Navigation method and system based on vehicle and road cloud and digital twinning technology and medium

Abstract

The invention discloses a navigation method and system based on vehicle and road cloud and a digital twinning technology, and a medium. Relates to the technical field of navigation. The method is improved on the basis of a traditional navigation technology, weather early warning data around a main vehicle and information of a lane where the main vehicle is located are obtained based on the vehicle-road cloud technology, traffic early warning information and dynamic scenes around the main vehicle are constructed through a third-party service platform, twin presentation and reminding are conducted on a navigation platform through a digital twin technology, and the navigation efficiency is improved. Early warning information, a road lane and a lane where a main vehicle is located can be displayed, and navigation data of a navigation platform can be displayed at the same time, so that a user can know the scene condition around the main vehicle and the early warning information more visually; and through multi-platform collaborative optimization division and cooperation, the calculation efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of navigation, and particularly to a navigation method, system and medium based on vehicle-road-cloud and digital twin technologies. Background Art

[0002] When providing driving navigation services, existing navigation platforms usually present route information in a flat display mode of a single lane or multiple lanes. Although this traditional navigation interface can provide users with basic road directions, turning prompts and traffic conditions, there are still the following significant defects in actual driving scenarios: 1. Lane-level positioning is fuzzy: Users cannot intuitively judge the specific lane where the current vehicle is located (such as the left lane, the middle lane or the right lane) through the navigation page. Especially in complex multi-lane sections (such as viaduct bifurcations or highway ramps), it is easy to cause misjudgment, increasing the risk of wrong lane changes or missing intersections; 2. Lack of surrounding dynamic information: Traditional navigation can only provide static lane lines or simple traffic sign prompts, but lacks visual feedback on real-time lane-level dynamic events (such as abnormal parking of surrounding vehicles, sudden collisions, illegal lane cutting or abnormal overtaking, etc.). Drivers need to rely entirely on visual observation, and there are significant safety hazards in bad weather or when the line of sight is blocked; 3. Insufficient interactivity and warning: Existing technologies do not deeply integrate lane-level environmental data (such as speed differences between adjacent vehicles and abnormal behaviors) with the navigation interface, resulting in the system being difficult to provide active warnings for users (such as prompting to avoid malfunctioning vehicles in adjacent lanes), reducing driving safety and the value of navigation assistance.

[0003] Therefore, there is an urgent need for a navigation solution that can achieve high-precision lane-level positioning, real-time dynamic environment perception and intelligent warning to solve the problems of single information presentation and poor interactivity in traditional technologies. Summary of the Invention

[0004] The technical problem to be solved by the present invention is the problem of single information presentation and poor interactivity in traditional driving navigation technologies. The purpose of the present invention is to provide a navigation method, system and medium based on vehicle-road-cloud and digital twin technologies. This solution provides a navigation method, system and medium based on vehicle-road-cloud and digital twin technologies. On the basis of traditional navigation technologies, it makes improvements in methods. It obtains scene data around the host vehicle (including information such as the lane where the host vehicle is located) and blind area warning, abnormal parking warning, and abnormal weather warning data around the host vehicle through vehicle-road-cloud technologies. Finally, through digital twin technologies, it presents and reminds on the navigation platform, can realize multi-lane display of roads, and can display the lane positions of the current vehicle and surrounding vehicles and navigation data on the navigation platform in real time, facilitating users to more intuitively understand the scene situation and warning information around the host vehicle.

[0005] The present invention is realized through the following technical solutions: This solution provides a navigation method based on vehicle-road-cloud and digital twin technologies, which is realized based on a third-party service platform, a navigation platform, and a vehicle-road-cloud platform; the method includes: The third-party service platform requests the navigation platform to start navigation. After the navigation platform successfully starts navigation, the navigation data is displayed in real time, and at the same time, the third-party service platform requests to start the vehicle-road-cloud platform. The vehicle-road-cloud platform collects collaborative data and performs primary operations; the vehicle-road-cloud platform sends the primary operation results to the third-party service platform; the primary operations include determining weather warning information and the lane information where the host vehicle is located, and denoising the collaborative data. The third-party service platform constructs a dynamic scene around the host vehicle based on the primary operation results, and uses digital twin technology to twin-display the dynamic scene around the host vehicle on the navigation platform in real time; the dynamic scene around the host vehicle includes: weather warning information, the environment information around the host vehicle, and traffic warning information.

[0006] The working principle of this solution: This solution provides a navigation method, system, and medium based on vehicle-road-cloud and digital twin technologies. On the basis of traditional navigation technologies, improvements are made in the method. This solution obtains the scene data around the host vehicle (including the lane information where the host vehicle is located, etc.), as well as the blind spot warning, abnormal parking warning, and abnormal weather warning data around the host vehicle based on vehicle-road-cloud technology. Finally, through digital twin technology, it is presented and reminded on the navigation platform, enabling multi-lane display of the road, and the positions of the current vehicle and surrounding vehicles can be displayed on the lane in real time; at the same time, the navigation data of the navigation platform can also be displayed, facilitating users to more intuitively understand the scene situation and warning information around the host vehicle. On the other hand, to display the positions of the current vehicle and surrounding vehicles on the lane in real time, there are strict requirements for the parsing calculation and transmission time of vehicle-road-cloud data, the construction and display time of the dynamic scene around the host vehicle, etc. If the time consumption is too long, the warning information and even the entire dynamic scene around the host vehicle are very likely to become invalid. Therefore, in order to ensure the timeliness of the dynamic scene around the host vehicle in this solution, the vehicle-road-cloud platform performs simple primary operations on the collaborative data to obtain primary operation results, and the third-party service platform constructs the dynamic scene around the host vehicle based on the primary operation results. Different platforms cooperate in calculation, and multiple platforms collaborate and optimize the division of labor; instead of piling up all the calculation work on a certain platform, effectively improving the calculation efficiency and ensuring the timeliness and effectiveness of the dynamic scene around the host vehicle. In addition, during the process of performing primary operations, the vehicle-road-cloud platform will denoise the collaborative data according to the needs of constructing the environment information around the host vehicle and traffic warning information, avoiding the transmission and calculation of irrelevant data from affecting the generation efficiency of the dynamic scene around the host vehicle. This solution uses digital twin technology to uniformly map information such as weather warnings (e.g., fog visibility models), traffic warnings (such as illegal parking / abnormal overtaking around the scene), and the lane where the host vehicle is located to the navigation platform, realizing a spatial and hierarchical information expression that traditional navigation (2D arrows + voice) cannot provide.

[0007] A further optimized solution is that the vehicle-road-cloud platform collects collaborative data and performs primary operations; the methods include: Collect and copy the collaborative data to obtain 2 sets of collaborative data, and perform the following parallel operations on the 2 sets of collaborative data respectively: For the first set of collaborative data: Delete invalid data and multi-source basic positioning data to obtain denoised collaborative data; the multi-source basic positioning data includes: roadside basic positioning data, host vehicle side basic positioning data, and GPS side basic positioning data; For the second set of collaborative data: Extract multi-source basic positioning data and weather data respectively; Perform spatio-temporal alignment and data synchronization processing on the multi-source basic positioning data to obtain synchronized multi-source basic positioning data; input the synchronized multi-source basic positioning data into the pre-constructed multi-source lane positioning model to obtain the lane information where the host vehicle is located; For the weather data: Perform warning determination to obtain weather warning information; Use the denoised collaborative data, synchronized multi-source basic positioning data, lane information where the host vehicle is located, and weather warning information as the primary operation results.

[0008] A further optimized solution is that the step of inputting the synchronized multi-source basic positioning data into the pre-constructed multi-source lane positioning model to obtain the lane information where the host vehicle is located; the methods include: Based on the synchronized multi-source basic positioning data, perform dynamic judgment to determine the data participating in the calculation; the data participating in the calculation includes roadside basic positioning data and GPS side basic positioning data, or host vehicle side basic positioning data and GPS side basic positioning data; Based on the data participating in the calculation, perform lane positioning fusion to obtain the host vehicle lane positioning information.

[0009] A further optimized solution is that the step of performing dynamic judgment to determine the data participating in the calculation based on the multi-source basic positioning data after spatio-temporal alignment and data synchronization; the methods include: Based on any one of the multi-source basic positioning data, obtain the occlusion area parameter of the host vehicle in the current traffic environment; Preset an occlusion area parameter threshold. When the occlusion area parameter exceeds the occlusion area parameter threshold, use the host vehicle side basic positioning data and GPS side basic positioning data as the data participating in the calculation; otherwise, use the roadside basic positioning data and GPS side basic positioning data as the data participating in the calculation.

[0010] A further optimization solution is that the lane positioning information of the host vehicle is obtained by fusing lane positioning based on the data participating in the calculation; the method includes: Preprocess the GPS-based basic positioning data based on the Kalman filtering algorithm; Considering the motion characteristics of the host vehicle, establish a hidden Markov fusion model based on lidar data and GPS data; Based on the hidden Markov fusion model, fuse the radar positioning data with the preprocessed GPS-based basic positioning data to obtain the lane positioning information of the host vehicle. The radar positioning data includes: the basic positioning data on the host vehicle side or the basic positioning data on the roadside.

[0011] A further optimization solution is that the construction method of the hidden Markov fusion model includes: Taking the lane as the hidden state, and the radar positioning data and GPS-based basic positioning data as the observation states; taking the time stamp of the observation state as the initial state probability distribution vector, and performing state transition according to the distance relationship between adjacent frames; taking the relative position, global position and driving parameter similarity of the host vehicle as the reference factors of the observation probability matrix, and constructing a hidden Markov fusion model; among them, the observation states include the driving speed and driving direction of the host vehicle; the hidden states include the lane position where the host vehicle is located and the driving direction of the host vehicle; Dynamically optimize the state transition probability in the state transition matrix according to the confidence level W: ; Among them, N1 represents the number of point clouds in the current frame; N2 represents the threshold of the number of effective verification point clouds; K represents the point cloud number coefficient; e represents the natural logarithm base.

[0012] A further optimization solution is that the third-party service platform constructs a dynamic scene around the host vehicle based on the primary operation result, and displays the dynamic scene around the host vehicle in real time on the navigation platform based on the digital twin technology; the method includes: Identify the traffic entities around the host vehicle based on the synchronized multi-source basic positioning data; Obtain the map of the target section, and render a static scene based on the Unity software or Unreal Engine software; the static scene includes: lane lines, road shoulders and green belts; Construct a dynamic scene in the static scene based on the lane information where the host vehicle is located, the traffic entities around the host vehicle, and the denoising collaborative data; the dynamic scene includes: the 3D model of the host vehicle and the traffic entity models around the host vehicle; Differentially display the weather warning information and traffic warning information in the dynamic scene.

[0013] A further optimization solution is that the weather warning information and traffic warning information are also displayed in real time in text form or voice form.

[0014] A further optimization solution is that the dynamic scenario around the host vehicle is twin - displayed in full - screen mode or split - screen mode based on the navigation data of the navigation platform.

[0015] This solution also provides a navigation system based on vehicle - road - cloud and digital - twin technologies for implementing the above - mentioned navigation method based on vehicle - road - cloud and digital - twin technologies. The system includes: a third - party service platform, a navigation platform, and a vehicle - road - cloud platform. The third - party service platform is used to request the navigation platform to start navigation; it is also used to request to start the vehicle - road - cloud platform after the navigation platform successfully starts navigation. The navigation platform is used to display navigation data in real - time. The vehicle - road - cloud platform is used to collect collaborative data and perform primary operations, and is also used to send the primary operation results to the third - party service platform. The primary operations include determining weather warning information and the lane information where the host vehicle is located, and denoising the collaborative data. The third - party service platform is also used to construct a dynamic scenario around the host vehicle based on the primary operation results, and twin - display the dynamic scenario around the host vehicle on the navigation platform in real - time based on digital - twin technology. The dynamic scenario around the host vehicle includes: weather warning information, the environment information around the host vehicle, and traffic warning information.

[0016] This solution also provides a computer - readable medium with a computer program stored thereon. The computer program, when executed by a processor, can implement the above - mentioned navigation method based on vehicle - road - cloud and digital - twin technologies.

[0017] Compared with the prior art, the present invention has the following advantages and beneficial effects: 1. The navigation method, system, and medium based on vehicle - road - cloud and digital - twin technologies provided by the present invention improve the method on the basis of traditional navigation technologies. This solution obtains the scenario data around the host vehicle (including the lane information where the host vehicle is located, etc.), as well as blind - spot warning, abnormal parking warning, and abnormal weather warning data around the host vehicle based on vehicle - road - cloud technologies. Finally, through digital - twin technology, it presents and reminds on the navigation platform, enabling multi - lane display on the road, and can display the positions of the current vehicle and surrounding vehicles on the lanes in real - time. At the same time, the navigation data of the navigation platform can also be displayed simultaneously, facilitating users to more intuitively understand the scenario situation and warning information around the host vehicle.

[0018] 2. The navigation method, system and medium based on vehicle-road-cloud and digital twin technologies provided by the present invention; in order to ensure the timeliness of the dynamic scenario around the host vehicle, the vehicle-road-cloud platform performs simple primary operations on the collaborative data to obtain a primary operation result, and the third-party service platform constructs the dynamic scenario around the host vehicle based on the primary operation result. Different platforms cooperate in computing, and multiple platforms collaborate and optimize the division of labor; instead of piling up all the computing work on a single platform, the computing efficiency is effectively improved, and the timeliness and effectiveness of the dynamic scenario around the host vehicle are ensured. In addition, during the primary operation process, the vehicle-road-cloud platform denoises the collaborative data according to the needs of constructing the host vehicle's surrounding environment information and traffic warning information, avoiding the transmission and calculation of irrelevant data from affecting the generation efficiency of the dynamic scenario around the host vehicle; 3. The navigation method, system and medium based on vehicle-road-cloud and digital twin technologies provided by the present invention; through digital twin technology, information such as weather warnings (such as fog visibility models), traffic warnings (situations such as illegal parking / abnormal overtaking around the scene), and the lane where the host vehicle is located are uniformly mapped to the navigation platform, realizing the spatial and hierarchical information expression that traditional navigation (2D arrows + voice) cannot provide. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts. In the drawings: Figure 1 It is a schematic flow chart of the navigation method based on vehicle-road-cloud and digital twin technologies; Figure 2 It is a schematic diagram of the navigation data flow based on vehicle-road-cloud and digital twin technologies. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] To make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the embodiments and the drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0021] Although the traditional navigation interface can provide users with basic road directions, turning prompts and traffic conditions, there are problems such as single information presentation and poor interactivity; in view of this, the following embodiments are provided in this solution to solve the above technical problems.

[0022] Embodiment 1: This embodiment provides a navigation method based on vehicle-road-cloud and digital twin technologies, which is implemented based on a third-party service platform, a navigation platform and a vehicle-road-cloud platform; as Figure 1And Figure 2 As shown, the method includes: Step 1: The third-party service platform requests the navigation platform to turn on navigation; Step 2: After the navigation platform successfully turns on navigation, the navigation data is displayed in real time. At the same time, the third-party service platform requests to turn on the vehicle-road-cloud platform; Step 3: The vehicle-road-cloud platform collects collaborative data and performs primary operations; the vehicle-road-cloud platform sends the primary operation results to the third-party service platform; the primary operations include determining weather warning information and the lane information where the host vehicle is located, and denoising the collaborative data; The vehicle-road-cloud platform collects collaborative data and performs primary operations; including methods: S31, collect and copy the collaborative data to obtain 2 sets of collaborative data, and perform the following parallel operations on the 2 sets of collaborative data respectively: For the first set of collaborative data: delete invalid data and multi-source basic positioning data to obtain denoised collaborative data; the multi-source basic positioning data includes: roadside basic positioning data, host vehicle side basic positioning data, and GPS side basic positioning data; in this step, the GPS side basic positioning data can be the high-precision GPS positioning data on the vehicle, or the GPS on the smartphone. Since the penetration rate of smartphones with global positioning system functions is as high as 93.3% currently. Therefore, this solution integrates the smartphone side, roadside side, and host vehicle side to achieve effective lane-level recognition.

[0023] For the second set of collaborative data: respectively extract multi-source basic positioning data and weather data; perform spatio-temporal alignment and data synchronization processing on the multi-source basic positioning data to obtain synchronized multi-source basic positioning data; input the synchronized multi-source basic positioning data into the pre-constructed multi-source lane positioning model to obtain the lane information where the host vehicle is located; in this step, based on the precision time protocol, the device clocks of the unified roadside side and host vehicle side are based, and the time deviation is controlled within ±10ms. For asynchronous data, the interpolation method is used to compensate for the time delay; taking the roadside side or the host vehicle side as the reference, a global coordinate system is established, and the data of other sides is subjected to coordinate transformation.

[0024] Inputting the synchronized multi-source basic positioning data into the pre-constructed multi-source lane positioning model to obtain the lane information where the host vehicle is located; including methods: S311, based on the synchronized multi-source basic positioning data, perform dynamic judgment to determine the data participating in the calculation; the data participating in the calculation includes roadside basic positioning data and GPS side basic positioning data, or host vehicle side basic positioning data and GPS side basic positioning data; this step specifically includes methods: S3111, based on any one of the multi-source basic positioning data, obtain the occlusion area parameters of the host vehicle in the current traffic environment; S3112. Preset the occlusion area parameter threshold. When the occlusion area parameter exceeds the occlusion area parameter threshold, use the host vehicle side basic positioning data and the GPS side basic positioning data as the data for participating in the calculation; otherwise, use the roadside basic positioning data and the GPS side basic positioning data as the data for participating in the calculation. Specifically, the occlusion area parameter can be parameters such as area, volume, point cloud density, etc. that can characterize the occlusion area. For example, for the roadside basic positioning data, calculate the change rate of the point cloud density of the host vehicle in the current traffic environment. If the point cloud density is lower than the occlusion area parameter threshold (such as <50 points / square meter) for more than 3 frames, it is determined as occlusion, and use the host vehicle side basic positioning data and the GPS side basic positioning data as the data for participating in the calculation; for the host vehicle side basic positioning data, use an in-vehicle camera + YOLOv8 to detect the bounding box size and position of the front obstacle (such as a truck, a bus); if the obstacle covers the central area of the image (such as the area ratio > 30% of the occlusion area parameter threshold), it is determined as occlusion, and use the host vehicle side basic positioning data and the GPS side basic positioning data as the data for participating in the calculation; for the GPS side basic positioning data, monitor the signal-to-noise ratio (SNR), the number of visible satellites, and the horizontal dilution of precision (HDOP) of the GPS in real time: if the signal-to-noise ratio SNR < the signal-to-noise ratio threshold of 20 dB, the number of visible satellites ≤ the number threshold of 4, and the horizontal dilution of precision HDOP > the horizontal positioning precision threshold of 3.0, then it is determined as non-occlusion, and use the host vehicle side basic positioning data and the GPS side basic positioning data as the data for participating in the calculation; in addition, it can also be matched according to the real-time GPS positioning result and the occlusion marker area (such as the tunnel entrance, under the overpass) in the high-precision map; if the position of the host vehicle enters the predefined blind area polygon in the map, trigger in advance to use the host vehicle side basic positioning data and the GPS side basic positioning data as the data for participating in the calculation.

[0025] S312. Perform lane positioning fusion based on the data for participating in the calculation to obtain the host vehicle lane positioning information. This step specifically includes the method: S3121. Preprocess the GPS side basic positioning data based on the Kalman filter algorithm; S3122. Considering the motion characteristics of the host vehicle, establish a hidden Markov fusion model based on lidar data and GPS data; S3123. Based on the hidden Markov fusion model, fuse the radar positioning data and the preprocessed GPS side basic positioning data to obtain the host vehicle lane positioning information, where the radar positioning data includes: the host vehicle side basic positioning data or the roadside basic positioning data.

[0026] The construction method of the hidden Markov fusion model includes: Taking the lane as the hidden state and the radar positioning data and GPS-based basic positioning data as the observation state; using the timestamp of the observation state as the initial state probability distribution vector and performing state transition according to the distance relationship between adjacent frames; constructing a hidden Markov fusion model with the relative position, global position, and driving parameter similarity of the host vehicle as the reference factors for the observation probability matrix; Among them, the observation state includes the driving speed and driving direction of the host vehicle; the hidden state includes the lane position where the host vehicle is located and the driving direction of the host vehicle; The initial state probability distribution vector is: , where I represents the number of all lidar point cloud data with the same timestamp as the observation state; calculating the observation probability matrix based on the following formula: ; Among them, b i represents the observation probability in the hidden state i; p1 represents the likelihood probability of the lateral deviation between the center of the host vehicle and the lane centerline in the hidden state i; β1 represents the weight of p1; p2 represents the likelihood probability of the lateral position of the host vehicle when the GPS coordinates of the host vehicle are projected onto the lane coordinate system in the hidden state i; β2 represents the weight of p2; n represents the total number of hidden states; H i represents the speed similarity parameter of the radar positioning data and GPS-based basic positioning data in the hidden state i; S i represents the driving direction parameter of the radar positioning data and GPS-based basic positioning data in the hidden state i; ; ; Among them, α represents the radar ranging error; d represents the lateral deviation between the center of the host vehicle and the lane centerline; L i represents the lateral coordinate of the lane centerline; γ represents the GPS horizontal positioning error; (x i , y i ) represents the coordinates of the lane center reference point; (x, y) represents the GPS positioning coordinates of the host vehicle; The radar positioning data and GPS-based basic positioning data both come from the same target. Therefore, the speeds of the lidar trajectory and GPS trajectory at the same moment should be similar. Hence, the corresponding speed similarity parameter is constructed; similarly, for the two types of data of the same target, the information contained should be consistent; therefore, the driving direction of the target should be the same on the road section. Hence, the driving direction parameter is constructed; ; ;

[0027] Among them, v1 represents the driving speed of the host vehicle in the radar positioning data; v2 represents the driving speed of the host vehicle in the GPS-based basic positioning data; F1 represents the driving direction of the host vehicle in the radar positioning data; F2 represents the driving direction of the host vehicle in the GPS-based basic positioning data.

[0028] S3124, dynamically optimize the state transition probability in the state transition matrix according to the confidence level W: ; Among them, N1 represents the number of point clouds in the current frame; N2 represents the threshold of the number of effective verification point clouds; K represents the point cloud number coefficient; e represents the natural logarithm base.

[0029] For weather data: perform early warning determination to obtain weather early warning information; specifically, pre-set an LSTM prediction network model or a random forest model, and predict abnormal weather phenomena (such as the generation and dissipation time of abnormal weather such as patchy fog) based on weather data obtained from the meteorological bureau API, roadside sensors (such as visibility detectors, temperature sensors), in-vehicle sensors (such as cameras to detect rain and snow), and even crowd-sourced data from users, so as to combine weather data with the existing navigation system and improve driving safety.

[0030] Although the collaborative data denoising, the operation of the lane information where the host vehicle is located, and the operation of the weather early warning information are parallel operations, the operation process of the collaborative data denoising is simple, so it is completed first, followed by the weather early warning information, and finally the lane information where the host vehicle is located. In order to ensure the effectiveness of the dynamic scenario around the host vehicle, when the vehicle-road-cloud platform sends the primary operation results to the third-party service platform, it can be sent in the order of completion of the collaborative data denoising, the operation of the lane information where the host vehicle is located, and the operation of the weather early warning information. If the collaborative data denoising is completed first, the denoised collaborative data will be sent first, and the denoised collaborative data will also be preferentially required in the subsequent construction of the dynamic scenario around the host vehicle. In the actual application process, multi-source positioning mainly includes: the high-precision positioning source of the host vehicle, the roadside perception source, and the in-vehicle perception source; a lightweight multi-source lane positioning model is constructed and configured on the vehicle-road-cloud platform, and the corresponding primary operations are completed on the vehicle-road-cloud platform side.

[0031] S32, use the denoised collaborative data, synchronized multi-source basic positioning data, the lane information where the host vehicle is located, and the weather early warning information as the primary operation results.

[0032] Step 4: The third-party service platform constructs the dynamic scenario around the host vehicle based on the primary operation results, and displays the dynamic scenario around the host vehicle in real time on the navigation platform based on digital twin technology; the dynamic scenario around the host vehicle includes: weather early warning information, the environmental information around the host vehicle, and traffic early warning information; this step specifically includes the method: S41. Identify the traffic entities around the host vehicle based on the synchronized multi-source basic positioning data. This step specifically includes the following methods: Perform radar point cloud clustering based on the DBSCAN algorithm to track different traffic entity targets (which can be achieved relying on the motion models of vehicles and pedestrians), independently run the Kalman filter for each traffic entity target, and fuse the roadside radar data with the on-vehicle radar data to identify different traffic entity targets. S42. Obtain the map of the target road section and render the static scene based on Unity software or Unreal Engine software. The static scene includes lane lines, road shoulders, and green belts. S43. Construct a dynamic scene in the static scene based on the lane information of the host vehicle, the traffic entities around the host vehicle, and the denoised collaborative data. The dynamic scene includes the 3D model of the host vehicle and the traffic entity models around the host vehicle. S44. Differentially display the weather warning information and traffic warning information in the dynamic scene.

[0033] The weather warning information and traffic warning information are also displayed in real-time twin in text form or voice form. The dynamic scene around the host vehicle is displayed in full-screen mode or split-screen mode based on the navigation data of the navigation platform. In split-screen mode, the dynamic scene around the host vehicle and the navigation data are displayed separately. In full-screen mode, the dynamic scene around the host vehicle covers the navigation data. Regardless of split-screen mode or full-screen mode, the weather warning information and traffic warning information in text form are displayed within the dynamic scene around the host vehicle.

[0034] This embodiment provides a navigation method based on vehicle-road-cloud and digital twin technologies. Scene data around the host vehicle (including information such as the lane where the host vehicle is located), as well as blind spot warning, abnormal parking warning, and abnormal weather warning data around the host vehicle are obtained based on vehicle-road-cloud technologies. Finally, through digital twin technologies, it is presented and reminded on the navigation platform, enabling multi-lane display on the road and allowing the positions of the current vehicle and surrounding vehicles to be displayed on the lane in real time. At the same time, the navigation data of the navigation platform can also be displayed simultaneously, facilitating users to more intuitively understand the scene situation around the host vehicle and the warning information. On the other hand, to display the positions of the current vehicle and surrounding vehicles on the lane in real time, there are strict requirements for the time-consuming of parsing and calculating vehicle-road-cloud data, transmission time, construction and display time of the dynamic scene around the host vehicle, etc. If the time-consuming is too long, the warning information and even the entire dynamic scene around the host vehicle are very likely to become invalid. Therefore, in order to ensure the timeliness of the dynamic scene around the host vehicle in this solution, the vehicle-road-cloud platform performs simple primary operations on the collaborative data to obtain a primary operation result, and the third-party service platform constructs the dynamic scene around the host vehicle based on the primary operation result. Different platforms cooperate in calculation, and multiple platforms collaborate, optimize, and divide the work; instead of piling up all the calculation work on a certain platform, effectively improving the calculation efficiency and ensuring the timeliness and effectiveness of the dynamic scene around the host vehicle. In addition, during the primary operation process, the vehicle-road-cloud platform denoises the collaborative data according to the needs of constructing the host vehicle's surrounding environment information and traffic warning information, avoiding the transmission and calculation of irrelevant data from affecting the generation efficiency of the dynamic scene around the host vehicle; In this embodiment, through digital twin technologies, information such as weather warnings (such as fog visibility models), traffic warnings (situations such as illegal parking / abnormal overtaking around the scene), and the lane where the host vehicle is located are uniformly mapped to the navigation platform, realizing a spatial and hierarchical information expression that traditional navigation (2D arrows + voice) cannot provide.

[0035] Embodiment 2: This embodiment provides a navigation system based on vehicle-road-cloud and digital twin technologies for implementing the navigation method based on vehicle-road-cloud and digital twin technologies described in Embodiment 1; the system includes: a third-party service platform, a navigation platform, and a vehicle-road-cloud platform; The third-party service platform is used to request the navigation platform to start navigation; it is also used to request to start the vehicle-road-cloud platform after the navigation platform successfully starts navigation; The navigation platform is used to display navigation data in real time; The vehicle-road-cloud platform is used to collect collaborative data and perform primary operations, and is also used to send the primary operation result to the third-party service platform; the primary operations include determining weather warning information and the lane information where the host vehicle is located, and denoising the collaborative data; The third-party service platform is also used to construct the main vehicle's weekly dynamic scenario based on the primary operation result, and display the real-time digital twin of the main vehicle's weekly dynamic scenario on the navigation platform based on digital twin technology; the main vehicle's weekly dynamic scenario includes: weather warning information, main vehicle's weekly environment information, and traffic warning information.

[0036] Embodiment 3: This embodiment provides a computer-readable medium, on which a computer program is stored. When the computer program is executed by a processor, it can implement the navigation method based on vehicle-road-cloud and digital twin technology as described in Embodiment 1; specifically, the following steps are executed: Step 1: The third-party service platform requests the navigation platform to start navigation. Step 2: After the navigation platform successfully starts navigation, the navigation data is displayed in real time. At the same time, the third-party service platform requests to start the vehicle-road-cloud platform. Step 3: The vehicle-road-cloud platform collects collaborative data and performs primary operations; the vehicle-road-cloud platform sends the primary operation result to the third-party service platform; the primary operations include determining weather warning information and the lane information where the main vehicle is located, and denoising the collaborative data. Step 4: The third-party service platform constructs the main vehicle's weekly dynamic scenario based on the primary operation result, and displays the real-time digital twin of the main vehicle's weekly dynamic scenario on the navigation platform based on digital twin technology; the main vehicle's weekly dynamic scenario includes: weather warning information, main vehicle's weekly environment information, and traffic warning information.

[0037] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A navigation method based on vehicle-road-cloud and digital twin technology, characterized in that: Implemented based on a third-party service platform, a navigation platform and a vehicle-road-cloud platform; the method includes: The third-party service platform requests the navigation platform to start navigation; After the navigation platform successfully starts navigation, the navigation data is displayed in real time, and at the same time, the third-party service platform requests to start the vehicle-road cloud platform; The vehicle-road cloud platform collects collaborative data and performs primary calculations; the vehicle-road cloud platform sends the primary calculation results to the third-party service platform; the primary calculations include determining weather warning information and lane information of the host vehicle, and denoising the collaborative data; The third-party service platform constructs a dynamic scene around the main vehicle based on the primary calculation results, and displays the dynamic scene around the main vehicle in real time on the navigation platform based on the digital twin technology; the dynamic scene around the main vehicle includes: weather warning information, environmental information around the main vehicle and traffic warning information.

2. The navigation method based on vehicle-road cloud and digital twin technology according to claim 1 is characterized in that: The vehicle-road-cloud platform collects collaborative data and performs primary calculations; including methods: Collect and copy the collaborative data to obtain two sets of collaborative data, and perform the following parallel operations on the two sets of collaborative data: For the first group of collaborative data: deleting invalid data and multi-source basic positioning data to obtain denoised collaborative data; the multi-source basic positioning data includes: roadside basic positioning data, main vehicle side basic positioning data and GPS side basic positioning data; For the second set of collaborative data: Extract multi-source basic positioning data and weather data respectively; Performing spatiotemporal alignment and data synchronization processing on the multi-source basic positioning data to obtain synchronized multi-source basic positioning data; inputting the synchronized multi-source basic positioning data into the constructed multi-source lane positioning model to obtain the lane information of the main vehicle; For weather data: make warning judgments to obtain weather warning information; The primary calculation results are denoised collaborative data, synchronized multi-source basic positioning data, the lane information of the main vehicle and weather warning information.

3. The navigation method based on vehicle-road cloud and digital twin technology according to claim 2 is characterized in that: The synchronous multi-source basic positioning data is input into the constructed multi-source lane positioning model to obtain the lane information of the host vehicle; Included methods: Based on the synchronous multi-source basic positioning data, dynamic judgment is performed to determine the participating calculation data; the participating calculation data includes the road side basic positioning data and the GPS side basic positioning data, or the main vehicle side basic positioning data and the GPS side basic positioning data; Lane positioning fusion is performed based on the participating calculation data to obtain the lane positioning information of the main vehicle.

4. The navigation method based on vehicle-road cloud and digital twin technology according to claim 3 is characterized in that: The dynamic judgment based on the synchronous multi-source basic positioning data determines the participating calculation data; Included methods: Based on any multi-source basic positioning data, obtain the occlusion area parameters of the main vehicle in the current traffic environment; A threshold value of the occlusion area parameter is preset. When the occlusion area parameter exceeds the threshold value, the basic positioning data on the main vehicle side and the basic positioning data on the GPS side are used as the data involved in the calculation; otherwise, the basic positioning data on the road side and the basic positioning data on the GPS side are used as the data involved in the calculation.

5. The navigation method based on vehicle-road cloud and digital twin technology according to claim 3 is characterized in that: The lane positioning fusion is performed based on the participating calculation data to obtain the lane positioning information of the host vehicle; Included methods: Preprocess the basic positioning data on the GPS side based on the Kalman filter algorithm; Considering the motion characteristics of the main vehicle, a hidden Markov model based on lidar data and GPS data is established; Based on the hidden Markov fusion model, the radar positioning data is fused with the pre-processed GPS side basic positioning data to obtain the main vehicle lane positioning information, and the radar positioning data includes: the main vehicle side basic positioning data or the road side basic positioning data.

6. The navigation method based on vehicle-road cloud and digital twin technology according to claim 5 is characterized in that: The method for constructing the hidden Markov fusion model includes: The lane is used as the hidden state, and the radar positioning data and GPS basic positioning data are used as the observed state; the timestamp of the observed state is used as the initial state probability distribution vector, and the state is transferred according to the distance relationship between adjacent frames; the relative position, global position and driving parameter similarity of the main vehicle are used as reference factors of the observation probability matrix to construct a hidden Markov fusion model; the observed state includes the driving speed and driving direction of the main vehicle; the hidden state includes the lane position of the main vehicle and the driving direction of the main vehicle; The state transfer probability in the state transfer matrix is ​​dynamically optimized according to the confidence W: ； Among them, N1 represents the number of point clouds in the current frame; N2 represents the threshold of the number of valid inspection point clouds; K represents the point cloud number coefficient; and e represents the natural base.

7. The navigation method based on vehicle-road cloud and digital twin technology according to claim 3 is characterized in that: The third-party service platform constructs a dynamic scene around the main vehicle based on the primary calculation results, and displays the dynamic scene around the main vehicle in real time on the navigation platform based on the digital twin technology; Included methods: Identify traffic objects around the main vehicle based on synchronized multi-source basic positioning data; Obtain a map of the target road section and render a static scene based on Unity software or Unreal Engine software; The static scene includes: lane lines, road shoulders and green belts; Constructing a dynamic scene in a static scene based on the lane information of the main vehicle, the traffic body around the main vehicle and the denoised collaborative data; the dynamic scene includes: a 3D model of the main vehicle and a model of the traffic body around the main vehicle; Weather warning information and traffic warning information are displayed separately in dynamic scenes.

8. The navigation method based on vehicle-road cloud and digital twin technology according to claim 1 is characterized in that: The weather warning information and traffic warning information are also displayed in real-time twin form in text or voice form; the dynamic scene around the main vehicle is displayed in twin mode in full screen mode or split screen mode based on the navigation data of the navigation platform.

9. The navigation system based on vehicle-road-cloud and digital twin technology is characterized by: Used to implement the navigation method based on vehicle-road-cloud and digital twin technology as described in any one of claims 1 to 8; the system includes: a third-party service platform, a navigation platform and a vehicle-road-cloud platform; The third-party service platform is used to request the navigation platform to start navigation; it is also used to request to start the vehicle-road cloud platform after the navigation platform successfully starts navigation; The navigation platform is used to display navigation data in real time; The vehicle-road cloud platform is used to collect collaborative data and perform primary calculations, and is also used to send the primary calculation results to a third-party service platform; the primary calculations include determining weather warning information and lane information of the host vehicle, and denoising the collaborative data; The third-party service platform is also used to construct dynamic scenes around the main vehicle based on the primary calculation results, and to display the dynamic scenes around the main vehicle in real time on the navigation platform based on the digital twin technology; the dynamic scenes around the main vehicle include: weather warning information, environmental information around the main vehicle and traffic warning information.

10. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the navigation method based on vehicle-road-cloud and digital twin technology as described in any one of claims 1 to 8.

Images