Data processing method, device and vehicle

Abstract

The present disclosure relates to a data processing method, device, and vehicle, and relates to the field of intelligent driving technology. The method comprises: receiving vehicle perception data provided by multiple data channels; extracting data to be processed from the vehicle perception data; wherein the data to be processed includes at least first data and second data, the first data and the second data corresponding to the same type of vehicle perception information; the first data and the second data corresponding to different data channels; and deduplicating the data to be processed based on the priority order of the multiple data channels to obtain target data. The present disclosure can streamline perception data, reduce resource consumption of the C‑V2X system for subsequent processing of vehicle perception data, and also facilitate the generation of subsequent intelligent driving decision-making judgments.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent driving technology, and in particular to a data processing method, device, and vehicle. Background Art

[0002] With the development of intelligent driving technology, vehicle perception of the external world has become increasingly important. Currently, smart cars are generally equipped with C-V2X systems. C-V2X (Cellular Vehicle-to-Everything) is a cellular network-based communication technology that enables information exchange between vehicles (V2V), vehicles (V2I), vehicles (V2P), and vehicles (V2N). C-V2X technology is a key component of intelligent transportation systems (ITS) and autonomous driving technologies, improving road safety, optimizing traffic flow, and supporting various value-added services.

[0003] The C-V2X system has multiple communication interfaces to receive various sensory data, enabling comprehensive information exchange between the vehicle and the outside world. However, in related technologies, the C-V2X system receives various sensory data but does not process it. This results in a large amount of data, requiring significant resources and hindering the subsequent intelligent driving decision-making.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to ordinary technicians in the field. Summary of the Invention

[0005] The present disclosure provides a data processing method, device, electronic device and storage medium.

[0006] According to a first aspect of an embodiment of the present disclosure, there is provided a data processing method, including:

[0007] Receive vehicle perception data provided by multiple data channels;

[0008] Extracting data to be processed from the vehicle perception data; wherein the data to be processed includes at least first data and second data, the first data and the second data correspond to the same type of vehicle perception information; and the first data and the second data correspond to different data channels;

[0009] Based on the priority order of the multiple data channels, deduplication processing is performed on the data to be processed to obtain target data.

[0010] In some embodiments, extracting the data to be processed from the vehicle perception data includes:

[0011] extracting event data from the vehicle perception data;

[0012] determining the first data and the second data in the event data to obtain the data to be processed;

[0013] The event data types corresponding to the first data and the second data are the same.

[0014] In some embodiments, the event data includes at least: object size data and object absolute position coordinate data;

[0015] A difference between the object size data in the first data and the object size data in the second data is within a preset range;

[0016] Furthermore, a difference between the absolute position coordinate data of the object in the first data and the absolute position coordinate data of the object in the second data is within a second preset range.

[0017] In some embodiments, deduplication processing is performed on the data to be processed based on the priority order of the multiple data channels to obtain target data, including:

[0018] Determining at least two data channels corresponding to the data to be processed;

[0019] Determining a target data channel with the highest priority among the at least two data channels based on the priority order of the multiple data channels;

[0020] The data corresponding to the target data channel in the data to be processed is retained to obtain the target data.

[0021] In some embodiments, the data processing method provided further includes: determining a priority order of the plurality of data channels;

[0022] Determining the priority order of the multiple data channels includes:

[0023] determining a preset priority order of the plurality of data channels;

[0024] Determining a credibility ranking of each of the at least two data channels based on a confidence identifier in the data to be processed;

[0025] Based on the credibility ranking, the preset priority order is adjusted to obtain the priority order of the multiple data channels.

[0026] In some embodiments, the provided data processing method further includes: preprocessing the vehicle perception data to obtain processed vehicle perception data;

[0027] Extracting the data to be processed from the vehicle perception data includes:

[0028] The data to be processed is extracted from the processed vehicle perception data.

[0029] In some embodiments, preprocessing the vehicle perception data includes:

[0030] For the vehicle perception data provided by each data channel, determining repeated perception data based on object identification and object position information in the vehicle perception data;

[0031] Based on the duplicate perception data, deduplication processing is performed on the vehicle perception data.

[0032] In some embodiments, the plurality of data channels include at least: an ego-vehicle perception channel;

[0033] In response to the data channel corresponding to the target data not being the vehicle perception channel, the target data is sent to the intelligent driving domain perception source.

[0034] In some embodiments, the plurality of data channels include:

[0035] Cloud perception channel, vehicle perception channel, other vehicle perception channel and roadside unit perception channel.

[0036] In some embodiments, the priority order of the plurality of data channels is preset;

[0037] The priority order of the multiple data channels includes: the priority of the self-vehicle perception channel is higher than the priority of the other vehicle perception channels; the priority of the other vehicle perception channels is higher than the roadside unit perception channel; the priority of the roadside unit perception channel is higher than the cloud perception channel.

[0038] According to a second aspect of an embodiment of the present disclosure, there is provided a data processing apparatus, including:

[0039] A data receiving unit, configured to receive vehicle sensing data provided by multiple data channels;

[0040] a data extraction unit, configured to extract data to be processed from the vehicle perception data; wherein the data to be processed includes at least first data and second data, the first data and the second data corresponding to the same vehicle perception information type; and the first data and the second data corresponding to different data channels;

[0041] The deduplication processing unit is used to perform deduplication processing on the data to be processed based on the priority order of the multiple data channels to obtain target data.

[0042] According to a third aspect of an embodiment of the present disclosure, there is provided a vehicle, comprising:

[0043] processor;

[0044] a memory for storing processor-executable instructions;

[0045] Wherein, the processor is configured to: implement the data processing method described in the first aspect above.

[0046] According to a fourth aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided, which, when instructions in the storage medium are executed by a processor of a mobile terminal, enables the mobile terminal to execute the data processing method described in the first aspect above.

[0047] The technical solutions provided by the embodiments of the present disclosure may have the following beneficial effects:

[0048] The system receives vehicle perception data from multiple data channels, extracts data to be processed from the vehicle perception data, and ensures that the data to be processed includes at least first data and second data, wherein the first data and the second data correspond to the same type of vehicle perception information and correspond to different data channels; and performs deduplication processing on the data to be processed based on the priority order of the multiple data channels to obtain target data. This system processes the vehicle perception data provided by multiple data channels received by the C-V2X system, simplifies the perception data through deduplication, reduces the resource consumption of the C-V2X system in subsequent processing of the vehicle perception data, and facilitates the generation of subsequent intelligent driving decisions.

[0049] The general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0051] Figure 1 This is a flow chart of a data processing method according to some embodiments of the present disclosure. Figure 1 .

[0052] Figure 2 is a flowchart of an implementation process of step S104 according to some embodiments of the present disclosure.

[0053] Figure 3is a flowchart of an implementation process of step S106 according to some embodiments of the present disclosure.

[0054] Figure 4 The present invention is a flowchart illustrating an implementation process of determining the priority order of multiple data channels according to some embodiments of the present disclosure.

[0055] Figure 5 This is a flow chart of a data processing method according to some embodiments of the present disclosure. Figure 2 .

[0056] Figure 6 It is a schematic diagram of the working data flow of a vehicle functional system according to a specific example shown in some embodiments of the present disclosure.

[0057] Figure 7 It is a block diagram of a data processing device according to some embodiments of the present disclosure.

[0058] Figure 8 It is a schematic functional block diagram of a vehicle according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0059] Some embodiments of the present disclosure will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. Various changes, modifications and equivalents of the methods, devices and / or systems described herein will become apparent after understanding the present disclosure. For example, the order of operations described herein is merely an example and is not limited to those orders set forth herein, but may be changed as becomes apparent after understanding the present disclosure, except for operations that must be performed in a specific order. In addition, for the sake of clarity and brevity, descriptions of features known in the art may be omitted.

[0060] The embodiments described in the following examples of the present disclosure do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0061] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0062] Figure 1 This is a flow chart of a data processing method according to some embodiments of the present disclosure. Figure 1 ,like Figure 1 As shown, the data processing method can be applied to electronic devices, including but not limited to vehicles.

[0063] Figure 1The data processing method shown includes the following steps.

[0064] In step S102 , vehicle perception data provided by multiple data channels is received.

[0065] It should be noted that multiple data channels are data source channels that are in communication with the C-V2X system in the vehicle. The C-V2X system is configured with corresponding communication interfaces to receive vehicle perception data provided by these data channels. Vehicle perception data refers to information about the vehicle's surroundings, vehicle status, and driving behavior collected by each data channel through sensors and other devices and information received from other data sources. This data is crucial for enabling autonomous driving, assisted driving, and improving driving safety and traffic efficiency. It can include vehicle status data, vehicle location information, driving behavior data, environmental perception data, and weather information.

[0066] In an exemplary embodiment of the present disclosure, multiple data channels may include: a cloud perception channel, a self-vehicle perception channel, other vehicle perception channels, and a roadside unit perception channel. It should be noted that the cloud perception channel refers to the data channel through which the cloud or other servers provide perception data to the vehicle, also known as the Uu SDK (Software Development Kit) perception channel. The vehicle can achieve perception of surrounding environment information through the software development kit provided by the Uu interface of the C-V2X system. The self-vehicle perception channel refers to the data channel through which the vehicle itself provides perception data to the vehicle through sensing and other technical means, also known as the HV (Highly Automated Vehicle) self-perception channel. The vehicle can access the intelligent driving domain self-perception capability module through the C-V2X system to receive vehicle perception data collected by its own vehicle. The intelligent driving domain self-perception capability module uses a variety of sensors and technical means such as cameras, radars, and laser radars (LiDAR) to collect and process the perception data of the surrounding environment in real time to generate a comprehensive understanding of the vehicle's surrounding environment. Other vehicle perception channels refer to data channels through which other vehicles provide perception data to the vehicle, also known as the V2V (Vehicle-to-Vehicle) PC5 perception channel. A vehicle can establish communication connections with other vehicles via the PC5 interface of the C-V2X system to obtain information collected by other vehicles and thus perceive its surrounding environment. A roadside unit perception channel refers to a data channel through which a roadside unit (RSU) provides perception data to the vehicle, also known as the RSU PC5 perception channel. A vehicle can establish communication connections with an RSU via the PC5 interface of the C-V2X system to obtain information collected by the RSU and thus perceive its surrounding environment. Those skilled in the art will appreciate that the multiple data channels in the embodiments of the present disclosure can include at least two of any of the four channels described above, or can include other data channels that provide vehicle perception data, such as the V2P (Vehicle-to-Pedestrian) PC5 perception channel. A vehicle can establish communication connections with pedestrian devices, such as smartphones, via the PC5 interface of the C-V2X system to obtain vehicle perception data such as location information. This is not a limitation in the embodiments of the present disclosure.

[0067] In step S104, data to be processed is extracted from the vehicle perception data.

[0068] It should be noted that the data to be processed includes at least first data and second data, and the first data and the second data correspond to different data channels and the first data and the second data correspond to the same type of vehicle perception information. The first data and the second data are vehicle perception data provided by different data channels, but the type of vehicle perception information described is the same, for example, it can be vehicle location, traffic light information, obstacle information, driving behavior, vehicle travel information, weather information, etc. In other words, the data to be processed can be repeated data with the same data description provided by different data channels. For example, it can include vehicle location information provided by the vehicle perception channel, vehicle location information provided by other vehicle perception channels, and vehicle location information provided by the cloud perception channel.

[0069] In an exemplary embodiment of the present disclosure, the data to be processed may include first data, second data, and third data, and the vehicle perception information types corresponding to the first data, second data, and third data are the same, and the data channels corresponding to the first data, second data, and third data are different. The data to be processed may include first data, second data, third data, and fourth data, and the vehicle perception information types corresponding to the first data, second data, third data, and fourth data are the same, and the data channels corresponding to the first data, second data, third data, and fourth data are different. It will be understood by those skilled in the art that the data to be processed may include first data, second data, ..., Nth data, and the vehicle perception information types corresponding to the first data, second data, ..., Nth data are the same, and the corresponding data channels are different, and N is less than or equal to the number of multiple data channels.

[0070] In step S106 , based on the priority order of the multiple data channels, the data to be processed is deduplicated to obtain target data.

[0071] It should be noted that the priority order of multiple data channels represents the order in which data channels are retained. Data with higher priority is retained first. Based on the priority order of multiple data channels, the data with the highest priority corresponding to the channel is retained and the remaining data is deleted to deduplicate the data to be processed and obtain the target data.

[0072] As can be seen from the above steps, the data processing method provided by the embodiment of the present disclosure receives vehicle perception data provided by multiple data channels; extracts the data to be processed from the vehicle perception data, so that the data to be processed includes at least first data and second data, the first data and the second data correspond to the same type of vehicle perception information and the first data and the second data correspond to different data channels; deduplication is performed on the data to be processed based on the priority order of the multiple data channels to obtain target data. The method realizes the processing of vehicle perception data provided by multiple data channels received by the C-V2X system, and through deduplication, the perception data is streamlined. The C-V2X system subsequently only needs to process the streamlined target data, reducing the resource consumption of the C-V2X system for subsequent processing of vehicle perception data; at the same time, subsequent intelligent driving decision-making judgments only need to analyze the target data, which does not require repeated analysis multiple times and avoids complex decision-making judgments caused by inconsistent analysis results due to inconsistent vehicle perception data provided by different data channels, thereby facilitating the generation of subsequent intelligent driving decision-making judgments.

[0073] like Figure 2 As shown, it is a flowchart of the implementation process of step S104 provided in some exemplary embodiments of the present disclosure, including the following steps.

[0074] In step S202 , event data is extracted from the vehicle perception data.

[0075] In step S204, first data and second data are determined in the event data to obtain data to be processed.

[0076] It should be noted that the event data types corresponding to the first data and the second data are the same. Event data represents data related to events that occur during vehicle driving. The event data type can be a collision event, an obstacle detection event, a signal light event, a lane departure event, a fault event, a pedestrian detection event, etc. Those skilled in the art will understand that the data to be processed may include the first data, the second data, ..., the Nth data, and the first data, the second data, ..., the Nth data have the same event data type and different corresponding data channels, and N is less than or equal to the number of multiple data channels.

[0077] In some exemplary embodiments of the present disclosure, event data includes at least object size data and object absolute position coordinate data. Different types of event data may include object size data, such as obstacle size data, pedestrian size data, and own vehicle size data, and may include object absolute position coordinate data, such as obstacle absolute position coordinate data, pedestrian absolute position coordinate data, and own vehicle absolute position coordinate data. Specifically, the difference between the object size data in the first data and the object size data in the second data is within a first preset range, and the difference between the object absolute position coordinate data in the first data and the object absolute position coordinate data in the second data is within a second preset range. Those skilled in the art will appreciate that the data to be processed may include the first data, the second data, ..., and the Nth data, and the difference between the object size data in any two data is within the first preset range, and the difference between the object absolute position coordinate data in any two data is within a second preset range. In other words, by determining that the object sizes in the event data provided by different data channels are the same or the difference in object sizes is within an error range, and determining that the object absolute position coordinates in the event data provided by different data channels are the same or the difference in absolute position coordinates is within an error range, it can be determined that the event data provided by different data channels describe the same event and require reprocessing.

[0078] It can be understood by those skilled in the art that the first preset range and the second preset range are pre-set and are a smaller error range. The first preset range can be the same as or different from the second preset range and can be set according to actual conditions. The embodiments of the present disclosure are not limited here.

[0079] In some exemplary embodiments of the present disclosure, event data may also include object color information, object type, etc. When extracting data to be processed, the data may be filtered by first determining whether the object color information and object type in the event data provided by different data channels are consistent, so as to screen out data that may describe the same event. It should be noted that the color information describes the color of the object in the event, such as the color of the preceding vehicle, the color of the roadblock, etc. The object type describes the type of object in the event, such as whether the preceding vehicle is a car or a truck, whether the object next to it is a motor vehicle or a pedestrian, etc. The obviously inconsistent data is filtered out in advance through basic information such as object color information and object type, and then the data to be processed is determined through object size data and object absolute position coordinate data, so as to reduce the amount of calculation during data extraction, save computing resources, and improve the efficiency of data extraction.

[0080] like Figure 3 As shown, it is a flowchart of the implementation process of step S106 provided in some exemplary embodiments of the present disclosure, including the following steps.

[0081] In step S302, at least two data channels corresponding to the data to be processed are determined.

[0082] In step S304 , based on the priority order of the multiple data channels, a target data channel with the highest priority among the at least two data channels is determined.

[0083] In step S306, the data corresponding to the target data channel in the data to be processed is retained to obtain the target data.

[0084] It should be noted that the at least two data channels corresponding to the data to be processed are part or all of the multiple data channels. Based on the priority order of the multiple data channels, a target data channel with the highest priority among the at least two data channels can be determined. The data corresponding to the target data channel in the data to be processed, that is, one of the first data, the second data, ..., the Nth data, is retained, and the other data is deleted to obtain the target data. Based on the priority order of the multiple data channels, the data corresponding to the data channel with the highest priority in the data to be processed is retained, and the data corresponding to the remaining data channels is deleted to achieve data deduplication. This reduces the repeated processing of this part of the data by the subsequent C-V2X system, and avoids problems such as inconsistent decision analysis in the subsequent processing process caused by inconsistencies in certain content of the data provided by multiple data channels.

[0085] Accordingly, in an exemplary embodiment of the present disclosure, the provided data processing method further includes: determining the priority order of multiple data channels. In some exemplary embodiments of the present disclosure, the priority order of multiple data channels is pre-set, and the setting order takes into account the data credibility and data timeliness of each data channel, and the data channels with high credibility and / or strong timeliness are sorted first. In an embodiment where the multiple data channels include a cloud perception channel, a self-vehicle perception channel, other vehicle perception channels, and a roadside unit perception channel, the priority order of the multiple data channels includes: the priority of the self-vehicle perception channel is higher than that of other vehicle perception channels; the priority of other vehicle perception channels is higher than that of the roadside unit perception channel; and the priority of the roadside unit perception channel is higher than that of the cloud perception channel.

[0086] In some other exemplary embodiments of the present disclosure, the priority order of multiple data channels can be preset and then dynamically adjusted. Figure 4 As shown, it is a flowchart of an implementation process of determining the priority order of multiple data channels provided by some exemplary embodiments of the present disclosure, including the following steps.

[0087] In step S402 , a preset priority order of multiple data channels is determined.

[0088] In step S404, the credibility ranking of each data channel in the at least two data channels is determined based on the confidence identifier in the data to be processed.

[0089] In step S406, based on the credibility ranking, the preset priority order is adjusted to obtain the priority order of the multiple data channels.

[0090] It should be noted that the preset priority order of multiple data channels is pre-set. You can refer to the examples provided in the above embodiments, consider the data credibility and data timeliness of each data channel, and sort the data channels with high credibility and / or strong timeliness first.

[0091] It should be noted that the confidence identifier in the data to be processed is provided together with the vehicle perception data in the form of a confidence identifier after each data channel determines whether the data is credible and evaluates the credibility when providing vehicle perception data. In some embodiments of the present disclosure, the confidence identifiers provided by different data channels, and the pre-set credibility judgment rules, can determine the credibility ranking of each data channel in at least two data channels. The credibility judgment rules are pre-set and describe the confidence identifier comparison rules corresponding to different data channels. For example, the confidence levels represented by the confidence identifiers corresponding to different data channels can be directly compared. The larger the value, the higher the credibility. It can also be that when the confidence level represented by the confidence identifier corresponding to the vehicle perception channel is lower than 50%, the credibility can be ranked lowest. The setting of specific rules needs to be determined according to actual conditions, and the embodiments of the present disclosure are not limited here.

[0092] In an exemplary embodiment of the present disclosure, based on the credibility ranking, the preset priority order is adjusted to obtain the priority order of multiple data channels. Specifically, channels with higher credibility rankings also have higher priorities, while rankings not described in the credibility ranking still refer to the preset priority order. For example, the preset priority order is: the priority of the vehicle's perception channel is higher than that of other vehicle perception channels; the priority of other vehicle perception channels is higher than that of the roadside unit perception channel; and the priority of the roadside unit perception channel is higher than that of the cloud perception channel. If the credibility ranking is such that the roadside unit perception channel is ranked before other vehicle perception channels, the adjusted priority order of the multiple data channels is: the priority of the vehicle's perception channel is higher than that of the roadside unit perception channel; the priority of the roadside unit perception channel is higher than that of other vehicle perception channels; and the priority of other vehicle perception channels is higher than that of the cloud perception channel. By dynamically adjusting the priority order of multiple data channels based on the confidence identifier uploaded with the data, it is ensured that even if the data of certain data channels is unreliable, it will not be retained due to its higher priority order, thereby ensuring the credibility of the target data after deduplication.

[0093] Figure 5This is a flow chart of a data processing method according to some embodiments of the present disclosure. Figure 2 , Figure 5 In the data processing method shown in FIG. Figure 1 Steps S102 and S106 in the data processing method shown correspond to each other and are not repeated here.

[0094] In some embodiments of the present disclosure, Figure 1 Based on the data processing method shown, Figure 5 The data processing method shown may further include the following steps.

[0095] In step S504, the vehicle perception data is preprocessed to obtain processed vehicle perception data.

[0096] In step S506 , the data to be processed is extracted from the processed vehicle perception data.

[0097] It should be noted that the preprocessing of vehicle perception data can be data cleaning, such as removing error data, or data integration, data format alignment, protocol conversion, etc.

[0098] In some exemplary embodiments of the present disclosure, the implementation of step S504 may include: determining duplicate perception data based on object identification and object location information in the vehicle perception data provided by each data channel; and performing deduplication processing on the vehicle perception data based on the duplicate perception data. It should be noted that vehicle perception data is real-time and may report the same event at different times, that is, duplicate perception. Duplicate perception data is not worthy of attention for the C-V2X system. Deduplication processing can be used to retain the data of the first perception, thereby reducing the computing resource consumption caused by multiple processing of duplicate data and improving data processing efficiency.

[0099] In some exemplary embodiments of the present disclosure, the vehicle perception data provided by each data channel is compared with the vehicle perception data at the previous reporting time, and based on the object identification (ID) and object location information, it is determined whether it is duplicate perception data. If the object identification and object location information are the same as those at the previous reporting time, it is determined to be duplicate perception data and can be directly deleted. For example, the roadside unit perception channel provides vehicle perception data every 2 seconds, and there is a vehicle parked on the roadside. While the vehicle is stationary, the relevant data for the vehicle in the vehicle perception data provided by the roadside unit perception channel every 2 seconds is the same. Except for the data reported for the first time, the relevant data for the vehicle in the subsequently provided vehicle perception data can be determined to be duplicate perception data and can be deleted. Until the vehicle starts to move, the object location information changes, and it will no longer be determined as duplicate perception data, and enter the subsequent processing flow.

[0100] In some exemplary embodiments of the present disclosure, after obtaining target data, it is sent to the V2X system application layer to provide specific application scenarios and service functions, directly serving end users or applications and providing user prompts through the HMI (Human-Machine Interface). The application layer can support various types of services, such as traffic safety, traffic efficiency improvement, and information services.

[0101] It should be noted that the vehicle perception data provided by the self-vehicle perception channel is crucial for functions such as vehicle intelligent driving, and the data is highly timely and reliable. Therefore, multiple data channels include at least: a self-vehicle perception channel. Functions such as intelligent driving decision analysis in the vehicle can be determined based on the vehicle perception data provided by the self-vehicle perception channel, but there are also cases where the vehicle perception data provided by the self-vehicle perception channel is missing or unreliable. In order to ensure the accurate implementation of the intelligent driving function, in some embodiments of the present disclosure, in response to the data channel corresponding to the target data not being the self-vehicle perception channel, the target data is sent to the intelligent driving domain perception source to complete or correct the data source of the intelligent driving domain perception source.

[0102] It should be noted that the Intelligent Driving Domain refers to the part of the vehicle responsible for realizing autonomous driving functions and related intelligent assisted driving technologies. It is a complex system that integrates multiple subsystems such as perception, decision-making and execution, aiming to improve driving safety, comfort and efficiency. The Intelligent Driving Domain perception source is used to collect or receive corresponding perception data for the Intelligent Driving Domain. It can collect data on the vehicle's surrounding environment through sensors including cameras, radar (RADAR), laser radar (LiDAR), ultrasonic sensors, etc. The precise position and posture of the vehicle can be determined through positioning systems such as GPS and inertial measurement units (IMU). Detailed geographic information can be provided through map data to help vehicles understand complex road environments.

[0103] In order to better illustrate the data processing method provided by the embodiment of the present disclosure, a specific example is now provided for further explanation. Figure 6 , which is a partial data flow diagram of a vehicle functional system constructed by applying the data processing method provided by the embodiment of the present disclosure in this specific example.

[0104] like Figure 6 As shown, the vehicle is equipped with an intelligent driving domain system, a V2X system, and a cockpit domain display system.

[0105] The V2X system includes a data access and protocol stack layer and an application layer. The data access and protocol stack layer includes an arbitration and deduplication layer. This layer accesses data transmitted by various communication interfaces and performs other processing, such as data format conversion, according to the corresponding protocols. The arbitration and deduplication layer performs the data processing described in the embodiments of this disclosure on the accessed data.

[0106] Specifically, vehicle-cloud integrated data is connected to the V2X system via the UU SDK interface, external data is connected to the V2X system via the RSU PC5 interface and the V2V PC5 interface, and the data provided by the self-vehicle perception channel is transmitted to the V2X system by the self-perception capability unit of the intelligent driving domain. After the vehicle perception data provided by multiple data channels is connected to the V2X system, it is processed by the arbitration deduplication layer to obtain the target data and then transmitted to the application layer. When the data channel corresponding to the target data is not the self-vehicle perception channel, the target data is sent to the intelligent driving domain system via the application layer to supplement the data of the intelligent driving domain perception source. After the application layer processes the target data, it displays the service results to the user through the display system of the cockpit domain, such as the HMI time prompt and / or signal display.

[0107] By setting up an arbitration deduplication layer, duplicate event data from multiple data sources is deduplicated and reported to the V2X application layer and downstream data users. This prevents the V2X application layer from repeatedly processing the same event data due to data reported by multiple channels, reducing system load. This also avoids duplicate notifications caused by multiple channels inputting the same event data to the V2X application layer, which can lead to functional failure or poor performance.

[0108] It should be noted that the acquisition, storage, use, and processing of data in the disclosed technical solution are in compliance with the relevant provisions of national laws and regulations.

[0109] The following are embodiments of the apparatus disclosed herein, which can be used to implement the method embodiments disclosed herein. For details not disclosed in the apparatus embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0110] Figure 7 FIG1 is a block diagram of a data processing device according to some embodiments of the present disclosure. Figure 7 The device includes: a data receiving unit 701, a data extraction unit 702, and a deduplication processing unit 703.

[0111] A data receiving unit 701 is configured to receive vehicle sensing data provided by multiple data channels;

[0112] The data extraction unit 702 is configured to extract data to be processed from the vehicle perception data; wherein the data to be processed includes at least first data and second data, the first data and the second data corresponding to the same type of vehicle perception information; and the first data and the second data corresponding to different data channels;

[0113] The deduplication processing unit 703 is used to perform deduplication processing on the data to be processed based on the priority order of multiple data channels to obtain target data.

[0114] It should be noted that the multiple data channels include: cloud perception channel, ego vehicle perception channel, other vehicle perception channel, and roadside unit perception channel. The priority order of the multiple data channels is pre-set; the priority order of the multiple data channels is as follows: ego vehicle perception channel takes precedence over other vehicle perception channels; other vehicle perception channels take precedence over roadside unit perception channels; and roadside unit perception channels take precedence over cloud perception channels.

[0115] In some exemplary embodiments of the present disclosure, the data extraction unit 702 is configured to:

[0116] Extracting event data from vehicle perception data;

[0117] Determining first data and second data in the event data to obtain data to be processed;

[0118] The event data types corresponding to the first data and the second data are the same.

[0119] In some exemplary embodiments of the present disclosure, event data includes at least: object size data and object absolute position coordinate data; the difference between the object size data in the first data and the object size data in the second data is within a first preset range; and the difference between the object absolute position coordinate data in the first data and the object absolute position coordinate data in the second data is within a second preset range.

[0120] In some exemplary embodiments of the present disclosure, the deduplication processing unit 703 is configured to:

[0121] Determining at least two data channels corresponding to the data to be processed;

[0122] Determining a target data channel with the highest priority among the at least two data channels based on a priority order of the multiple data channels;

[0123] The data corresponding to the target data channel in the data to be processed is retained to obtain the target data.

[0124] In some exemplary embodiments of the present disclosure, the provided data processing apparatus further includes: an order determination unit, configured to determine a priority order of the plurality of data channels.

[0125] In some exemplary embodiments of the present disclosure, the sequence determination unit is configured to:

[0126] Determine a preset priority order for multiple data channels;

[0127] Determining a credibility ranking of each data channel in at least two data channels based on a confidence identifier in the data to be processed;

[0128] Based on the credibility ranking, the preset priority order is adjusted to obtain the priority order of multiple data channels.

[0129] In some exemplary embodiments of the present disclosure, the provided data processing device further includes: a preprocessing unit for preprocessing the vehicle perception data to obtain processed vehicle perception data. Accordingly, the data extraction unit 702 is used to extract the data to be processed from the processed vehicle perception data.

[0130] In some exemplary embodiments of the present disclosure, the pre-processing unit is configured to:

[0131] For the vehicle perception data provided by each data channel, determining duplicate perception data based on object identification and object location information in the vehicle perception data;

[0132] Based on duplicate perception data, vehicle perception data is deduplicated.

[0133] In some exemplary embodiments of the present disclosure, the multiple data channels include at least a self-vehicle perception channel. The provided data processing device further includes a data sending unit configured to send the target data to the intelligent driving domain perception source in response to the data channel corresponding to the target data not being the self-vehicle perception channel.

[0134] Figure 8 FIG1 is a block diagram illustrating a vehicle 800 according to an exemplary embodiment. For example, vehicle 800 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or another type of vehicle. Vehicle 800 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0135] Reference Figure 8 Vehicle 800 may include various subsystems, such as an infotainment system 810, a perception system 820, a decision-making and control system 830, a drive system 840, and a computing platform 850. Vehicle 800 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of vehicle 800 may be interconnected via wired or wireless means.

[0136] In some embodiments, the infotainment system 810 may include a communication system, an entertainment system, a navigation system, and the like.

[0137] The perception system 820 may include several sensors for sensing information about the environment surrounding the vehicle 800. For example, the perception system 820 may include a global positioning system (which may be a GPS system, a BeiDou system, or another positioning system), an inertial measurement unit (IMU), a laser radar, a millimeter-wave radar, an ultrasonic radar, and a camera.

[0138] The decision control system 830 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0139] The drive system 840 may include components that provide power to the vehicle 800. In one embodiment, the drive system 840 may include an engine, a power source, a transmission system, and wheels. The engine may be an internal combustion engine, an electric motor, an air compression engine, or a combination thereof. The engine is capable of converting energy provided by the power source into mechanical energy.

[0140] Some or all functions of the vehicle 800 are controlled by a computing platform 850. The computing platform 850 may include at least one processor 851 and a memory 852. The processor 851 may execute instructions 853 stored in the memory 852.

[0141] The processor 851 can be any conventional processor, such as a commercially available CPU. The processor can also include a graphics processing unit (GPU), a field programmable gate array (FPGA), a system on chip (SOC), an application specific integrated circuit (ASIC), or a combination thereof.

[0142] The memory 852 may be implemented by any type of volatile or nonvolatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0143] In addition to instructions 853 , memory 852 may also store data, such as road maps, route information, and vehicle location, direction, speed, etc. The data stored in memory 852 may be used by computing platform 850 .

[0144] In the embodiment of the present disclosure, the processor 851 may execute the instruction 853 to complete all or part of the steps of the above-mentioned data processing method.

[0145] In some embodiments of the present disclosure, a non-transitory computer-readable storage medium enables the mobile terminal to perform the above-mentioned data processing method when instructions in the storage medium are executed by a processor of the mobile terminal.

[0146] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0147] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A data processing method, characterized in that: The data processing method is applied to a C-V2X system in a vehicle, comprising: Receiving vehicle perception data provided by multiple data channels; wherein the vehicle perception data represents information collected by each data channel about the vehicle's surrounding environment, vehicle status, and driving behavior; Extracting data to be processed from the vehicle perception data; wherein the data to be processed includes at least first data and second data, the first data and the second data correspond to the same type of vehicle perception information; and the first data and the second data correspond to different data channels; Based on the priority order of the multiple data channels, deduplication processing is performed on the data to be processed to obtain target data; Among them, in response to the multiple data channels including: the vehicle perception channel, other vehicle perception channels, and roadside unit perception channels, the vehicle perception channel has a higher priority than the other vehicle perception channels, and the other vehicle perception channels have a higher priority than the roadside unit perception channel.

2. The data processing method according to claim 1, wherein: Extracting data to be processed from the vehicle perception data includes: extracting event data from the vehicle perception data; determining the first data and the second data in the event data to obtain the data to be processed; The event data types corresponding to the first data and the second data are the same.

3. The data processing method according to claim 2, characterized in that: The event data includes at least: object size data and object absolute position coordinate data; A difference between the object size data in the first data and the object size data in the second data is within a preset range; Furthermore, a difference between the absolute position coordinate data of the object in the first data and the absolute position coordinate data of the object in the second data is within a second preset range.

4. The data processing method according to claim 1, wherein: Deduplication processing is performed on the data to be processed based on the priority order of the multiple data channels to obtain target data, including: Determining at least two data channels corresponding to the data to be processed; Determining a target data channel with the highest priority among the at least two data channels based on the priority order of the multiple data channels; The data corresponding to the target data channel in the data to be processed is retained to obtain the target data.

5. The data processing method according to claim 4, characterized in that: Also includes: Determining a priority order of the multiple data channels; Determining the priority order of the multiple data channels includes: determining a preset priority order of the plurality of data channels; Determining a credibility ranking of each of the at least two data channels based on a confidence identifier in the data to be processed; Based on the credibility ranking, the preset priority order is adjusted to obtain the priority order of the multiple data channels.

6. The data processing method according to claim 1, wherein: Also includes: Preprocessing the vehicle perception data to obtain processed vehicle perception data; Extracting the data to be processed from the vehicle perception data includes: The data to be processed is extracted from the processed vehicle perception data.

7. The data processing method according to claim 6, characterized in that: Preprocessing the vehicle perception data includes: For the vehicle perception data provided by each data channel, determining repeated perception data based on object identification and object position information in the vehicle perception data; Based on the duplicate perception data, deduplication processing is performed on the vehicle perception data.

8. The data processing method according to claim 1, wherein: The multiple data channels include at least: a self-vehicle perception channel; In response to the data channel corresponding to the target data not being the vehicle perception channel, the target data is sent to the intelligent driving domain perception source.

9. The data processing method according to claim 1, wherein: The multiple data channels include: Cloud perception channel, vehicle perception channel, other vehicle perception channel and roadside unit perception channel.

10. The data processing method according to claim 9, characterized in that: The priority order of the multiple data channels is preset; The priority order of the multiple data channels includes: the priority of the self-vehicle perception channel is higher than the priority of the other vehicle perception channels; the priority of the other vehicle perception channels is higher than the roadside unit perception channel; the priority of the roadside unit perception channel is higher than the cloud perception channel.

11. A data processing device, characterized in that: The data processing device is applied to a C-V2X system in a vehicle, including: A data receiving unit, configured to receive vehicle perception data provided by multiple data channels; wherein the vehicle perception data represents information collected by each data channel about the vehicle's surrounding environment, vehicle status, and driving behavior; a data extraction unit, configured to extract data to be processed from the vehicle perception data; wherein the data to be processed includes at least first data and second data, the first data and the second data corresponding to the same vehicle perception information type; and the first data and the second data corresponding to different data channels; a deduplication processing unit, configured to perform deduplication processing on the data to be processed based on the priority order of the multiple data channels to obtain target data; Among them, in response to the multiple data channels including: the vehicle perception channel, other vehicle perception channels, and roadside unit perception channels, the vehicle perception channel has a higher priority than the other vehicle perception channels, and the other vehicle perception channels have a higher priority than the roadside unit perception channel.

12. A vehicle, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: Implement a data processing method according to any one of claims 1 to 10.

13. A non-transitory computer-readable storage medium, which, when instructions in the storage medium are executed by a processor of a mobile terminal, enables the mobile terminal to execute a data processing method according to any one of claims 1 to 10.

Images