High-precision map cooperative control system and method based on v-pon and v2x, device and medium

Abstract

The application provides a high-precision map cooperative control system and method based on V-PON and V2X, a device and a medium, belonging to the technical field of vehicles. The system comprises a data acquisition module, a vehicle-mounted optical communication module, a vehicle-mounted main control module, a V2X wide-area communication module, a high-precision map cloud, and various vehicle-mounted terminals. Through the vehicle-mounted optical communication module, lossless and low-delay transmission of the original sensing data of the data acquisition module is realized. Through the deep cooperation between the vehicle-mounted optical communication module and the V2X wide-area communication module, the full link of data acquisition, in-vehicle data conversion, cloud processing, incremental distribution, and vehicle terminal application is opened up, real-time sharing of multi-vehicle road condition information in the region is realized, and the limitation of single-vehicle sensing is broken. The vehicle terminal adjusts the driving strategy according to the map incremental update package, displays the latest driving road conditions, and improves the accident avoidance rate. The distribution mode of the incremental update package greatly reduces the operation cost of the cloud and the vehicle terminal, solves the pain point of a long update cycle, and improves the safety and reliability of assisted driving.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a high-precision map collaborative control system, method, device and medium based on V-PON and V2X. Background Technology

[0002] High-precision maps, as a core support for advanced driver assistance systems (ADAS), directly determine the safety and reliability of ADAS based on their timeliness. Current technologies rely on the periodic coverage of dedicated data collection vehicles, which cannot capture dynamically changing road scenarios such as construction barriers, accident scenes, and temporary traffic signs. This leads to a disconnect between the map information relied upon by ADAS and actual road conditions. Furthermore, existing traditional in-vehicle Ethernet and CAN buses cannot meet the requirements for lossless and low-latency transmission, resulting in delayed data fusion and processing. Additionally, the independent links between in-vehicle data transmission and external V2X information interaction, lacking collaborative design, all negatively impact the safety and reliability of ADAS. Summary of the Invention

[0003] The main objective of this application is to propose a high-precision map collaborative control system, method, device, and medium based on V-PON and V2X, so as to solve one or more technical problems existing in the prior art, and at least provide a beneficial option or create conditions.

[0004] To achieve the above objectives, one aspect of this application proposes a high-precision map collaborative control system based on V-PON and V2X, the system comprising: Vehicle-mounted terminal; The data acquisition module is used to acquire the current vehicle's operating data and output raw perception data. The vehicle-mounted optical communication module is used to transmit the original sensing data and distribute the map incremental update package downloaded from the cloud of the high-precision map to each of the vehicle-mounted terminals. The vehicle-mounted main control module is connected to the data acquisition module and each of the vehicle-mounted terminals through the vehicle-mounted optical communication module. The vehicle-mounted main control module is used to convert the raw perception data into key change information, encapsulate the key change information, and receive the map incremental update package. The V2X wide area communication module is connected to the vehicle main control module. The V2X wide area communication module is used to encrypt and upload the key change information and receive the map incremental update package. The high-precision map cloud establishes a wireless connection with the V2X wide-area communication module. The high-precision map cloud is used to decrypt and verify the key change information uploaded by each current vehicle, and generate the map incremental update package based on the key change information.

[0005] Furthermore, the vehicle-mounted optical communication module includes: A first optical communication link is connected to the data acquisition module and the vehicle main control module respectively, and the first optical communication link is used to transmit the raw sensing data. The second optical communication link is connected to each of the vehicle terminals and the vehicle main control module, and is used to distribute the map incremental update package to each of the vehicle terminals.

[0006] Furthermore, the V2X wide-area communication module includes: The V2X vehicle communication unit is connected to the vehicle main control module and wirelessly connected to the high-precision map cloud. A roadside communication unit, which is wirelessly connected to the V2X vehicle-mounted communication unit, is used to extend the communication range of the high-precision map cloud. A 5G communication unit is wirelessly connected to the high-precision map cloud and is also connected to the V2X vehicle-mounted communication unit and the roadside communication unit.

[0007] Furthermore, the high-precision map cloud includes: A data verification module is wirelessly connected to the 5G communication unit. The data verification module is used to decrypt and verify the key change information according to the set map database to obtain the key change information that has passed the verification. An update package generation module is connected to the data verification module. The update package generation module is used to generate the map incremental update package based on the set map database and the verified key change information. The V2X broadcast module is connected to the update package generation module and wirelessly connected to the 5G communication unit. The V2X broadcast module is used to broadcast the map incremental update package to each of the vehicle terminals.

[0008] To achieve the above objectives, one aspect of this application proposes a high-precision map collaborative control method based on V-PON and V2X, the method comprising: The vehicle-mounted terminal acquires the current vehicle's operating data, processes the operating data, outputs raw sensing data, and transmits the raw sensing data using the vehicle-mounted optical communication module. The vehicle-mounted terminal converts the raw sensing data into key change information, encapsulates the key change information, and encrypts and uploads the key change information using a V2X wide area communication module. The high-precision map cloud decrypts and verifies the key change information uploaded by each current vehicle, generates a map incremental update package based on the key change information, and broadcasts the map incremental update package to each current vehicle in the area based on the key change information using the V2X wide area communication module. The vehicle-mounted terminal receives the corresponding map incremental update package and distributes the map incremental update package to each vehicle-mounted terminal using the vehicle-mounted optical communication module, so that each vehicle-mounted terminal can parse and apply the map incremental update package, adjust the driving strategy, and update and display the latest driving conditions.

[0009] Furthermore, the vehicle-mounted terminal converts the raw sensing data into key change information, including: Using the established multi-sensor fusion algorithm, the original sensing data is denoised and features are extracted to generate the key change information; The key change information is encapsulated in a standardized format using the established data encapsulation protocol.

[0010] Furthermore, the high-precision map cloud verifies and decrypts the key change information uploaded by each current vehicle, including: The key change information is decrypted to determine the current vehicles at the same location within the area. The established multi-source data cross-validation algorithm is used to compare the consistency of the key change information uploaded by multiple current vehicles at the same location to determine the valid key change information. The system calls the established map database to obtain historical map data. Based on the historical map data, misidentified information is removed from the valid key change information to obtain the verified key change information.

[0011] Furthermore, generating the map incremental update package based on the key change information includes: Based on the verified key change information, the established map database is invoked to obtain the original high-precision map data; By comparing the original high-precision map data with the verified key change information, the difference feature data, difference coordinate range, and difference event type are extracted. Based on the difference feature data, the difference coordinate range, and the difference event type, the set compression algorithm is used to generate the map incremental update package, so as to update the event identifier, coordinate range, and feature data block in the core fields of the map incremental update package accordingly.

[0012] To achieve the above objectives, another aspect of the embodiments of this application proposes a vehicle control device, including a memory, a processor, and a program stored in the memory and executable on the processor. When the program is executed by the processor, it implements the above-described high-precision map collaborative control method based on V-PON and V2X.

[0013] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described high-precision map collaborative control method based on V-PON and V2X.

[0014] The embodiments of this application include at least the following beneficial effects: This application provides a high-precision map collaborative control system, method, device, and medium based on V-PON and V2X. This solution utilizes the network technology characteristics of the vehicle-mounted optical communication module to achieve lossless and low-latency transmission of raw sensing data, providing stable data support for the rapid fusion processing of the vehicle-mounted main control module and improving data processing efficiency; through deep collaboration between the vehicle-mounted optical communication module and the V2X wide-area communication module, it connects the entire link of data acquisition, in-vehicle data conversion, cloud processing, incremental distribution, and vehicle terminal application, realizing real-time sharing of multi-vehicle road condition information within the area and breaking the limitations of single-vehicle perception; the vehicle terminal can update the data packet incrementally according to the map. Adjusting driving strategies and updating the latest road conditions enables advance risk prediction and improves accident avoidance rates. Instead of relying on numerous dedicated data collection vehicles, map updates are achieved using the distributed perception resources of a vast number of vehicles, reducing deployment and maintenance costs. Simultaneously, the incremental update package distribution model reduces network bandwidth usage, significantly decreasing cloud and vehicle-side operating costs. A three-tiered collaborative architecture is constructed, consisting of the in-vehicle high-speed transmission layer of the vehicle-mounted optical communication module, the interaction layer of the V2X wide-area communication module, and the cloud-based intelligent processing layer. Through end-to-end optimization, real-time updates and distribution of high-precision maps are achieved, addressing the pain point of long update cycles in existing technologies and achieving minute-level updates, thus enhancing the safety and reliability of assisted driving. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the framework of the high-precision map collaborative control system based on V-PON and V2X provided in the embodiments of this application; Figure 2 This is a flowchart of the high-precision map collaborative control method based on V-PON and V2X provided in the embodiments of this application; Figure 3 This is a timing diagram of the high-precision map collaboration process based on V-PON and V2X provided in the embodiments of this application. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0017] It is understood that the terms "first," "second," etc., used in this application may be used to describe various concepts herein, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of embodiments of this application, Ethernet signaling information may also be referred to as interface signaling information, and similarly, interface signaling information may also be referred to as Ethernet signaling information. Depending on the context, the words "if" or "when" as used herein may be interpreted as "when," "in response to a determination," or "in the event of a determination."

[0018] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0019] Unless otherwise defined, 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 application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0020] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0021] V-PON networks typically refer to vehicular passive optical networks.

[0022] V2X wide-area communication network is a C-V2X (Cellular-V2X) technology system based on cellular mobile communication networks, which supports long-distance information interaction between vehicles and the cloud and network.

[0023] The Roadside Unit (RSU) is a critical infrastructure device deployed at the edge of the road in an Intelligent Transportation System (ITS), serving as a core node for realizing vehicle-road cooperation and vehicle-to-everything (V2X) communication. Essentially, it is a multi-functional edge computing and communication gateway located between the road infrastructure and the Onboard Unit (OBU), responsible for bidirectional information exchange and processing.

[0024] In some embodiments of one aspect of the present invention Figure 1 This is an optional structural framework diagram of a high-precision map collaborative control system based on V-PON and V2X provided in the embodiments of this application. Figure 1 The system may include, but is not limited to: data acquisition module, vehicle optical communication module, vehicle main control module, V2X wide area communication module, high-precision map cloud, and various vehicle terminals in the current vehicle.

[0025] In one embodiment, each vehicle terminal, data acquisition module, vehicle optical communication module, and vehicle main control module are modules in the vehicle terminal and can serve as a sensing and in-vehicle transmission layer.

[0026] The signal output interface of the data acquisition module is connected to the input end of the vehicle optical communication module via an automotive-grade cable. The vehicle optical communication module is connected to the input end of the vehicle main control module. The vehicle optical communication module is connected to the input end of each vehicle terminal via another fiber optic link of the vehicle optical communication module.

[0027] The vehicle-mounted optical communication module includes a V-PON optical unit. The output of the V-PON optical unit is connected to a passive optical splitter via an optical fiber link. The optical splitter is connected to the optical module input of the vehicle-mounted main control module via an optical fiber link.

[0028] The data acquisition module includes a lidar unit, an image acquisition unit, and a positioning unit. The lidar unit is used to acquire 3D point cloud data of the road, the image acquisition unit is used to acquire road marking image data, and the positioning unit is used to obtain the coordinate positioning of the perception data. The three work together to output the raw perception data.

[0029] The vehicle-mounted optical communication module adopts passive optical transmission technology to transmit raw perception data to the vehicle main control module without loss and with low latency. At the same time, it quickly distributes map incremental update packages from the cloud to each vehicle terminal. It is free from electromagnetic interference and has strong anti-interference capabilities.

[0030] The vehicle-mounted main control module interacts with the V-PON network through the PCIe 4.0 interface, is equipped with a heterogeneous computing platform, and runs the designed multi-sensor fusion algorithm and data encapsulation protocol to transform the unstructured raw sensing data from the data acquisition module into key change information that can be uploaded.

[0031] In one embodiment, the V2X wide-area communication module can serve as an external interaction layer. The V2X wide-area communication module connects to the Ethernet output interface of the vehicle's main control module and establishes a wireless connection with the high-precision map cloud platform. The V2X wide-area communication module can encrypt and upload key change information processed by the vehicle's main control module to the high-precision map cloud platform, while simultaneously receiving map incremental update packets from the high-precision map cloud platform. The AES-256 encryption algorithm can be used for encryption.

[0032] In one embodiment, the high-precision map cloud can serve as a cloud processing layer. The high-precision map cloud is wirelessly connected to a V2X wide-area communication module to receive key change information uploaded by multiple vehicles.

[0033] The high-precision map cloud can decrypt and verify key change information uploaded by each vehicle within the area. Based on this key change information, it generates incremental map update packets and dynamically adjusts the V2X broadcast coverage. Utilizing the V2X wide-area communication module, incremental map update packets are transmitted at a frequency of 10Hz to ensure rapid reception by vehicles within the area.

[0034] Each vehicle terminal receives incremental map update packets through the vehicle optical communication module, updates the local map cache and incorporates decision planning algorithms, and displays the latest driving conditions in real time with a response time of ≤50ms.

[0035] This application leverages the network technology characteristics of the vehicle-mounted optical communication module to achieve lossless and low-latency transmission of raw sensing data, providing stable data support for the rapid fusion processing of the vehicle-mounted main control module and improving data processing efficiency. Through deep collaboration between the vehicle-mounted optical communication module and the V2X wide-area communication module, it establishes a complete link connecting data acquisition, in-vehicle data conversion, cloud processing, incremental distribution, and vehicle terminal applications, enabling real-time sharing of road condition information among multiple vehicles within a region and breaking through the limitations of single-vehicle sensing. The vehicle terminal can adjust its driving strategy based on map incremental update packages, updating and displaying the latest road conditions, and enabling early risk prediction. This improves the accident avoidance rate; it eliminates the need to rely on a large number of dedicated data collection vehicles, utilizing the distributed perception resources of a massive number of vehicles to achieve map updates, reducing the deployment and maintenance costs of data collection vehicles. At the same time, the incremental update package distribution mode reduces network bandwidth consumption, significantly reducing the operating costs of the cloud and the vehicle. The in-vehicle high-speed transmission layer of the vehicle optical communication module, the interaction layer of the V2X wide-area communication module, and the cloud intelligent processing layer construct a three-level collaborative architecture, achieving real-time updates and distribution of high-precision maps through end-to-end optimization, solving the pain point of long update cycles in existing technologies, achieving minute-level updates, and improving the safety and reliability of assisted driving.

[0036] Reference Figure 1 In one embodiment of the present invention, the vehicle-mounted optical communication module includes: a first optical communication link and a second optical communication link.

[0037] The input end of the first optical communication link is connected to the output end of the data acquisition module, and the output end of the first optical communication link is connected to the vehicle main control module. The first optical communication link can transmit raw sensing data.

[0038] Specifically, the first optical communication link includes: a V-PON optical unit, a first optical fiber link, and a passive optical splitter. The input end of the V-PON optical unit is connected to the output interface of the data acquisition module, the output end of the V-PON optical unit is connected to the passive optical splitter through the first optical fiber link, and the optical splitter is connected to the optical module input end of the vehicle-mounted main control module through the first optical fiber link.

[0039] The first optical communication link transmits uplink data, using time-division multiplexing to transmit raw sensing data.

[0040] The input end of the second optical communication link is connected to the output end of the vehicle main control module, and the output end of the second optical communication link is connected to each vehicle terminal in the current vehicle. The second optical communication link can quickly distribute the map incremental update package sent from the cloud to each vehicle terminal in the current vehicle, without electromagnetic interference and with strong anti-interference capability.

[0041] Specifically, the second optical communication link includes: a V-PON optical unit, a second optical fiber link, and a passive optical splitter. The input end of the V-PON optical unit is connected to the vehicle main control module, the output end of the V-PON optical unit is connected to the passive optical splitter through the second optical fiber link, and the optical splitter is connected to the optical module input end of each vehicle terminal through the second optical fiber link.

[0042] The second optical communication link transmits downlink data and distributes map incremental update packets via broadcast.

[0043] In this embodiment, the V-PON network adopts passive optical transmission, which is free from electromagnetic interference and has a bandwidth of 10Gbps (expandable to 50Gbps). It perfectly adapts to the massive data transmission requirements of LiDAR and image acquisition, ensuring a data loss rate of ≥99.9% and a latency of ≤1ms. This solves the transmission bottleneck of traditional in-vehicle networks, provides a data foundation for subsequent rapid fusion processing, and solves the problems of high latency and easy packet loss in the transmission of massive raw sensing data in vehicles, which leads to low fusion processing efficiency.

[0044] In one embodiment of the present invention, the V2X wide-area communication module includes: a V2X vehicle-mounted communication unit, a roadside communication unit, and a 5G communication unit.

[0045] The input terminal of the V2X vehicle communication unit is connected to the Ethernet output interface of the vehicle main control module. The V2X vehicle communication unit establishes a wireless connection with the roadside communication unit and the high-precision map cloud platform through the 5G public network / C-V2X dedicated frequency band. The 5G communication unit is connected to the roadside communication unit, and the 5G communication unit also establishes a wireless connection with the high-precision map cloud platform.

[0046] The V2X vehicle communication unit supports dual-mode communication with 5G communication unit and C-V2X direct connection. The V2X vehicle communication unit can encrypt and upload key change information processed by the vehicle main control module to the cloud; at the same time, it can receive map incremental update packages sent from the cloud.

[0047] The roadside communication unit acts as a regional communication relay node, expanding the coverage of V2X broadcasts and ensuring that incremental update packets quickly reach all current vehicles in the area.

[0048] In this embodiment, through deep collaboration between V-PON and V2X, a closed-loop collaborative system is constructed, connecting the entire chain from data collection to in-vehicle aggregation, cloud processing, incremental distribution, and terminal application. This enables real-time sharing of road condition information among multiple vehicles within the region, breaking the limitations of single-vehicle perception. It also addresses the insufficient collaboration between in-vehicle networks and V2X wide area networks, resolving the issues of single-vehicle perception data not being shared and the link being fragmented.

[0049] In one embodiment of the present invention, the high-precision map cloud includes: a data verification module, an update package generation module, a V2X broadcast module, and a set map database.

[0050] The data verification module is wirelessly connected to the 5G communication unit via a dedicated line to receive key change information uploaded by multiple current vehicles. The output of the data verification module is connected to the input of the update package generation module. The update package generation module is bidirectionally connected to the V2X broadcast module and the established map database. The V2X broadcast module communicates with the roadside communication unit and the V2X vehicle communication unit through the 5G communication unit.

[0051] The data verification module can decrypt the key change information uploaded by each current vehicle, run the set multi-source data cross-validation algorithm, and verify the key change information. That is, it compares the consistency of data uploaded by multiple vehicles at the same location, calculates the data similarity between multiple vehicles, determines the valid data based on the data similarity, and eliminates misidentified information by combining historical map data to obtain the key change information that has passed the verification.

[0052] Specifically, when the data similarity is greater than or equal to a set threshold, the key change information uploaded by the current vehicle is considered valid data. The established map database stores raw high-precision map data and historical incremental update records, supporting rapid querying and comparison. Historical map data can be obtained by accessing the established map database. False identification information can be caused by sensor malfunctions resulting in misinformation.

[0053] The update package generation module can generate incremental map update packages based on verified key change information and by comparing it with the original high-precision map data. Specifically, it uses the verified key change information to call the established map database to obtain the original high-precision map data; it extracts the difference information between the original high-precision map data and the verified key change information; and based on the difference information, it uses the established compression algorithm to generate incremental map update packages. The update packages contain core fields such as event identifiers, precise coordinates, validity period, and feature data blocks, and the generation time is ≤300ms.

[0054] The difference information includes: difference feature data, difference coordinate range, and difference event type. The core fields include: event identifier, coordinate range, and feature data block.

[0055] The V2X broadcast module can dynamically adjust the broadcast coverage based on the event impact range in the difference information, and send map incremental update packages to each vehicle terminal to ensure that each current vehicle in the area receives the information quickly.

[0056] In this embodiment, through the V2X broadcast module, road condition information for long-tail scenarios such as temporary construction and accident scenes is quickly disseminated to all vehicles in the area. Vehicle terminals such as assisted driving systems can predict risks in advance and adjust driving strategies (such as slowing down in advance and intelligent detours), improving the accident avoidance rate in long-tail scenarios by ≥80% and significantly enhancing the safety of assisted driving. It does not rely on a large number of dedicated data collection vehicles, but utilizes the distributed perception resources of massive vehicles to achieve map updates, reducing the deployment and maintenance costs of data collection vehicles by ≥70%. At the same time, the incremental update package distribution mode reduces network bandwidth usage by ≥60%, significantly reducing the operating costs of the cloud and vehicle.

[0057] In some embodiments of another aspect of the present invention Figure 2 This is an optional flowchart of the high-precision map collaborative control method provided in the embodiments of this application. Figure 2 The method may include, but is not limited to, steps S100 to S400.

[0058] In step S100, the vehicle-mounted terminal acquires the current vehicle operation data, processes the operation data, outputs raw sensing data, and transmits the raw sensing data using the vehicle-mounted optical communication module.

[0059] In step S200, the vehicle-mounted terminal converts the raw perception data into key change information, encapsulates the key change information, and encrypts and uploads the key change information using the V2X wide area communication module.

[0060] In step S300, the high-precision map cloud decrypts and verifies the key change information uploaded by each current vehicle, generates a map incremental update package based on the key change information, and broadcasts the map incremental update package to each current vehicle in the area using the V2X wide area communication module based on the key change information.

[0061] In step S400, the vehicle-mounted terminal receives the corresponding map incremental update package and distributes the map incremental update package to each vehicle-mounted terminal using the vehicle-mounted optical communication module, so that each vehicle-mounted terminal can parse and apply the map incremental update package, adjust the driving strategy, and update and display the latest driving conditions.

[0062] Steps S100 to S400 as illustrated in this embodiment utilize the network technology characteristics of the vehicle-mounted optical communication module to achieve lossless and low-latency transmission of raw sensing data, providing stable data support for the rapid fusion processing of the vehicle-mounted main control module and improving data processing efficiency. Through deep collaboration between the vehicle-mounted optical communication module and the V2X wide-area communication module, the entire link of data acquisition, in-vehicle data conversion, cloud processing, incremental distribution, and vehicle terminal application is connected, enabling real-time sharing of road condition information among multiple vehicles within the area and breaking the limitations of single-vehicle perception. The vehicle terminal can adjust its driving strategy according to the map incremental update package, update and display the latest road conditions, and achieve early risk prediction, improving the accident avoidance rate. It does not rely on a large number of dedicated data collection vehicles, but utilizes the distributed sensing resources of massive vehicles to achieve map updates, reducing the deployment and maintenance costs of data collection vehicles. At the same time, the distribution mode of incremental update packages reduces network bandwidth consumption, significantly reducing the operating costs of the cloud and the vehicle. Through end-to-end optimization, high-precision map updates and distribution are achieved in real time, solving the pain point of long update cycles in existing technologies, achieving minute-level updates, and improving the safety and reliability of assisted driving.

[0063] In some embodiments of S100, the vehicle-mounted terminal includes: a data acquisition module, a vehicle-mounted optical communication module, a vehicle-mounted main control module, and various vehicle-mounted terminals within the current vehicle.

[0064] The vehicle-mounted terminal acquires the current vehicle's operating data through a data acquisition module, performs collaborative output processing on the operating data, and outputs raw perception data. This operating data includes: 3D point cloud data of the road, road surface images and marking information, and precise positioning of the perception data; these three elements are collaboratively output as raw perception data.

[0065] The vehicle-mounted unit utilizes an onboard optical communication module to transmit raw sensing data to the onboard main control module, achieving lossless and low-latency transmission of raw sensing data to the central computing unit. The onboard optical communication module includes a V-PON optical unit.

[0066] In some embodiments of S200, the vehicle-mounted terminal converts the transmitted raw perception data into key change information through the vehicle-mounted main control module, encapsulates the key change information, and uses the V2X wide area communication module to encrypt and upload the key change information of the current vehicle to the high-precision map cloud.

[0067] Specifically, the vehicle-mounted main control module runs the set multi-sensor fusion algorithm to perform data denoising and feature extraction on the raw sensing data, generate key change information, and use the set data encapsulation protocol to encapsulate the key change information in a standardized format.

[0068] For example, a multi-sensor fusion algorithm is run to process point cloud data based on Kalman filtering, and an image registration algorithm is performed to complete data denoising, feature extraction, and generation of key change information, which is then standardized and encapsulated in Protobuf format. Key change information includes: event type (e.g., construction site fencing); precise positioning (latitude and longitude ±0.5m); and feature data (keyframe images of compressed point cloud segments).

[0069] In some embodiments of S300, the high-precision map cloud decrypts and verifies key change information uploaded by each current vehicle within the area. Based on this key change information, an incremental map update package is generated, and the broadcast distribution range is adjusted. Then, through the V2X wide-area communication module, the incremental map update package is distributed to each current vehicle within the area.

[0070] Specifically, the key change information uploaded by each current vehicle is decrypted, and the set multi-source data cross-validation algorithm is run to verify the key change information. That is, the consistency of data uploaded by multiple vehicles at the same location is compared to determine the valid data. Combined with historical map data, misidentified information is eliminated to obtain the key change information that has passed the verification.

[0071] Specifically, when the data similarity is greater than or equal to a set threshold, the key change information uploaded by the current vehicle is considered valid data. The established map database stores raw high-precision map data and historical incremental update records, supporting rapid querying and comparison. Historical map data can be obtained by accessing the established map database. False identification information can be caused by sensor malfunctions resulting in misinformation.

[0072] Based on the verified key change information, an incremental map update package is generated by comparing it with the original high-precision map data. Specifically, the original high-precision map data is obtained by calling the established map database using the verified key change information; the difference information between the original high-precision map data and the verified key change information is extracted; and based on the difference information, the established compression algorithm is used to generate the incremental map update package. The update package contains core fields such as event identifier, precise coordinates, validity period, and feature data blocks, and the generation time is ≤300ms.

[0073] The difference information includes: difference feature data, difference coordinate range, and difference event type. The core fields include: event identifier, coordinate range, and feature data block.

[0074] Based on the scope of event impact in the difference information, the broadcast coverage is dynamically adjusted, and corresponding map incremental update packages are broadcast to each vehicle terminal to ensure that all current vehicles in the area receive the updates quickly.

[0075] For example, a multi-source data cross-validation algorithm is run to compare the similarity of data uploaded by multiple vehicles at the same location. When the data similarity is ≥95%, the key change information uploaded by the current vehicle is deemed valid. Combined with historical map data, false data caused by sensor malfunctions is eliminated. The data verification accuracy is ≥99%, and the verification time is ≤200ms. Based on the verified key change information, the original high-precision map data is compared to extract the difference feature data, difference coordinate range, and difference event type. The LZ4 compression algorithm is used to generate a map incremental update package with a compression ratio ≥10:1. The map incremental update package includes core fields such as event identifier, precise coordinates, validity period, and feature data blocks, with a generation time ≤300ms. Based on the difference coordinate range and difference event type, a construction area radius of 1km is determined. Based on the construction area radius, the broadcast coverage is dynamically adjusted, and the map incremental update package is distributed at a frequency of 10Hz to ensure that all current vehicles in the area receive it quickly.

[0076] In some embodiments of S400, the vehicle-mounted terminal receives the corresponding map incremental update package through the vehicle-mounted main control module and distributes the map incremental update package to each vehicle-mounted terminal using the vehicle-mounted optical communication module.

[0077] Each vehicle terminal parses the update package, updates the local map, applies the map incremental update package, integrates it into the decision planning algorithm, adjusts the driving strategy, and the cockpit navigation domain controller displays the latest driving conditions in real time with a response time of ≤50ms.

[0078] In some embodiments of another aspect of the present invention, the conversion process of key change information in S200 includes: S210 utilizes the established multi-sensor fusion algorithm to perform data denoising and feature extraction on the raw sensing data, generating key change information.

[0079] S220 utilizes the established data encapsulation protocol to standardize and encapsulate key change information in a standardized format. In this embodiment, the vehicle main control module runs the set multi-sensor fusion algorithm to perform data denoising and feature extraction on the original sensing data, generate key change information, and use the set data encapsulation protocol to encapsulate the key change information in a standardized format.

[0080] For example, a multi-sensor fusion algorithm is run to process point cloud data based on Kalman filtering, and an image registration algorithm is performed to complete data denoising, feature extraction, and generation of key change information, which is then standardized and encapsulated in Protobuf format. Key change information includes: event type (e.g., construction site fencing); precise positioning (latitude and longitude ±0.5m); and feature data (keyframe images of compressed point cloud segments).

[0081] In some embodiments of another aspect of the present invention, in S300, the process of generating the map incremental update package includes: S310: Decrypt the key change information, identify the current vehicles at the same location within the area, and use the established multi-source data cross-validation algorithm to compare the consistency of key change information uploaded by multiple current vehicles at the same location to determine the valid key change information.

[0082] S320 calls the set map database to obtain historical map data. Based on the historical map data, it removes misidentified information from the valid key change information to obtain the verified key change information.

[0083] S330, based on the verified key change information, calls the set map database to obtain the original high-precision map data.

[0084] S340 compares the original high-precision map data with the verified key change information to extract difference feature data, difference coordinate range, and difference event type.

[0085] S350, based on the difference feature data, difference coordinate range, and difference event type, uses the set compression algorithm to generate map incremental update packages, and updates the event identifier, coordinate range, and feature data blocks in the core fields of the map incremental update packages accordingly.

[0086] In some embodiments of S310, the data verification module in the high-precision map cloud decrypts the key change information uploaded by each current vehicle, runs the set multi-source data cross-validation algorithm, compares the consistency of data uploaded by multiple vehicles at the same location, obtains the data similarity between the current vehicles, and when the data similarity is greater than or equal to the set threshold, the key change information uploaded by the current vehicle is considered to be valid data, that is, it is determined to be valid key change information.

[0087] In some embodiments of S320, the established map database stores raw high-precision map data and historical incremental update records, supporting rapid querying and comparison. The established map database is queried to obtain historical map data. Based on the historical map data, false data is identified and treated as misidentified information, removed from the key change information to obtain the verified key change information.

[0088] In some embodiments of S330, the original high-precision map data is obtained by querying the established map database through verification of key change information.

[0089] In some embodiments of S340, difference information is extracted between the original high-precision map data and the verified key change information. This difference information includes: difference feature data, difference coordinate range, and difference event type.

[0090] In some embodiments of S350, based on the difference information, a set compression algorithm is used to generate a map incremental update package. The update package contains core fields such as event identifier, precise coordinates, validity period, and feature data blocks, and the generation time is ≤300ms.

[0091] The core fields include: event identifier, coordinate range, and feature data block.

[0092] Based on the scope of event impact in the difference information, the broadcast coverage is dynamically adjusted, and corresponding map incremental update packages are broadcast to each vehicle terminal to ensure that all current vehicles in the area receive the updates quickly.

[0093] For example, a multi-source data cross-validation algorithm is run to compare the similarity of data uploaded by multiple vehicles at the same location. When the data similarity is ≥95%, the key change information uploaded by the current vehicle is deemed valid. Combined with historical map data, false data caused by sensor malfunctions is eliminated. The data verification accuracy is ≥99%, and the verification time is ≤200ms. Based on the verified key change information, the original high-precision map data is compared to extract the difference feature data, difference coordinate range, and difference event type. The LZ4 compression algorithm is used to generate a map incremental update package with a compression ratio ≥10:1. The map incremental update package includes core fields such as event identifier, precise coordinates, validity period, and feature data blocks, with a generation time ≤300ms. Based on the difference coordinate range and difference event type, a construction area radius of 1km is determined. Based on the construction area radius, the broadcast coverage is dynamically adjusted, and the map incremental update package is distributed at a frequency of 10Hz to ensure that all current vehicles in the area receive it quickly.

[0094] In this application, reference is made to Figure 3 The above steps are divided into the data collection and in-vehicle aggregation stage, the external upload and cloud processing stage, and the reverse distribution and terminal application stage according to the time sequence.

[0095] For example, during the data acquisition and in-vehicle convergence phase: 0ms: The on-board data acquisition module starts acquisition, the lidar unit outputs point cloud data, the image acquisition unit outputs image data, and the GNSS unit outputs positioning data; 1ms: The on-board optical communication module uses the V-PON network to transmit the raw sensing data losslessly to the on-board main control module; 101ms: The on-board main control module runs a multi-sensor fusion algorithm, using a Kalman filter-based point cloud and image registration algorithm to complete data denoising, feature extraction, and generate key change information, which is then standardized and encapsulated in Protobuf format. The key change information includes: event type (e.g., construction site fencing); precise positioning (latitude and longitude ±0.5m); and feature data (compressed point cloud fragments and keyframe images).

[0096] During the vehicle-to-vehicle and cloud-based processing phase: 151ms: The V2X wide-area communication module uploads standardized, encapsulated key change information to the high-precision map cloud, with an upload latency of ≤50ms; 351ms: The data verification module in the high-precision map cloud receives data uploaded from multiple vehicles, initiates a cross-validation algorithm, removes abnormal data, outputs valid information, and obtains the verified key change information; 651ms: Based on the verified key change information, the update package generation module in the high-precision map cloud compares it with the original high-precision map data to generate an incremental map update package, with a compressed data size of ≤10MB.

[0097] During the reverse distribution and terminal application phase, at 651ms: the V2X broadcast module in the high-precision map cloud broadcasts to all current vehicles in the area through the V2X wide area communication module, and correspondingly distributes map incremental update packages; at 701ms: the V2X vehicle communication unit in the V2X wide area communication module receives the corresponding map update package and transmits it to the V-PON network in the vehicle optical communication module; at 702ms: the V-PON network in the vehicle optical communication module distributes the update package to vehicle terminals such as the autonomous driving domain controller and the cockpit navigation system; at 752ms: each vehicle terminal parses the update package and applies it, the autonomous driving system adjusts its driving strategy, and the cockpit navigation updates and displays the latest driving conditions.

[0098] Another embodiment of this application provides a vehicle control device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned high-precision map collaborative control method based on V-PON and V2X. This vehicle control device can be any intelligent terminal, including tablet computers, in-vehicle computers, etc.

[0099] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0100] This invention also provides a vehicle, including the high-precision map collaborative control method based on V-PON and V2X described in the above embodiments.

[0101] The vehicle can be a private car, such as a sedan, SUV, MPV, or pickup truck. It can also be a commercial vehicle, such as a van, bus, small truck, or large semi-trailer. The vehicle must have an electric motor capable of outputting power or acting as a generator to store mechanical energy. When the vehicle is a new energy vehicle, it can be a hybrid or a pure electric vehicle.

[0102] Since the vehicle applies all the technical solutions of the above-described vehicle control device, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0103] Another embodiment of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described high-precision map collaborative control method based on V-PON and V2X.

[0104] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0105] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0106] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0107] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0108] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or a combination of certain steps, or different steps. Those skilled in the art will understand that all or some steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0109] Furthermore, the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion, such that a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or apparatus.

[0110] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0111] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0112] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A high-precision map collaborative control system based on V-PON and V2X, characterized in that, The system includes: Vehicle-mounted terminal; The data acquisition module is used to acquire the current vehicle's operating data and output raw perception data. The vehicle-mounted optical communication module is used to transmit the original sensing data and distribute the map incremental update package downloaded from the cloud of the high-precision map to each of the vehicle-mounted terminals. The vehicle-mounted main control module is connected to the data acquisition module and each of the vehicle-mounted terminals through the vehicle-mounted optical communication module. The vehicle-mounted main control module is used to convert the raw perception data into key change information, encapsulate the key change information, and receive the map incremental update package. The V2X wide area communication module is connected to the vehicle main control module. The V2X wide area communication module is used to encrypt and upload the key change information and receive the map incremental update package. The high-precision map cloud establishes a wireless connection with the V2X wide-area communication module. The high-precision map cloud is used to decrypt and verify the key change information uploaded by each current vehicle, and generate the map incremental update package based on the key change information.

2. The high-precision map collaborative control system according to claim 1, characterized in that, The vehicle-mounted optical communication module includes: A first optical communication link is connected to the data acquisition module and the vehicle main control module respectively, and the first optical communication link is used to transmit the raw sensing data. The second optical communication link is connected to each of the vehicle terminals and the vehicle main control module, and is used to distribute the map incremental update package to each of the vehicle terminals.

3. The high-precision map collaborative control system according to claim 1, characterized in that, The V2X wide area communication module includes: The V2X vehicle communication unit is connected to the vehicle main control module and wirelessly connected to the high-precision map cloud. A roadside communication unit, which is wirelessly connected to the V2X vehicle-mounted communication unit, is used to extend the communication range of the high-precision map cloud. A 5G communication unit is wirelessly connected to the high-precision map cloud and is also connected to the V2X vehicle-mounted communication unit and the roadside communication unit.

4. The high-precision map collaborative control system according to claim 3, characterized in that, The high-precision map cloud includes: A data verification module is wirelessly connected to the 5G communication unit. The data verification module is used to decrypt and verify the key change information according to the set map database to obtain the key change information that has passed the verification. An update package generation module is connected to the data verification module. The update package generation module is used to generate the map incremental update package based on the set map database and the verified key change information. The V2X broadcast module is connected to the update package generation module and wirelessly connected to the 5G communication unit. The V2X broadcast module is used to broadcast the map incremental update package to each of the vehicle terminals.

5. A high-precision map collaborative control method based on V-PON and V2X, characterized in that, The method includes: The vehicle-mounted terminal acquires the current vehicle's operating data, processes the operating data, outputs raw sensing data, and transmits the raw sensing data using the vehicle-mounted optical communication module. The vehicle-mounted terminal converts the raw sensing data into key change information, encapsulates the key change information, and encrypts and uploads the key change information using a V2X wide area communication module. The high-precision map cloud decrypts and verifies the key change information uploaded by each current vehicle, generates a map incremental update package based on the key change information, and broadcasts the map incremental update package to each current vehicle in the area based on the key change information using the V2X wide area communication module. The vehicle-mounted terminal receives the corresponding map incremental update package and distributes the map incremental update package to each vehicle-mounted terminal using the vehicle-mounted optical communication module, so that each vehicle-mounted terminal can parse and apply the map incremental update package, adjust the driving strategy, and update and display the latest driving conditions.

6. The high-precision map collaborative control method according to claim 5, characterized in that, The vehicle-mounted terminal converts the raw sensing data into key change information, including: Using the established multi-sensor fusion algorithm, the original sensing data is denoised and features are extracted to generate the key change information; The key change information is encapsulated in a standardized format using the established data encapsulation protocol.

7. The high-precision map collaborative control method according to claim 5, characterized in that, The high-precision map cloud decrypts and verifies the key change information uploaded by each current vehicle, including: The key change information is decrypted to determine the current vehicles at the same location within the area. The established multi-source data cross-validation algorithm is used to compare the consistency of the key change information uploaded by multiple current vehicles at the same location to determine the valid key change information. The system calls the established map database to obtain historical map data. Based on the historical map data, misidentified information is removed from the valid key change information to obtain the verified key change information.

8. The high-precision map collaborative control method according to claim 5, characterized in that, The step of generating the map incremental update package based on the key change information includes: Based on the verified key change information, the established map database is invoked to obtain the original high-precision map data; By comparing the original high-precision map data with the verified key change information, the difference feature data, difference coordinate range, and difference event type are extracted. Based on the difference feature data, the difference coordinate range, and the difference event type, the set compression algorithm is used to generate the map incremental update package, so as to update the event identifier, coordinate range, and feature data block in the core fields of the map incremental update package accordingly.

9. A vehicle control device, characterized in that, It includes a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the high-precision map collaborative control method according to any one of claims 5 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the high-precision map collaborative control method as described in any one of claims 5 to 8.

Images