, moving personnel, or emergencies. Traditional systems lack the ability to perceive this dynamic information and are unable to quickly update path planning, thereby reducing navigation accuracy and safety. Summary of the Invention

[0004] In order to solve the technical problem that the existing digital twin navigation model cannot respond in real time to obstacles appearing in the monitoring blind spot, resulting in navigation planning deviation, the purpose of the present invention is to provide a smart park vehicle navigation planning method based on digital twin. The technical solution adopted is as follows:

[0005] Construct a monitoring area within the smart park, collect dynamic and static data within the monitoring area, generate and process data, and obtain a digital twin model;

[0006] Analyze and process data, compare the monitored area with the digital twin model, and update obstacles within the monitored area;

[0007] Generate a road topology map based on the monitoring area, abstract the video images in the monitoring area into nodes and edges, obtain the monitoring range ratio of the edges, and determine whether there are blind spots in the monitoring area;

[0008] The congestion coefficient is calculated based on whether there is a monitoring blind spot. The digital twin model is updated based on the congestion coefficient and obstacles to adjust the vehicle's navigation path.

[0009] Preferably, a monitoring area within the smart park is constructed, dynamic data and static data within the monitoring area are collected to generate and process data, and a digital twin model is obtained, including:

[0010] Cameras and sensors are deployed in the smart park to build a monitoring area. The data collected by the cameras and sensors is obtained through the data acquisition module to obtain dynamic data and static data in the monitoring area, and then transmitted to the digital twin module to generate and process data. Combined with three-dimensional modeling technology, a virtual model of the physical environment and real-time operating status in the smart park is constructed. Through data-driven and simulation analysis, a digital twin model is obtained.

[0011] Preferably, analyzing and processing data, comparing the monitored area with the digital twin model, and updating obstacles within the monitored area include:

[0012] The lane line information is obtained by analyzing and processing data through the lane line detection model, and the lane line information is compared with the digital twin model. The matching relationship between the monitoring area and the digital twin model is obtained based on the SIFT image registration algorithm, and the obstacles in the monitoring area are updated.

[0013] Preferably, a road topology map is generated based on the monitoring area, the video images in the monitoring area are abstracted into nodes and edges, the monitoring range ratio of the edges is obtained, and whether there is a monitoring blind spot in the monitoring area is determined, including:

[0014] Based on the processed data, the monitoring range of the monitoring area in the corresponding digital twin model is obtained, and a road topology map is generated based on the monitoring area. The video images in the monitoring area are abstracted into nodes and edges, and the edges are defined as lane line information;

[0015] Analyze the edges and combine them with the monitoring range to get the monitoring range ratio of any edge;

[0016] Set a judgment threshold. If the monitoring range ratio is greater than the judgment threshold, there is no monitoring blind spot; if the monitoring range ratio is less than the judgment threshold, there is a monitoring blind spot.

[0017] Preferably, if there is no monitoring blind spot, the congestion coefficient is calculated including:

[0018] The YOLO model is used to monitor the target. Based on the current analysis time, the number of vehicles passing through the edge in the historical time period is counted to obtain the average speed of any vehicle passing through any edge.

[0019] The time difference is calculated based on the time when any vehicle enters any side and the current analysis time, and normalized to obtain the timeliness of the corresponding vehicle, and the congestion coefficient is calculated.

[0020] Preferably, the time difference is calculated based on the time when any vehicle enters any side and the current analysis time, and normalized to obtain the timeliness of the corresponding vehicle. The corresponding calculation formula is:

[0021] The corresponding calculation formula is:

[0022] ;

[0023] in, represents the timeliness of the r-th vehicle on the i-th edge; represents the time when the r-th vehicle enters the i-th edge; t represents the current analysis time; norm represents the normalization function;

[0024] Calculate the congestion coefficient. The corresponding calculation formula is:

[0025] ;

[0026] in, represents the congestion coefficient of the i-th edge at the current analysis time t; represents the number of vehicles passing through the i-th edge in the historical time based on the current analysis time t; r represents the number of vehicles; represents the timeliness of the r-th vehicle on the i-th edge; represents the average speed of the r-th vehicle passing through the i-th edge; represents the number of vehicles already on the ith edge when the rth vehicle enters the ith edge; h represents the length of the edge; l Represents the number of edges, recorded as the number of lanes.

[0027] Preferably, if there is a monitoring blind spot, the congestion coefficient is calculated, including: analyzing the adjacent edges of the edge with the monitoring blind spot, obtaining the congestion coefficient and the monitoring range ratio of the adjacent edges, and obtaining an estimated value of the congestion coefficient of the edge with the monitoring blind spot. The corresponding calculation formula is:

[0028] ;

[0029] in, represents the estimated value of the congestion coefficient of the j-th edge at the current analysis time t; represents the number of edges adjacent to the jth edge; z represents the edge adjacent to the monitoring blind spot; Indicates the monitoring range ratio of the zth edge; represents the congestion coefficient of the z-th edge at the current analysis time t; norm represents the normalization function.

[0030] Preferably, the digital twin model is updated by combining the congestion coefficient with obstacles to adjust the navigation path of the vehicle, including:

[0031] The initial edge weight and initial update time interval of any edge are obtained through the digital twin model. The congestion coefficient is combined with the initial edge weight and initial update time interval to obtain the updated edge weight and update time interval based on the current analysis time.

[0032] The digital twin model is updated according to the updated edge weights and update time intervals to avoid obstacles and adjust the vehicle's navigation path.

[0033] Preferably, the updated edge weight based on the current analysis moment is obtained, and the corresponding calculation formula is: Calculate the updated edge weight of the edge without monitoring blind spot:

[0034] ;

[0035] in, represents the updated edge weight of the i-th edge at the current analysis time t; represents the congestion coefficient of the i-th edge at the current analysis time t; represents the initial edge weight of the i-th edge; norm represents the normalization function; similarly, the updated edge weight of the edge with a monitoring blind spot is calculated;

[0036] Get the updated time interval based on the current analysis time. The corresponding calculation formula is: Calculate the updated time interval when there is no monitoring blind spot edge:

[0037] ;

[0038] in, represents the update time interval after the i-th edge is updated; represents the congestion coefficient of the i-th edge at the current analysis time t; Represents the initial update time interval; norm represents the normalization function; similarly, the update time interval after the update of the monitoring blind spot edge is calculated.

[0039] To solve the above problems, the present application also provides a smart park vehicle navigation planning system based on digital twins. The system stores program data. When the program data is executed, it combines camera equipment, sensors, data acquisition modules, digital twin modules, vehicle terminals, navigation decision modules, road information databases and road detection modules to implement the smart park vehicle navigation planning method based on digital twins as described in any of the above items.

[0040] The present invention has the following beneficial effects:

[0041] 1. This application generates and processes data through static and dynamic data acquired in real time by cameras and sensors, and combines it with a digital twin model to dynamically update road information within the park, quickly respond to congestion, obstacles and other conditions, and improve the real-time performance of navigation. By matching the monitoring area with the digital twin model, it is determined whether there are blind spots in monitoring, and the corresponding congestion coefficients are obtained respectively, effectively reducing the navigation errors that may be caused in each blind spot in monitoring. In addition, the lane line detection and YOLO target detection model based on deep learning are used to monitor the different positions of the twin model in real time. Combined with the vehicle deviation of the planned path, the obstacle conditions of different vehicle navigation are updated to achieve accurate identification and positioning of vehicles and obstacles in a dynamic environment, further improve navigation accuracy, quickly respond to congestion, obstacles and other conditions, and improve the real-time performance of navigation. In addition, this application also takes into account the needs of different types of vehicles, and provides personalized services such as fixed parking space navigation and vacant parking space search to comprehensively improve the user experience.

[0042] 2. The smart park vehicle navigation planning system based on digital twins provided by the present invention has the same beneficial effects as the smart park vehicle navigation planning method based on digital twins provided by the present invention, which will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 A flowchart of a method for smart park vehicle navigation planning based on digital twins provided by one embodiment of the present invention;

[0045] Figure 2 A schematic diagram of nodes and edges of a digital twin-based smart park vehicle navigation planning method provided by one embodiment of the present invention;

[0046] Figure 3 A schematic structural diagram of a digital twin-based smart park vehicle navigation planning system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0047] To further illustrate the technical means and effects adopted by the present invention to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effects of a digital twin-based smart park vehicle navigation planning method and system proposed by the present invention. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable form.

[0048] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0049] The following describes in detail a specific scheme of a vehicle navigation planning method and system for a smart park based on digital twins provided by the present invention in conjunction with the accompanying drawings.

[0050] The existing technology usually makes navigation plans based on existing situations, and is unable to obtain obstacles or congestion in real time, resulting in the inability to update navigation plans according to emergencies, which reduces the safety of navigation. In one embodiment of the present invention, a smart park vehicle navigation planning method based on digital twins is provided. By real-time monitoring of different positions of the twin model and combining the vehicle deviation of the planned path, the obstacle conditions of different vehicle navigations are updated. In order to realize a smart park vehicle navigation planning method based on digital twins, a smart park vehicle navigation planning system based on digital twins is provided. The system is essentially a software system, which is composed of modules that realize corresponding functions. The specific steps in this method are now introduced in detail.

[0051] See also Figure 1 , which shows a flowchart of the steps of a smart park vehicle navigation planning method based on digital twins provided by one embodiment of the present invention, the method comprising:

[0052] Step S1: Construct a monitoring area within the smart park, collect dynamic data and static data within the monitoring area, generate and process data, and obtain a digital twin model;

[0053] Step S2: Analyze and process the data, compare the monitored area with the digital twin model, and update the obstacles in the monitored area;

[0054] Step S3: Generate a road topology map based on the monitoring area, abstract the video images in the monitoring area into nodes and edges, obtain the monitoring range ratio of the edges, and determine whether there are monitoring blind spots in the monitoring area;

[0055] Step S4: Calculate the congestion coefficient based on whether there is a monitoring blind spot, update the digital twin model based on the congestion coefficient and obstacles, and adjust the vehicle's navigation path.

[0056] To better explain, digital twin refers to the simulation, analysis and prediction of various situations and behaviors in the real world by creating a virtual copy of a physical entity. It is about using computer simulation, data analysis and artificial intelligence to operate and manage this virtual copy in order to simulate, analyze and predict various complex situations and behaviors in the real world. The smart park is an innovative concept that integrates modern information technology with traditional park management. It uses advanced technologies such as the Internet of Things, big data analysis, and cloud computing to achieve efficient allocation and management of various resources within the park. Therefore, the vehicle navigation planning of the smart park based on digital twins aims to create a virtual smart park model, obtain the vehicle's driving path within the park, analyze traffic flow, update congestion, obstacles and possible emergencies on the road in real time, update the initial digital twin model, and develop the optimal navigation route to help vehicles in the smart park drive more efficiently and safely, reduce waiting time, and improve overall traffic efficiency.

[0057] Preferably, in this embodiment, obstacles refer to objects that should not appear on the lane lines, which may interfere with or endanger the normal driving of the vehicle. They may be stationary, such as construction waste left on the road, fallen goods, and accident debris that has not been cleared in time, or they may be active, such as animals, pedestrians, or even other out-of-control vehicles that suddenly cross the road. The presence of obstacles will not only hinder the smooth flow of traffic, but may also cause traffic accidents and pose a threat to the safety of drivers and pedestrians. Therefore, in order to better obtain the navigation plan of the vehicle, the obstacles in the smart park also need to be updated in real time.

[0058] Furthermore, step S1 includes:

[0059] Cameras and sensors are deployed in the smart park to build a monitoring area. The data collected by the cameras and sensors is obtained through the data acquisition module to obtain dynamic data and static data in the monitoring area, and then transmitted to the digital twin module to generate and process data. Combined with three-dimensional modeling technology, a virtual model of the physical environment and real-time operating status in the smart park is constructed. Through data-driven and simulation analysis, a digital twin model is obtained.

[0060] As an optional implementation, in this embodiment, the imaging device refers to a camera.

[0061] It can be explained that sensors are used to obtain static data such as environmental information. That is, sensors use various sensing technologies to detect parameters such as temperature, humidity, light intensity, air quality, etc. in the environment to provide real-time environmental information parameters.

[0062] Specifically, cameras and sensors are deployed at major road nodes, key intersections, and parking areas to construct monitoring areas. Real-time video images are collected to obtain dynamic data such as vehicles, pedestrians, and obstacles, as well as static data such as roads, buildings, parking spaces, and traffic facilities. The static and dynamic data of the camera equipment and sensors are obtained through the data acquisition module and integrated to obtain environmental perception information within the smart park, which is transmitted to the digital twin module to generate processed data. Combined with three-dimensional modeling technology, a virtual model of the physical environment within the smart park is created using a computer to reflect the real-time operating status. Through data-driven and simulation analysis, that is, using processed data to identify patterns and phenomena, hidden relationships in the data are excavated, and systems and processes in the real world are simulated to obtain a digital twin model for subsequent vehicle navigation planning.

[0063] Furthermore, step S2 includes:

[0064] The lane line information is obtained by analyzing and processing data through the lane line detection model, and the lane line information is compared with the digital twin model. The matching relationship between the monitoring area and the digital twin model is obtained based on the SIFT image registration algorithm, and the obstacles in the monitoring area are updated.

[0065] To better illustrate, LaneNet (Lane Detection Network) uses a deep learning lane detection model to accurately obtain lane information. This convolutional neural network architecture can handle a variety of complex road scenarios, including curves, intersections, and multi-lane situations. LaneNet not only improves detection accuracy but also reduces false alarm rates, ensuring vehicle safety during driving.

[0066] The SIFT (Scale-Invariant Feature Transform) image registration algorithm is an algorithm used for image feature extraction and matching. It detects key parts in the image and calculates the direction, scale, and description of these key parts to generate feature descriptions with scale invariance and rotation invariance. It can achieve accurate matching even in complex environments such as changing perspectives, changing lighting conditions, or noise interference.

[0067] Specifically, lane line information is obtained based on the lane line detection model, and the road area within the monitoring area is obtained, that is, the image video is obtained through the camera equipment, and the RGB (Red, Green, Blue) color image is input, that is, the images of other colors are generated by combining red, green and blue lights of different intensities; the output is a binary mask of the same size as the input image, which is used to represent the pixel area of ​​the lane line, and each pixel value is 0 or 1, where 0 represents the background and 1 represents the lane line.

[0068] The obtained lane lines are compared with the digital twin model. Based on the SIFT image registration algorithm, representative feature points on the lane lines are selected, that is, areas that can be accurately identified and matched under different viewing angles and lighting conditions and are invariant. They are then aligned with the top-view projection results of the digital twin model to determine the specific position and direction of the lane lines in the monitored area, and obtain the matching relationship between the monitored area and the digital twin model, ensuring that the digital twin model can accurately reflect the road conditions in the smart park, to assist in the real-time update of obstacles, and to improve the accuracy of vehicle navigation in the smart park, as well as the efficiency and reliability of the intelligent transportation system.

[0069] It can be understood that through the matching relationship between the monitoring area and the digital twin model, the correlation characteristics between multiple monitoring areas in the smart park can be obtained, which is conducive to the subsequent analysis of whether there are monitoring blind spots in each road section, that is, potential monitoring loopholes.

[0070] See also Figure 2 , which shows a schematic diagram of nodes and edges of a smart park vehicle navigation planning method based on digital twins provided by an embodiment of the present invention, wherein V0, V1, V2 and V3 represent nodes, 1, 2, 3, 4 and 5 represent edges, and arrows represent allowed directions of passage.

[0071] Furthermore, step S3 includes:

[0072] Step S31: Obtain the monitoring range of the monitoring area in the corresponding digital twin model based on the processed data, generate a road topology map based on the monitoring area, abstract the video images in the monitoring area into nodes and edges, and define the edges as lane line information.

[0073] To explain, a road topology map is a graphical display method for representing the structure of a road network, using nodes and edges to represent road intersections and road segments; it can intuitively depict the connection relationship between road intersections and various road segments; among them, nodes represent key locations on the road, such as intersections, parking area entrances, turning points and other traffic points; edges are used to represent the road segment between two nodes, and the edges are lane line information, including length, width, road surface type and allowed direction of travel; when an edge is bidirectional, the obstacles and congestion conditions on the road are different when vehicles travel in different directions, so the road segment is divided into two edges in different directions.

[0074] Step S32: Analyze the edges and combine them with the monitoring range to obtain the monitoring range ratio of any edge.

[0075] Specifically, the monitoring range of the monitoring area in the corresponding digital twin model is obtained according to the processed data, that is, the monitoring range of any edge is manually calibrated; the monitoring range proportion refers to the ratio of the monitoring range on any edge to the total length of the corresponding edge, which is recorded as , representing the monitoring range proportion of the edge.

[0076] Step S33: Set a judgment threshold. If the proportion of the monitoring range is greater than the judgment threshold, there is no monitoring blind spot; if the proportion of the monitoring range is less than the judgment threshold, there is a monitoring blind spot.

[0077] As an optional implementation, in this embodiment, the judgment threshold is.

[0078] Specifically, when , indicates that the monitoring range of the th edge in the road topology map is large, and there is basically no monitoring blind spot. At this time, path planning can be carried out with greater confidence; on the contrary, when , indicates that the monitoring range of the th edge in the road topology map is small, and there may be a monitoring blind spot. Therefore, when navigating the vehicle, it is necessary to pay special attention to the blind spot range in the corresponding road section, and take corresponding measures to identify and avoid potential monitoring blind spots; that is, the various road sections in the smart park are distinguished by the size of the monitoring range, so as to effectively navigate the vehicle more accurately.

[0079] It can be understood that there is no monitoring blind spot, which means that the monitoring range ratio is greater than the judgment threshold, indicating that the monitoring coverage of the edge corresponding to the monitoring range ratio is high. At this time, the congestion coefficient can be calculated based on real-time monitoring.

[0080] Furthermore, in step S4, if there is no monitoring blind spot, the congestion coefficient is calculated, including:

[0081] Step S411: Target monitoring is performed using the YOLO model. Based on the current analysis moment, the number of vehicles passing through the edge in the historical time period is counted to obtain the average speed of any vehicle passing through any edge.

[0082] To better explain, the YOLO (You Only Look Once) model is a real-time target detection algorithm that converts the target detection task into a single regression problem. It performs target detection by directly predicting bounding boxes and category probabilities in the image. That is, the image is divided into grids, and each grid is responsible for predicting the target whose center point falls within the grid to improve detection speed.

[0083] As an optional implementation, in this embodiment, the historical time is the past 10 minutes based on the current analysis time.

[0084] Specifically, for road sections with no blind spots or small blind spots, the YOLO model is used to perform target detection on each frame of the acquired surveillance video to extract the position and number of vehicles. The output results of YOLO include the bounding box coordinates of each vehicle, the confidence of each bounding box, and the category label. The number of vehicles passing through the edge in the historical time is then counted to obtain the average speed of any vehicle passing through any edge. The average speed of the th vehicle passing through the th road section is recorded as .

[0085] Step S412: Calculate the time difference based on the time when any vehicle enters any side and the current analysis time, perform normalization processing to obtain the timeliness of the corresponding vehicle, and calculate the congestion coefficient.

[0086] Furthermore, in step S412, the time difference is calculated based on the time when any vehicle enters any side and the current analysis time, and normalized to obtain the timeliness of the corresponding vehicle. The corresponding calculation formula is:

[0087] ;

[0088] in, represents the timeliness of the r-th vehicle on the i-th edge; represents the time when the rth vehicle enters the ith edge; t represents the current analysis time; and norm represents the normalization function. Timeliness refers to the efficiency and speed with which a vehicle completes a task or reaches its destination within a specific time period. It reflects the vehicle's operating status on the road. By analyzing timeliness, traffic flow, road congestion, and vehicle scheduling can be optimized, improving the operational efficiency of the entire digital twin system.

[0089] Calculate the congestion coefficient. The corresponding calculation formula is:

[0090] ;

[0091] in, represents the congestion coefficient of the i-th edge at the current analysis time t; represents the number of vehicles passing through the i-th edge in the historical time based on the current analysis time t; r represents the number of vehicles; represents the timeliness of the r-th vehicle on the i-th edge; represents the average speed of the r-th vehicle passing through the i-th edge; represents the number of vehicles already on the ith edge when the rth vehicle enters the ith edge; h represents the length of the edge; lRepresents the number of edges, recorded as the number of lanes. It should be noted that to ensure meaningful calculation results, when performing fractional operations in the embodiments of the present invention, when the denominator is 0, a parameter adjustment factor greater than 0 must be added to the denominator to prevent the denominator from being 0. The value of the parameter adjustment factor is set by the implementer based on actual conditions and is not specifically limited in this application.

[0092] It should be noted that the congestion coefficient is an indicator to measure the degree of road congestion, which comprehensively considers factors such as vehicle timeliness, the number of passing vehicles and traffic flow; by analyzing the congestion coefficient, we can better understand the real-time traffic conditions of the road and lay the foundation for better subsequent vehicle route planning.

[0093] It can be understood that if there is a monitoring blind spot on the edge and the monitoring blind spot is large, the relevant connection between the currently analyzed edge and its adjacent edges is obtained, and the congestion coefficient of the edge with the monitoring blind spot is estimated to obtain an estimated value of the congestion coefficient, that is, the monitoring area of ​​the monitoring blind spot is expanded to make up for the information loss of the monitoring blind spot, and then indirectly infer the congestion coefficient of the edge with the monitoring blind spot, to assist the digital twin system in making new navigation plans.

[0094] Furthermore, in step S4, if there is a monitoring blind spot, the congestion coefficient is calculated, including:

[0095] Analyze the adjacent edges of the edge with a monitoring blind spot, obtain the congestion coefficient and monitoring range ratio of the adjacent edges, and obtain the estimated value of the congestion coefficient of the edge with a monitoring blind spot. The corresponding calculation formula is:

[0096] ;

[0097] in, represents the estimated value of the congestion coefficient of the j-th edge at the current analysis time t; represents the number of edges adjacent to the jth edge; z represents the edge adjacent to the monitoring blind spot; Indicates the monitoring range ratio of the zth edge; represents the congestion coefficient of the z-th edge at the current analysis time t; norm represents the normalization function.

[0098] Specifically, in this embodiment, the th edge is defined as a road segment with a monitoring blind spot. First, the starting point and end point of the th edge are obtained, and the edge with the starting point of the th edge as the end point and the edge with the end point of the th edge as the starting point are selected. The boundaries that meet these conditions are defined as the edges adjacent to the monitoring blind spot. For better explanation, in Figure 2 In the example, if we analyze the fourth edge, according to the direction, the edges associated with it are the third and fifth edges; then, we combine the adjacent edges to obtain the estimated value of the congestion coefficient of each edge.

[0099] Understandably, in the process of vehicle navigation within traditional smart parks, the optimal path is selected based on the road topology map generated by the digital twin system. If the traditional digital twin model is not updated in a timely manner, it will directly affect the final vehicle navigation results. Therefore, based on the congestion coefficient or estimated value of the congestion coefficient obtained on each side, the obstacles of any road section are updated in real time, and then the congestion coefficient or the estimated value of the congestion coefficient is analyzed to complete the update of the traditional digital twin model.

[0100] Furthermore, in step S4, the digital twin model is updated by combining the congestion coefficient with obstacles to adjust the navigation path of the vehicle, including:

[0101] Step S421: Obtain the initial edge weight and initial update time interval of any edge through the digital twin model, combine the congestion coefficient with the initial edge weight and initial update time interval, and obtain the updated edge weight and update time interval based on the current analysis moment.

[0102] It can be explained that in this embodiment, the initial edge weight is obtained based on the length of the edge, where the edge weight refers to the weight value of the edge. The initial edge weight is obtained by first obtaining the actual length of the edge, and then converting the actual length of the edge into the edge weight to reflect the actual length of the edge in the algorithm, and then reflect factors such as traffic congestion and road conditions; the initial update time interval refers to the time interval between data synchronization and update operations when the digital twin system is started and starts running, which is used to illustrate the initial state of navigation.

[0103] Optionally, in this embodiment, the initial update time interval is 30 minutes.

[0104] Step S422: Update the digital twin model according to the updated edge weights and update time intervals to avoid obstacles and adjust the vehicle's navigation path.

[0105] Furthermore, in step S421, the updated edge weight based on the current analysis time is obtained, and the corresponding calculation formula is: Calculate the updated edge weight of the edge without monitoring blind spot:

[0106] ;

[0107] in, represents the updated edge weight of the i-th edge at the current analysis time t; represents the congestion coefficient of the i-th edge at the current analysis time t; represents the initial edge weight of the i-th edge; norm represents the normalization function.

[0108] Similarly, the updated edge weights of the edges in the monitoring blind spot are calculated. Specifically, the corresponding calculation formula is:

[0109]

[0110] in, represents the updated edge weight of the j-th edge at the current analysis time t; represents the estimated value of the congestion coefficient of the j-th edge at the current analysis time t; represents the initial edge weight of the j-th edge.

[0111] Furthermore, the updated time interval based on the current analysis moment is obtained, and the corresponding calculation formula is: Calculate the updated time interval when there is no monitoring blind spot edge:

[0112] ;

[0113] in, represents the update time interval after the i-th edge is updated; represents the congestion coefficient of the i-th edge at the current analysis time t; represents the initial update time interval; norm represents the normalization function.

[0114] Similarly, the update time interval after the update of the edge with monitoring blind spot is calculated. Specifically, the corresponding calculation formula is:

[0115] ;

[0116] in, represents the update time interval after the jth edge is updated; Represents the estimated value of the congestion coefficient of the j-th edge at the current analysis time t.

[0117] Specifically, based on the above, the updated edge weight and update time interval of each edge in the smart park are obtained, and then the digital twin model is updated to adjust the optimal path planning of the vehicle from the current position to the destination in real time, that is, the edge weight in the road topology map is adjusted based on the updated edge weight and update time interval, combined with the Dijkstra algorithm, and obstacles are avoided, and the updated navigation path of the vehicle is obtained in real time to adjust the vehicle heading in real time; wherein, the Dijkstra algorithm is an algorithm for finding the best path in the road topology map, which starts from the source point and gradually expands the shortest path tree. Each time, an unvisited node closest to the current node is selected, added to the shortest path tree, and the distance of other nodes to the source point is updated, and the process continues until all nodes have been visited or the target node is reached.

[0118] Preferably, when different vehicles enter the smart park, they obtain license plate information based on the vehicle identification system in the monitoring area, and analyze whether there is a fixed parking location for the current vehicle inside the smart park. If so, the updated digital twin model in the smart park is used through the aforementioned vehicle planning method to determine the starting point and target location point for intelligent navigation to ensure that the vehicle can reach the predetermined location efficiently and accurately; conversely, if there is no fixed parking space in the smart park, the vacant parking space is obtained based on the digital twin model, and then navigated to the vacant parking space, so that the vehicle can be parked smoothly while maintaining order and efficiency within the smart park.

[0119] It can be understood that this application generates and processes data through static data and dynamic data obtained in real time by cameras and sensors, and combines it with a digital twin model to dynamically update road information within the park, quickly respond to congestion, obstacles and other conditions, and improve the real-time performance of navigation; by matching the monitoring area with the digital twin model, it is determined whether there are monitoring blind spots, and the corresponding congestion coefficients are obtained respectively, effectively reducing the navigation errors that may be caused in each monitoring blind spot; in addition, the lane line detection and YOLO target detection model based on deep learning are used to monitor the different positions of the twin model in real time, and the obstacle conditions of different vehicle navigations are updated in combination with the vehicle deviation of the planned path, so as to achieve accurate identification and positioning of vehicles and obstacles in a dynamic environment, further improve navigation accuracy, quickly respond to congestion, obstacles and other conditions, and improve the real-time performance of navigation; in addition, this application also takes into account the needs of different types of vehicles, and provides personalized services such as fixed parking space navigation and vacant parking space search to comprehensively improve the user experience.

[0120] See also Figure 3 , which shows a structural diagram of a smart park vehicle navigation planning system based on digital twins provided by an embodiment of the present invention.

[0121] One embodiment of the present invention proposes a smart park vehicle navigation planning system based on digital twins. The system stores program data. When the program data is executed, it combines camera equipment, sensors, data acquisition modules, digital twin modules, vehicle terminals, navigation decision modules, road information databases and road detection modules to implement a smart park vehicle navigation planning method based on digital twins as described in the aforementioned embodiment; this system has the same beneficial effects as the aforementioned smart park vehicle navigation planning method based on digital twins, and will not be repeated here.

[0122] To better illustrate, the camera equipment can capture a continuous sequence of images, and after digital processing, convert the images into electronic signals to obtain real-time video stream data; the sensor can perceive and respond to specific types of input signals, and convert these input signals into electrical signals to monitor environmental changes or equipment status in real time and generate sensor data; it is transmitted to the data acquisition module and obtained after analysis. The processed data is responsible for collecting the required information from various different data sources to achieve data accuracy and completeness; the processed data is transmitted to the digital twin platform to obtain the initial digital twin model, that is, the processed data is synchronized and simulated in real time through the digital twin platform, so as to realize the monitoring, analysis and optimization of physical entities in the smart park.

[0123] Connected to the digital twin platform are the vehicle terminal, road information database, and road detection module. The vehicle terminal is a navigation terminal, including a GPS (Global Positioning System Module), a display screen, and a communication module. It is used to indicate the vehicle's location, receive navigation instructions from the digital twin model, and provide real-time feedback on the vehicle's status. The road information database refers to the central server, namely the cloud computing platform, which is used to store historical data, road information, and dynamic environmental information within the smart park. It also assists in running the core models and algorithms of the digital twin module. The storage of dynamic environmental information is to respond to various emergencies in a timely manner, avoid potential problems within the smart park, and prevent dangers caused by the digital twin model's untimely response. The road detection module can detect road congestion and vehicle driving conditions within the smart park in real time, and perform predictive analysis on obstacles in the monitoring area, which is conducive to updating obstacles within the smart park and navigating and avoiding them.

[0124] The navigation decision module is connected between the vehicle terminal and the road detection module. The congestion coefficient or the estimated value of the congestion coefficient obtained in the road detection module is transmitted to the navigation decision module. The updated edge weight and update time interval are obtained in the navigation decision module to update the initial digital twin model and send a new navigation path to the vehicle terminal. Among them, the navigation decision module can find the optimal navigation path based on the updated digital twin model and the real-time updated obstacles, combined with the path planning algorithm and the current driving status of the vehicle.

[0125] Preferably, in this embodiment, the digital twin-based smart park vehicle navigation planning system also includes edge computing equipment, wireless communication equipment and a user interaction and display module; wherein, the edge computing module is used to process data from camera equipment and sensors in real time to reduce data transmission delay; the wireless communication equipment mainly adopts 5G or Wi-Fi 6 communication technology to ensure real-time communication between vehicles in the smart park and the digital twin platform. 5G is the fifth generation of mobile communication technology; Wi-Fi 6, also known as 802.11ax, provides a higher data transmission rate and more efficient network capacity than the previous generation of Wi-Fi technology; the user interaction and display module can display navigation information, road conditions and vehicle locations in the current smart park to users, so that users can quickly understand through a graphical interface, which is highly flexible and improves user experience.

[0126] It can be understood that when a module of a smart campus vehicle navigation planning system based on digital twins is in operation, it is necessary to utilize a smart campus vehicle navigation planning method based on digital twins provided by the aforementioned embodiment. Therefore, whether the method and program data are integrated or different hardware is configured to produce functions similar to the effects achieved by the present invention, it falls within the scope of protection of the present invention.

[0127] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0128] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A vehicle navigation planning method for a smart park based on digital twins, characterized in that: The method comprises: Build a monitoring area within the smart park, collect dynamic and static data in the monitoring area in real time, generate and process data, and obtain a digital twin model; Analyze and process data, compare the monitored area with the digital twin model, and update obstacles within the monitored area; Generate a road topology map based on the monitoring area, abstract the video images in the monitoring area into nodes and edges, obtain the monitoring range ratio of the edges, and determine whether there are blind spots in the monitoring area; The congestion coefficient is calculated based on whether there are blind spots. The digital twin model is updated based on the congestion coefficient and obstacles, and the vehicle's navigation path is adjusted. If there is no monitoring blind spot, calculate the congestion coefficient, including: The YOLO model is used to monitor the target. Based on the current analysis time, the number of vehicles passing through the edge in the historical time period is counted to obtain the average speed of any vehicle passing through any edge. The time difference is calculated based on the time when any vehicle enters any side and the current analysis time, and then normalized to obtain the timeliness of the corresponding vehicle and the congestion coefficient. If there is a monitoring blind spot, calculate the congestion coefficient, including: analyzing the adjacent edges of the edge with the monitoring blind spot, obtaining the congestion coefficient and monitoring range ratio of the adjacent edges, and obtaining an estimated value of the congestion coefficient of the edge with the monitoring blind spot. The corresponding calculation formula is: Among them, ψ' j，t represents the estimated value of the congestion coefficient of the jth edge at the current analysis time t; n j represents the number of edges adjacent to the jth edge; z represents the edge adjacent to the monitoring blind spot; represents the monitoring range proportion of the zth edge; ψ z，t represents the congestion coefficient of the z-th edge at the current analysis time t; norm represents the normalization function.

2. A method for smart park vehicle navigation planning based on digital twins according to claim 1, characterized in that: Construct a monitoring area within the smart park, collect dynamic and static data within the monitoring area, generate and process data, and obtain a digital twin model, including: Cameras and sensors are deployed in the smart park to build a monitoring area. The data collected by the cameras and sensors is obtained through the data acquisition module to obtain dynamic data and static data in the monitoring area, and then transmitted to the digital twin module to generate and process data. Combined with three-dimensional modeling technology, a virtual model of the physical environment and real-time operating status in the smart park is constructed. Through data-driven and simulation analysis, a digital twin model is obtained.

3. The method for smart park vehicle navigation planning based on digital twins according to claim 1, characterized in that: Analyze and process data, compare the monitoring area with the digital twin model, and update obstacles in the monitoring area, including: obtaining lane information through lane line detection model analysis and processing data, comparing the lane line information with the digital twin model, obtaining the matching relationship between the monitoring area and the digital twin model based on the SIFT image registration algorithm, and updating obstacles in the monitoring area.

4. The method for smart park vehicle navigation planning based on digital twins according to claim 1, characterized in that: Generate a road topology map based on the monitored area, abstract the video images in the monitored area into nodes and edges, obtain the monitoring range ratio of the edges, and determine whether there are blind spots in the monitored area, including: Based on the processed data, the monitoring range of the monitoring area in the corresponding digital twin model is obtained, and a road topology map is generated based on the monitoring area. The video images in the monitoring area are abstracted into nodes and edges, and the edges are defined as lane line information; Analyze the edges and combine them with the monitoring range to get the monitoring range ratio of any edge; Set a judgment threshold. If the monitoring range ratio is greater than the judgment threshold, there is no monitoring blind spot; if the monitoring range ratio is less than the judgment threshold, there is a monitoring blind spot.

5. The method for smart park vehicle navigation planning based on digital twins according to claim 1, characterized in that: The time difference is calculated based on the time when any vehicle enters any side and the current analysis time, and then normalized to obtain the timeliness of the corresponding vehicle. The corresponding calculation formula is: or i，r =norm(-|t r -t|) Among them, η i，r represents the timeliness of the r-th vehicle on the i-th edge; t r represents the time when the r-th vehicle enters the i-th edge; t represents the current analysis time; norm represents the normalization function; Calculate the congestion coefficient. The corresponding calculation formula is: Among them, ψ i，t represents the congestion coefficient of the i-th edge at the current analysis time t; n i，t represents the number of vehicles passing through the i-th edge in the historical time based on the current analysis time t; r represents the number of vehicles; η i，r represents the timeliness of the r-th vehicle on the i-th edge; v i，r represents the average speed of the rth vehicle passing the i-th edge; m i，r It represents the number of vehicles already existing on the i-th edge when the r-th vehicle enters the i-th edge; h represents the length of the edge; l represents the number of edges, which is recorded as the number of lanes.

6. The method for smart park vehicle navigation planning based on digital twins according to claim 1, characterized in that: The digital twin model is updated by combining the congestion coefficient with obstacles to adjust the vehicle's navigation path, including: The initial edge weight and initial update time interval of any edge are obtained through the digital twin model. The congestion coefficient is combined with the initial edge weight and initial update time interval to obtain the updated edge weight and update time interval based on the current analysis time. The digital twin model is updated according to the updated edge weights and update time intervals to avoid obstacles and adjust the vehicle's navigation path.

7. The method for smart park vehicle navigation planning based on digital twins according to claim 1, characterized in that: Get the updated edge weight based on the current analysis time. The corresponding calculation formula is: Calculate the updated edge weight of the edge without monitoring blind spot: q i，t =(1+norm(ψ i，t ))×q i Among them, q i，t represents the updated edge weight of the i-th edge at the current analysis time t; ψ i，t represents the congestion coefficient of the i-th edge at the current analysis time t; q i represents the initial edge weight of the i-th edge; norm represents the normalization function; similarly, the updated edge weight of the edge with a monitoring blind spot is calculated; Get the updated time interval based on the current analysis time. The corresponding calculation formula is: Calculate the updated time interval when there is no monitoring blind spot edge: Δt i =norm(-ψ i，t )×Δt Where Δt i represents the update time interval after the i-th edge is updated; ψ i，t represents the congestion coefficient of the i-th edge at the current analysis time t; Δt represents the initial update time interval; norm represents the normalization function; similarly, the update time interval after the update of the edge with a monitoring blind spot is calculated.

8. A smart park vehicle navigation planning system based on digital twins, characterized by: The system stores program data. When the program data is executed, it combines with camera equipment, sensors, data acquisition modules, digital twin modules, vehicle terminals, navigation decision modules, road information databases and road detection modules to implement a smart park vehicle navigation planning method based on digital twins as described in any one of claims 1 to 7.

Images