Automatic driving data processing method based on vehicle and road cloud collaboration

Abstract

The invention discloses an automatic driving data processing method based on vehicle-road cloud collaboration, and the method specifically comprises the steps: generating driving data through a vehicle end after a vehicle starts automatic driving, and carrying out the structural arrangement of the driving data; in the automatic driving process, whether a road side unit exists or not is detected in real time, when it is determined that the road side unit exists, structured driving data are preprocessed preferentially through the road side unit and then uploaded to the cloud through a preset data interface module, and the cloud stores the structured driving data through a preset database. Real-time processing and offline analysis are carried out on the driving data based on a big data processing algorithm; and when the vehicle end requests operation from the database of the cloud end through the data interface module, automatic driving control and / or automatic driving function updating can be realized. According to the method, the accurate automatic driving decision is effectively ensured, in addition, the change requirement of the data structure can be flexibly met, the method is suitable for automatic driving function iteration, and the retrieval and processing efficiency is remarkably improved through the cloud database.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an autonomous driving data processing method based on vehicle-road-cloud collaboration. Background Art

[0002] In autonomous driving technology, the collection, transmission and storage of driving data are crucial. Specifically, the autonomous driving system needs to collect and process a large amount of data to realize intelligent driving functions, including vehicle configuration parameters, environmental perception data, map positioning data, path planning data, task execution data, historical report data and other important data. How to reasonably and efficiently upload and store a large amount of key data is a core issue for autonomous driving vehicles.

[0003] The current solutions proposed by the industry mainly involve establishing a vehicle-side database through the acquired file attribute fields, generating file configuration information based on the vehicle-side files and storing it in the vehicle-side database, extracting file aging scores from the vehicle-side database, and then determining whether to delete the vehicle-side files based on the file aging scores. By establishing a vehicle-side database and using the vehicle-side database to generate, query, and pull file attribute information and file aging scores of vehicle-side files, centralized management of vehicle-side files can be achieved.

[0004] However, after an in-depth analysis of the technical solution, it is found that there are at least the following problems:

[0005] 1. In the vehicle-side file system storage mode, there is a lack of effective protection mechanism for data integrity and consistency. Since data is stored in a scattered manner and there is no clear association mechanism, once data loss or inconsistency occurs in the decision-making module of the autonomous driving system, it may lead to system decision errors; in a real-time driving environment, incorrect path planning or obstacle avoidance decisions seriously affect driving safety and stability.

[0006] Second, when the system needs to change scenarios, upgrade programs, or expand functions, the local data storage method on the vehicle cannot flexibly respond to changes in data structure. Programmers may need to handle data migration and structural adjustments in a timely manner, increasing the complexity and risk of maintaining the autonomous driving system.

[0007] 3. When the local hardware on the vehicle stores a large amount of data, due to the scattered and disordered physical storage location of the data, long-term data retrieval and processing will reduce the system's response speed and performance, resulting in low data reading and query efficiency. Summary of the invention

[0008] In view of the above, the present invention aims to provide an autonomous driving data processing method based on vehicle-road-cloud collaboration to solve the technical problems mentioned above.

[0009] The technical solution adopted by the present invention is as follows:

[0010] The present invention provides an autonomous driving data processing method based on vehicle-road-cloud collaboration, which includes:

[0011] After the vehicle starts autonomous driving, driving data is generated by the vehicle end;

[0012] The vehicle side organizes the generated driving data in a structured manner;

[0013] During the autonomous driving process, the presence of a roadside unit is detected in real time; and when it is determined that a roadside unit exists, the structured driving data is pre-processed by the roadside unit first and then uploaded to the cloud via a preset data interface module;

[0014] The cloud stores structured driving data in a preset database and processes the driving data in real time and performs offline analysis based on big data processing algorithms;

[0015] The vehicle side requests operations from the database in the cloud through the data interface module to achieve autonomous driving control and / or autonomous driving function updates.

[0016] In at least one possible implementation manner, the structured organization includes: based on different types of driving data features and in accordance with a preset data structure, organizing each type of driving data into an independent structure.

[0017] In at least one possible implementation, when it is determined that a roadside unit exists, data enhancement and data filtering are performed on the sorted autonomous driving data; the processed driving data is compressed and encrypted, and transmitted to the cloud server through a secure communication channel preset by a data interface module.

[0018] In at least one possible implementation, the real-time detection of whether a roadside unit exists includes:

[0019] If no roadside unit is detected within the preset first driving distance or first detection duration, obtaining prediction information of whether there is a roadside unit within the second driving distance or second detection duration by any of the following methods: feedback from the detected roadside unit, feedback from other vehicles, feedback from the Internet of Vehicles platform, or feedback from the map;

[0020] If it is predicted that the roadside unit cannot be detected within the second driving distance or the second detection time, it is determined that there is no roadside unit.

[0021] In at least one possible implementation, the data processing method further includes: if it is determined that there is no roadside unit, the vehicle side compresses and encrypts the driving data locally, and then directly uploads it to the cloud server through an encrypted communication channel for processing and storage.

[0022] In at least one possible implementation manner, the cloud stores the structured driving data through a preset database, including: mapping the uploaded driving data structure to a corresponding data table pre-configured in the cloud database.

[0023] Compared with the prior art, the overall solution of the present invention has at least the following advantages:

[0024] Introducing database storage methods to ensure the structured storage of a large amount of key driving data, including map data, mission data, path planning data, decision control data, environmental perception data, and vehicle configuration parameters, etc., improves the manageability of data and the clarity of the overall structure, and effectively prevents data fragmentation and loss; for different types of autonomous driving data, design corresponding data structures and map them to different tables in the cloud database. In addition, through the association mechanism of primary key values, effective associations between map data, mission data, and decision data are achieved, thereby improving data consistency and traceability.

[0025] In addition, the system automatically initializes when it starts and automatically checks the matching of the data structure and the database table. If any inconsistency is found, the system automatically backs up the old table data, deletes the old table and creates a new table after the backup, ensuring the security and integrity of data migration, while avoiding data inconsistency problems caused by changes in application scenarios or program upgrades.

[0026] The present invention also provides an operation interface, which reduces the errors and inefficiencies that may be caused by manually writing instruction statements by automatically generating database statements corresponding to the data structure. The optimized interface layer design and automatic generation of instruction statements can improve the efficiency of data operations and simplify the maintenance and expansion process of the autonomous driving system.

[0027] Furthermore, through the mapping design between data structures and database table fields, the autonomous driving system can flexibly respond to changes in driving scenarios; by adjusting the format of the data structure, it can realize changes in table structure and backup and recovery of driving data, effectively responding to the impact of data changes that may be caused by program upgrades, and ensuring the stability of the autonomous driving system and the continuity of data. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described below with reference to the accompanying drawings, in which:

[0029] Figure 1 A schematic diagram of an autonomous driving data processing method based on vehicle-road-cloud collaboration provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0031] The present invention proposes an embodiment of an autonomous driving data processing method based on vehicle-road-cloud collaboration. Specifically, Figure 1 shown, including:

[0032] Step S1: After the vehicle starts automatic driving, the vehicle generates driving data;

[0033] During the startup and operation of an autonomous vehicle, a variety of key driving data will be generated, including but not limited to vehicle configuration parameters, mission data, environmental perception data, map data, path planning data, decision control data, etc. The above driving data can be generated in real time by different on-board sensors and control modules, and is mainly used to record the driving status and surrounding environment information of the autonomous vehicle.

[0034] Step S2: The vehicle end structures and organizes the generated driving data;

[0035] Specifically, the structure can be designed according to the data characteristics of each perception and control module, and the driving data can be organized according to a preset structure using an object-oriented design method: based on different types of driving data characteristics, each type of driving data can be organized into an independent structure according to a preset data structure, such as a map data structure, a task history report data structure, a diagnostic data structure, etc., to ensure efficient storage and rapid retrieval of driving data.

[0036] Here is a data structure design example for reference:

[0037] struct MapData {

[0038] int map_id;

[0039] std::string map_name;

[0040] std::string map_data;

[0041] };

[0042] Step S3: During the automatic driving process, whether there is a roadside unit is detected in real time; and when it is determined that there is a roadside unit, the structured driving data is pre-processed by the roadside unit first and then uploaded to the cloud via a preset data interface module;

[0043] When a roadside unit is present, the sorted driving data will be uploaded to the roadside unit first for preliminary processing and filtering, such as eliminating redundant and invalid data to enhance the quality and validity of the data, and the pre-processed data will be compressed and encrypted before being transmitted to the cloud server through a secure communication channel; in other embodiments, if the roadside unit is not detected, the vehicle side compresses and encrypts the driving data locally, and then directly uploads it to the cloud server through an encrypted communication channel for processing and storage.

[0044] Step S4: The cloud stores structured driving data in a preset database, and processes the driving data in real time and performs offline analysis based on a big data processing algorithm;

[0045] The cloud server receives, stores and analyzes the uploaded driving data. When storing, the key driving data structures of each module in the autonomous driving system can be mapped to the corresponding data tables pre-configured in the cloud database (such as but not limited to vehicle parameter configuration data tables, environmental perception data tables, path planning data tables, target detection data tables, diagnostic data tables, interaction data tables, positioning data tables, map data tables, decision control data tables, task data tables, etc.), and the file paths are also stored in the database, thereby ensuring the efficiency and flexibility of driving data management. Database technology is used to ensure reliable storage and efficient query of data, and based on the big data processing framework and the computing power of the cloud, the autonomous driving data is processed in real time and analyzed offline, which can provide support for the decision-making of the autonomous driving system and support the dynamic optimization and intelligent improvement of the autonomous driving function.

[0046] Step S5: The vehicle requests an operation from the cloud database through the data interface module to achieve autonomous driving control and / or function update.

[0047] The autonomous driving system module generates and executes database instruction statements by calling the interface of the corresponding interface module. That is, the interface module is responsible for converting high-level operation requests into specific database operations and returning execution results, thereby enabling the autonomous driving system to read data. The interface layer design follows the design specifications to ensure the universality and scalability of the interface; and through structured storage and associated query of different types of data, the system can better integrate multi-source data and improve data utilization efficiency and decision-making accuracy.

[0048] In summary, the security and efficiency of data storage embodied in the solution of the present invention ensures the high reliability of driving data during uploading, storage and transmission, and improves the efficiency of data storage and access; moreover, the large amount of data generated by driving is counted, classified and effectively divided, so as to realize efficient storage and fast reading of vehicle driving data, and ensure the stability and performance of the system under large data volume and high concurrency; in addition, after the system is upgraded or the program is changed, the changes in data structure are effectively managed and processed to ensure the continuous availability and consistency of data, and greatly reduce the impact of data changes caused by program changes and upgrades.

[0049] If the expressions expressing orientation are mentioned in the embodiments of the present invention, they are relative concepts based on the embodiments. In addition, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b, c can be single or multiple.

[0050] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings, but the above is only a preferred embodiment of the present invention. It should be noted that the technical features involved in the above embodiments and their preferred methods can be reasonably combined and matched into a variety of equivalent schemes by those skilled in the art without departing from or changing the design ideas and technical effects of the present invention; therefore, the present invention is not limited to the scope of implementation shown in the drawings, and all changes made in accordance with the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the specification and drawings, should be within the protection scope of the present invention.

Claims

1. A method for processing autonomous driving data based on vehicle-road-cloud collaboration, characterized in that: include: After the vehicle starts autonomous driving, driving data is generated by the vehicle end; The vehicle side organizes the generated driving data in a structured manner; During the autonomous driving process, the presence of a roadside unit is detected in real time; and when it is determined that a roadside unit exists, the structured driving data is pre-processed by the roadside unit first and then uploaded to the cloud via a preset data interface module; The cloud stores structured driving data in a preset database and processes the driving data in real time and performs offline analysis based on big data processing algorithms; The vehicle side requests operations from the database in the cloud through the data interface module to achieve autonomous driving control and / or autonomous driving function updates.

2. The method for processing autonomous driving data based on vehicle-road-cloud collaboration according to claim 1, characterized in that: The structured arrangement includes: arranging each type of driving data into an independent structure based on different types of driving data features and according to a preset data structure.

3. The method for processing autonomous driving data based on vehicle-road-cloud collaboration according to claim 1, characterized in that: When it is determined that there is a roadside unit, the sorted autonomous driving data is enhanced and filtered; the processed driving data is compressed and encrypted, and transmitted to the cloud server through the secure communication channel preset by the data interface module.

4. The method for processing autonomous driving data based on vehicle-road-cloud collaboration according to claim 1, characterized in that: The real-time detection of whether there is a roadside unit includes: If no roadside unit is detected within the preset first driving distance or first detection duration, obtaining prediction information of whether there is a roadside unit within the second driving distance or second detection duration by any of the following methods: feedback from the detected roadside unit, feedback from other vehicles, feedback from the Internet of Vehicles platform, or feedback from the map; If it is predicted that the roadside unit cannot be detected within the second driving distance or the second detection time, it is determined that there is no roadside unit.

5. The method for processing autonomous driving data based on vehicle-road-cloud collaboration according to claim 4, characterized in that: The data processing method also includes: if it is determined that there is no roadside unit, the vehicle end compresses and encrypts the driving data locally, and then directly uploads it to the cloud server through an encrypted communication channel for processing and storage.

6. The method for processing autonomous driving data based on vehicle-road-cloud collaboration according to any one of claims 1 to 5, characterized in that: The cloud stores the structured driving data through a preset database, including: mapping the uploaded driving data structure to a corresponding data table pre-configured in the cloud database.

Images