Data processing methods, devices, and autonomous vehicles for autonomous vehicles

Abstract

This disclosure provides a data processing method, apparatus, and autonomous vehicle for autonomous vehicles, relating to the field of data processing technology, particularly artificial intelligence, autonomous driving, intelligent transportation, and big data. The specific implementation scheme involves: determining the target functions of the autonomous vehicle that require incremental updates; the target function being any control function in the set of autonomous driving control functions that needs updating; acquiring upgrade data for updating the target function; and incrementally updating the target function based on the upgrade data of the target function, building upon the current version of the autonomous driving system. In this embodiment, it does not rely on system version updates, can acquire relevant data for upgrading the target function in real time, and can upgrade the target function individually, achieving incremental updates at the function level and avoiding the waste of processing resources caused by full data updates.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to the fields of artificial intelligence, autonomous driving, intelligent transportation, and big data. Background Technology

[0002] Autonomous vehicles are equipped with autonomous driving systems, which include key autonomous driving control functions such as perception, recognition, and prediction. As autonomous driving control technology iterates and updates, these related functions are updated accordingly.

[0003] The current update strategy involves updating these functions as the autonomous driving system is updated. However, the long update cycle of autonomous driving systems results in low efficiency in updating autonomous driving control functions. Summary of the Invention

[0004] This disclosure provides a data processing method, apparatus, and autonomous vehicle for autonomous vehicles.

[0005] According to one aspect of this disclosure, a data processing method for an autonomous vehicle is provided, applied to an autonomous vehicle, comprising:

[0006] Identify the target functions that require incremental updates for autonomous vehicles; the target functions are any control functions in the set of autonomous driving control functions that need to be updated.

[0007] Obtain upgrade data used to update the target functionality;

[0008] Based on the upgrade data of the target function, the target function is incrementally updated on the basis of the current version of the autonomous driving system.

[0009] According to another aspect of this disclosure, a data processing method for autonomous vehicles is provided, applied in the cloud, comprising:

[0010] In response to the incremental update operation of the target function, the upgrade data of the target function is obtained; the target function is any control function in the set of autonomous driving control functions that needs to be updated.

[0011] When an upgrade to a target function is required, the upgrade data for the target function is sent to the autonomous vehicle so that the autonomous vehicle can incrementally update the target function based on the current version of the autonomous driving system.

[0012] According to another aspect of this disclosure, a data processing apparatus for an autonomous vehicle is provided, applied to the autonomous vehicle, comprising:

[0013] The first determining module is used to determine the target function that needs to be incrementally updated for the autonomous vehicle; the target function is any control function in the set of autonomous driving control functions that needs to be updated.

[0014] The first acquisition module is used to acquire upgrade data for updating the target function;

[0015] The update module is used to incrementally update the target functions based on the upgrade data of the target functions, on the basis of the current version of the autonomous driving system.

[0016] According to another aspect of this disclosure, a data processing apparatus for an autonomous vehicle, applied in the cloud, is provided, comprising:

[0017] The response module is used to respond to incremental update operations on the target function and obtain the upgrade data for the target function; the target function is any control function in the set of autonomous driving control functions that needs to be updated.

[0018] The first sending module is used to send upgrade data of the target function to the autonomous vehicle when an upgrade of the target function is required, so that the autonomous vehicle can incrementally update the target function based on the current version of the autonomous driving system.

[0019] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0020] At least one processor; and

[0021] The memory is communicatively connected to the at least one processor; wherein,

[0022] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any of the methods described in the present disclosure.

[0023] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform any of the methods according to embodiments of this disclosure.

[0024] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the methods according to embodiments of this disclosure.

[0025] According to another aspect of this disclosure, an autonomous vehicle is provided, including an electronic device for implementing a communication method implemented on the vehicle's in-vehicle terminal.

[0026] In this embodiment of the disclosure, after determining the target functions that need to be upgraded in the autonomous vehicle, relevant data for upgrading the target functions can be obtained in real time, avoiding the problem of long update cycles caused by only being able to upgrade the autonomous driving system version. Furthermore, it allows for individual upgrades of the target functions, achieving incremental updates at the functional granularity and avoiding the waste of processing resources caused by full data updates.

[0027] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0028] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0029] Figure 1 This is a schematic diagram illustrating an application scenario of a data processing method for autonomous vehicles according to an embodiment of this disclosure;

[0030] Figure 2 This is a flowchart illustrating a data processing method for an autonomous vehicle according to another embodiment of the present disclosure;

[0031] Figure 3 This is a flowchart illustrating the process of determining the target functions that need to be upgraded in an autonomous vehicle according to another embodiment of this disclosure;

[0032] Figure 4 This is a flowchart illustrating the process of determining the target function of an autonomous vehicle according to another embodiment of this disclosure;

[0033] Figure 5 This is a flowchart illustrating a data processing method for an autonomous vehicle according to another embodiment of the present disclosure;

[0034] Figure 6 This is a flowchart illustrating a data processing method for an autonomous vehicle according to another embodiment of the present disclosure;

[0035] Figure 7 This is a schematic diagram of the interaction process between an autonomous vehicle and the cloud according to another embodiment of this disclosure;

[0036] Figure 8 This is a schematic diagram of the interaction process between an autonomous vehicle and the cloud according to another embodiment of this disclosure;

[0037] Figure 9 This is a schematic diagram of the structure of a data processing device for an autonomous vehicle according to another embodiment of the present disclosure;

[0038] Figure 10This is a schematic diagram of the structure of a data processing device for an autonomous vehicle according to another embodiment of the present disclosure;

[0039] Figure 11 This is a block diagram of an electronic device used to implement the data processing method for an autonomous vehicle according to embodiments of the present disclosure. Detailed Implementation

[0040] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0041] Because the autonomous driving control functions need to be updated with each version of the autonomous driving system, the update cycle is long and it is difficult to meet the requirements. Therefore, this disclosure provides a data processing method for autonomous vehicles.

[0042] like Figure 1 The diagram illustrates an application scenario for this method, including an autonomous vehicle 11 and a cloud platform 12. The cloud platform 12 may include multiple servers, some of which manage the autonomous driving control functions of the autonomous vehicle 11, while others are used to remotely control the autonomous vehicle.

[0043] To improve the efficiency of updating autonomous driving control functions, such as Figure 2 The diagram shown is a flowchart of a data processing method for an autonomous vehicle according to an embodiment of this disclosure. This method is applied to an autonomous vehicle and includes:

[0044] S201, Identify the target function that needs incremental updates for the autonomous vehicle; the target function is any one of the control functions in the set of autonomous driving control functions that needs to be updated.

[0045] Among them, the autonomous driving control functions may include, for example, AEB (Autonomous Emergency Braking), ACC (Adaptive Cruise Control), LKA (LaneKeeping Assist), ELK (Emergency Lane Keeping), TSR (Traffic Sign Recognition System), automatic horn sounding, etc.

[0046] Among these features, AEB (Autonomous Emergency Braking) is an active safety technology that prevents collisions or minimizes the damage caused by one. ACC (Adaptive Cruise Control) uses sensors at the front of the vehicle to continuously detect intersections ahead and actively controls the vehicle to slow down when necessary. LKA (Lane Keeping Assist) assists the driver in keeping the vehicle within its lane. ELK (Electronic Lane Keeping Assist) detects vehicles in front and behind and maintains lane keeping. TSR (Traffic Speed ​​Recognition) uses a front-facing camera to detect road signs (such as speed limits and no-overtaking zones) and displays the information. Automatic horn use determines when it is necessary to sound the horn based on obstacles ahead.

[0047] The above-described control functions for autonomous driving are used to construct an autonomous driving control function set. Upgrading the autonomous driving control functions may involve upgrading one or more control functions. Since the upgrade operation for each control function is the same, this disclosure uses one control function as an example for illustration.

[0048] S202, Obtain upgrade data for updating the target function.

[0049] In this process, autonomous vehicles obtain upgrade data from the cloud for updating target functions.

[0050] S203, based on the upgrade data of the target function, incrementally updates the target function on the basis of the current version of the autonomous driving system.

[0051] In this embodiment of the disclosure, after determining the target functions that need to be upgraded in the autonomous vehicle, relevant data for upgrading the target functions can be obtained in real time, avoiding the problem of long update cycles caused by only being able to upgrade the autonomous driving system version. Furthermore, it allows for individual upgrades of the target functions, achieving incremental updates at the functional granularity and avoiding the waste of processing resources caused by full data updates.

[0052] In some embodiments, such as Figure 3 The diagram shown is a flowchart illustrating the process of determining the target functions that need to be upgraded in an autonomous vehicle according to an embodiment of this disclosure, including:

[0053] S301, requesting the cloud to send the test file.

[0054] In practice, a test file can be requested from the cloud if certain testing conditions are met. These conditions may include at least one of the following: the autonomous vehicle is powered on and started, or the testing cycle has been reached. That is, when the autonomous vehicle is powered on and started, it is necessary to check whether an update is needed. Alternatively, to ensure that updates generated during vehicle operation are promptly implemented in the autonomous vehicle, the autonomous vehicle can periodically check for updates.

[0055] If the detection conditions are met, the autonomous vehicle requests a unified detection document to be sent from the cloud.

[0056] S302, Obtain the first global description information of the set of autonomous driving control functions from the detection file.

[0057] The first global description information refers to the information on the set of autonomous driving control functions in the cloud version.

[0058] This first global description information is used to compare whether the set of autonomous driving control functions of autonomous vehicles is consistent with that in the cloud. If they are inconsistent, they need to be updated.

[0059] During implementation, the cloud can use MD5 (Message-Digest Algorithm) to generate the first global description information of the set of autonomous driving control functions. MD5 is a widely used cryptographic hash function that can produce a 128-bit (16-byte) hash value.

[0060] Similarly, in order to enable comparison, autonomous vehicles store a second global description of the local set of autonomous driving control functions.

[0061] S303, if the first global description information and the second global description information of the set of autonomous driving control functions stored in the autonomous vehicle do not match, determine the first local description information of the control function in the set of autonomous driving control functions.

[0062] In some embodiments, the first global description information is obtained by sequentially concatenating the second local description information, and the second local description information can be extracted from the first global description information.

[0063] In some embodiments, the second global description information and the first global description information are compared to determine whether they match. If they match, it indicates that the cloud has not updated the autonomous driving control function set; if they do not match, it indicates that the cloud has updated the autonomous driving control function set. To achieve incremental updates at the control function granularity, when the second and first global description information do not match, the first partial description information of each control function in the autonomous driving control function set is obtained from the detection file. Therefore, the first partial description information of each control function can be controlled and accessed independently, which is beneficial for maintaining information for different control functions.

[0064] Since the various control functions within the autonomous driving control function set are independent of each other, it is convenient to obtain the first partial description information of each control function from the detection file. This first partial description information refers to the information generated by the cloud based on each independent control function to detect whether the function has been updated. In implementation, MD5 hashes of each control function can be generated. Based on the MD5 data of each control function, it can be identified whether each control function has been updated. This allows for the determination of the target functions that need to be updated, enabling incremental updates.

[0065] Specifically, in S304, if the first partial description information of the control function does not match the second partial description information of the control function stored in the autonomous vehicle, the control function is determined to be the target function.

[0066] The first partial description information of the control function can be understood as the version information in the cloud, while the second partial description information of the control function stored in the autonomous vehicle can be understood as the local version information of the autonomous vehicle. When it is determined that one or more control functions in the local version information of the autonomous vehicle are inconsistent with the version information in the cloud, it can be determined that the version information in the cloud has been updated. At this time, the local version information of the autonomous vehicle needs to be consistent with the version information in the cloud, so it is necessary to determine the control function to be updated as the target function.

[0067] In this embodiment of the disclosure, MD5 value is used as global or local description information. This not only allows MD5 to be used to verify the integrity of information, but also allows MD5 to be reused to detect whether the autonomous driving function needs to be updated.

[0068] In this embodiment, incremental updates of the target function are achieved by comparing the consistency of the description information of the same control function in the autonomous vehicle and the cloud. Specifically, the target function that requires an update can be accurately located through the description information, and only the upgrade data of the target function needs to be transmitted to achieve an independent update of the target function. Instead of updating all autonomous driving control functions, this saves local storage space in the autonomous vehicle and improves update efficiency.

[0069] In this embodiment, the cloud can send the same detection file to different vehicles, allowing the vehicles to detect which control functions need to be updated, thereby identifying the target functions that need incremental updates.

[0070] In addition, the target function can also be determined by the cloud in this embodiment of the disclosure. For example... Figure 4 The diagram shown is a flowchart illustrating the process of determining the target function of an autonomous vehicle in an embodiment of this disclosure, including:

[0071] S401, Obtain the second partial description information of each control function in the set of autonomous driving control functions.

[0072] The second partial description information is the same as that described above, that is, the second partial description information of each control function in the set of autonomous driving control functions is the local information stored by the autonomous vehicle.

[0073] Alternatively, if the testing conditions are met, S401 can be executed. The testing conditions have been explained above and will not be repeated here.

[0074] S402, the second partial description information of each control function is sent to the cloud so that the cloud can determine the target function based on the first partial description information of each control function stored in the cloud.

[0075] Among them, the cloud-based system compares the target function's operation with the second local description information. Figure 3 The comparison method is the same, so it will not be repeated here. After identifying the target functions that need incremental updates in the cloud, the autonomous vehicle can be notified.

[0076] In S403, autonomous vehicles receive the function identifier of the target function sent from the cloud.

[0077] In summary, after comparing the first and second global description information in the cloud, the autonomous vehicle also needs to obtain the comparison result, i.e., the target function. Therefore, at this time, the autonomous vehicle needs to receive the function identifier of the target function sent by the cloud. The function identifier corresponds one-to-one with the target function, and the target function can be determined through this identifier.

[0078] S404, the control function corresponding to the function identifier is identified as the target function.

[0079] This disclosure provides a method for detecting target functions that require incremental updates for autonomous vehicles in the cloud. When autonomous vehicles have limited processing resources, cloud resources can be utilized to determine the target functions. In this embodiment, the cloud can implement personalized updates for different autonomous vehicles. That is, if multiple autonomous vehicles require different target functions to be updated, the cloud only needs to issue the incremental update portion of the target function separately, avoiding excessive consumption of autonomous vehicle resources.

[0080] In some embodiments, upgrade data for the target function can be sent to the autonomous vehicle along with the detection file, facilitating the vehicle's update of the target function. Therefore, obtaining the upgrade data for updating the target function can be implemented as follows: obtaining the download path of the upgrade data for the target function from the detection file; and obtaining the upgrade data based on the download path. In this embodiment, the detection file is used by the autonomous vehicle to detect the target function requiring incremental updates, and the download path of the target function, which is located in the cloud, is obtained from the detection file. Then, based on this download path, the upgrade data for the target function is downloaded separately from the cloud, instead of downloading all the data to the autonomous vehicle, thus saving storage resources and shortening the upgrade time.

[0081] In this embodiment, the upgrade data is stored in the download path specified by the detection file, rather than directly in the detection file. This allows for determination of whether the control function needs to be updated based on the detection file. If an update is required, the upgrade data is retrieved as needed, avoiding excessive consumption of processing resources.

[0082] In other embodiments, the cloud can distribute all functional data to the autonomous vehicle, allowing the vehicle to obtain upgrade data locally for updates. This can be implemented as follows:

[0083] Step A1: While receiving the detection file sent from the cloud, also receive the upgrade data for the target function sent from the cloud.

[0084] It is understandable that the detection files distributed from the cloud contain the first global description information of the set of autonomous driving control functions. When the first global description information in the cloud changes, the cloud updates the set of autonomous driving control functions.

[0085] In some embodiments, the upgrade data can be in the form of a compressed file. The compressed file format is chosen because upgrade data is sensitive and cannot be sent in plaintext via the interface. Additionally, and primarily because autonomous vehicles have numerous functions, compression reduces the amount of data transmission.

[0086] In some embodiments, considering both security and ease of use, a gzip (GNUzip, a file compression program) archive may be used.

[0087] Step A2: Store the upgrade data in the download path specified in the detection file.

[0088] This download path is the same as the storage path in the autonomous vehicle.

[0089] Step A3: Obtain the download path from the detection file.

[0090] Step A4: Obtain the upgrade data from the download path.

[0091] In some embodiments, when using a detection file for incremental updates, the cloud can distribute upgrade data for each control function in the autonomous driving control function set to the autonomous vehicle. The autonomous vehicle identifies the parts that need incremental updates and obtains the download path of the upgrade data to be incrementally updated from the detection file, thereby completing the incremental update.

[0092] In some embodiments, regardless of whether the target function is determined by the autonomous vehicle or the cloud, in order to cope with the continuous improvement of autonomous driving control functions and the gradual increase in data volume, the upgrade data is all custom structure, which includes control data for various autonomous driving tasks.

[0093] In some embodiments of this disclosure, examples of custom structures may be shown below:

[0094] --online_config_version=167

[0095] --houston_online_enable_cross_solid_line_nudge=true

[0096] --houston_online_enable_three_point_turn=true

[0097] --perception_online_enable_receive_v2x_obstacle=true

[0098] --caros_online_enable_energon=true

[0099] Here, the parameters `caros`, `perception`, and `houston` are the names of different control functions in the autonomous driving control function set. The parameter `config_version = 167` indicates that the obtained control function parameter version is 167; the parameter `online` indicates that the environment parameter is used in an online environment. It's understood that the environment parameter may have multiple values, and `online` is just one of them. The parameter `enable energor = true` indicates the status of the corresponding control function, such as enabling (true) or disabling (false) the function. For example, the automatic horn function can be enabled or disabled. The parameter `receive_v2x_obstacle = true` indicates whether to use V2X technology to receive intelligent traffic-related signals; `true` means enabled, and `false` means disabled.

[0100] It should be noted that the parameters listed above are only a limited set. In practice, more parameters may exist, and a single parameter may be configured with multiple values. For example, since autonomous vehicles may perform different autonomous driving tasks, each parameter can be configured with a corresponding value for different autonomous driving tasks. For instance, autonomous vehicles may be deployed at tourist attractions to transport tourists. Before the autonomous vehicles are officially put into use, testing may be required; in this case, the autonomous driving task can be understood as road testing. After the testing is passed, the autonomous vehicles are put into use, and the autonomous driving task can be understood as the task to be performed after an order is dispatched to the autonomous vehicles. Of course, other autonomous driving tasks can be set according to actual needs, and this disclosure does not limit this.

[0101] In some embodiments, performing different autonomous driving tasks can be implemented as follows:

[0102] Step B1: If the first target task among multiple autonomous driving tasks is determined, the control data of the first target task is obtained.

[0103] Step B2: The control target function executes the first target task based on the control data of the first target task.

[0104] Step B3: If it is determined that the second target task among multiple autonomous driving tasks is to be switched, the control data of the second target task is obtained.

[0105] Step B4: The control target function executes the second target task based on the control data of the second target task.

[0106] In this embodiment, the control in steps B2 and B4 can be understood as sending corresponding information to the target function to assist it in completing the corresponding operation. Taking the automatic horn function as an example, during the control of an autonomous vehicle, before horn sounds, it is necessary to detect the surrounding conditions, such as whether the road allows horn use, and determine whether horn use is permissible based on the detection results. These detection results can be obtained by other functional modules besides the automatic horn function after detection, or by the automatic horn function analyzing the collected data to obtain the detection results. In either case, corresponding data will be input to the automatic horn function to achieve control over it.

[0107] In this embodiment, a custom structure is used to store upgrade data, which reduces the file size of the upgrade data and minimizes the file size. Furthermore, the custom structure data format is a data format recognized by both the autonomous vehicle and the cloud, facilitating reading of the same data file from different devices. By controlling the target function to obtain control data corresponding to the target task and sequentially executing the target tasks in various autonomous driving tasks, the data processing of the autonomous vehicle becomes efficient and controllable. For example, when the autonomous vehicle needs to frequently switch autonomous driving tasks, it can perform autonomous driving operations based on pre-stored control data for various autonomous driving tasks, which improves task execution efficiency compared to temporarily obtaining the corresponding data each time an autonomous driving task is switched.

[0108] In some embodiments, since the surrounding environment affects the operating state of the autonomous vehicle, the control data for each autonomous driving task includes control sub-data for at least one operating scenario. In implementation, appropriate control sub-data can be obtained based on different operating scenarios to execute the target function. This can be implemented by having the cloud analyze relevant data, determine the currently applicable operating scenario as the target scenario, and inform the autonomous vehicle, after which the autonomous vehicle performs the following operations:

[0109] Step C1: Receive the target scenario sent from the cloud.

[0110] The cloud can send scene identifiers for the target scene so that autonomous vehicles can confirm the operating scene they are using.

[0111] In some embodiments, such as Figure 1 As described herein, the cloud provides two platforms: one platform manages the set of autonomous driving control functions and is responsible for updating related control functions; the other is a cloud control platform responsible for remotely controlling the autonomous vehicle. The target scenario can be determined by either platform, and this disclosure does not limit this.

[0112] In step C2, when the target scenario is confirmed, the autonomous driving strategy controls the target function to perform autonomous driving tasks based on the control sub-data of the target scenario.

[0113] In some embodiments, the target scenario may include at least one of key parameters, such as the driving area, weather conditions, road congestion, and time. For example, an autonomous vehicle operating in a science park might perform employee pick-up and drop-off duties between 10:00 AM and 11:00 AM on January 1st. During implementation, the cloud can use big data analysis to determine whether the roads in the science park are congested between 10:00 AM and 11:00 AM on January 1st, and further combine this with weather conditions to determine the corresponding operating scenario. For example, on rainy days when roads are slippery, the speed limit could be lower than on sunny days.

[0114] Therefore, control sub-data applicable to different operating scenarios can be recorded in the cloud, and the corresponding control sub-data can be used to complete autonomous driving tasks.

[0115] In this embodiment of the disclosure, the target function is controlled to perform corresponding autonomous driving tasks according to different target scenarios. Distinguishing the target scenarios helps to improve the control efficiency of autonomous vehicles in executing target functions.

[0116] In summary, autonomous vehicles can perform incremental updates at the functional granularity level and can better complete autonomous driving tasks according to different situations and needs.

[0117] Based on the same technical concept, embodiments of this disclosure also provide a data processing method for autonomous vehicles, which is applied in the cloud. For example... Figure 5 The diagram shown is a flowchart of the method, including:

[0118] S501, in response to the incremental update operation of the target function, obtains the upgrade data of the target function; the target function is any control function in the set of autonomous driving control functions that needs to be updated.

[0119] S502, when an upgrade to a target function is required, sends the upgrade data for the target function to the autonomous vehicle so that the autonomous vehicle can incrementally update the target function based on the current version of the autonomous driving system.

[0120] In this embodiment, when the cloud determines that a target function needs to be updated, it sends the upgrade data of the target function to the autonomous vehicle. This avoids the problem of having to resort to version updates of the autonomous driving system to solve the data update issue, thereby enabling the target function to be upgraded automatically and effectively in a timely manner, improving the efficiency of related data updates. Moreover, based on basic functional updates, incremental updates can be implemented, further improving update efficiency.

[0121] In some embodiments, before sending the upgrade data for the target function to the autonomous vehicle, the cloud can first authenticate the autonomous vehicle. In practice, a token (text vector) of the autonomous vehicle can be obtained and then compared with a token generated in the cloud for the same autonomous vehicle. If the comparison matches, authentication is successful. After successful authentication, the autonomous vehicle obtains the upgrade data. The autonomous vehicle can perform integrity verification on the upgrade data, for example, based on MD5. After successful verification, the autonomous vehicle completes the upgrade operation for the target function.

[0122] Accordingly, as described above, the use of detection files is crucial. To facilitate autonomous vehicles' self-identification of target functions requiring incremental updates, the cloud needs to generate and send detection files to the autonomous vehicles in a timely manner, such as... Figure 6 As shown, it includes:

[0123] S601, generate first local description information for each control function in the set of autonomous driving control functions, and generate first global description information for the set of autonomous driving control functions.

[0124] S602 generates a detection file based on the first local description information and the first global description information of each control function.

[0125] In this embodiment of the disclosure, the execution order of generating the first global description information and the first local description information in the cloud is not limited. That is, the first global description information can be generated first, and then the first local description information of each control function can be generated; the first local description information of each control function can be generated first, and then the first global description information can be generated; or the first global description information and the first local description information can be generated simultaneously.

[0126] S603, upon receiving a detection request from an autonomous vehicle for detecting functions requiring incremental updates, sends the detection file to the autonomous vehicle.

[0127] Similar to what was described earlier, autonomous vehicles send a request to the cloud when the detection conditions are met, so that the cloud can send the detection files to the autonomous vehicle.

[0128] In this embodiment of the disclosure, a detection file is generated in the cloud and sent to the autonomous vehicle upon request, so that the autonomous vehicle can determine the target functions that need incremental updates.

[0129] When autonomous vehicles need to determine the target function based on detection files, a request received by the cloud from an autonomous vehicle can be interpreted as the target function needing an upgrade.

[0130] In some embodiments, the cloud can determine which target function needs to be updated. Accordingly, determining that a target function needs an upgrade can be implemented as follows:

[0131] Step D1: Receive the second partial description information of each control function sent by the autonomous vehicle.

[0132] Step D2: Match the first local description information of each stored control function with the corresponding second local description information.

[0133] In some embodiments, the cloud may first compare the first global description information and the second global description information, and if the two do not match, then compare the first local description information and the second local description information.

[0134] Step D3: If the second partial description information and the first partial description information of the target function do not match, it is determined that the target function needs to be upgraded.

[0135] Similarly, if the second local description information of the target function is consistent with the first local description information, that is, it has not changed, then the target function does not need to be upgraded.

[0136] In this embodiment of the disclosure, by comparing whether the second local description information and the first local description information corresponding to the same control function in the autonomous vehicle and the cloud are consistent, the target function that needs to be incrementally updated can be determined, which can save the local storage space of the autonomous vehicle, avoid the waste of download resources, and improve the update efficiency of the target function.

[0137] In some embodiments, as described above, the upgrade data is a custom structure that includes control data for various autonomous driving tasks. The use of this control data has been explained previously and will not be repeated here.

[0138] In this embodiment of the disclosure, the upgrade data is stored using a custom structure, which can reduce the file size of the upgrade data and make the file size as small as possible, thereby saving storage space.

[0139] In some embodiments, as described above, the control data for each autonomous driving task includes control sub-data for at least one operating scenario, and further includes:

[0140] Step E1: Determine the target scenario where the autonomous vehicle is located.

[0141] For example, the cloud can obtain the driving area and tasks of autonomous vehicles, and determine the target scenario based on the task's execution time and driving path. Similar to the previous description, it can be determined that the autonomous vehicle picks up and drops off tourists from station A to station B within a scenic area. When the temperature inside the scenic area is high, the vehicle's air conditioning can be automatically turned on; when the temperature is low, the vehicle's heating can be turned on; in rainy weather, the maximum speed limit can be reduced; and when the roads within the scenic area are clear and there are few tourists, the maximum speed limit can be increased, and the departure interval can be adjusted. It is understood that different operating scenarios can be configured according to different application needs, and this disclosed embodiment does not limit this.

[0142] Step E2: Send the target scenario to the autonomous vehicle.

[0143] The relevant applications for the target scenario have been explained above and will not be repeated here.

[0144] In this embodiment of the disclosure, the cloud distinguishes different target scenarios, which helps to improve the service quality of autonomous vehicles.

[0145] In some embodiments, the cloud can maintain the autonomous driving capabilities required for each vehicle at the vehicle level, based on a vehicle version management platform. These vehicle capabilities are applicable to real vehicle, simulation, and other environments. For example:

[0146] Step F1: Construct the data corresponding to each control function of the autonomous vehicle to obtain the function tree of the autonomous vehicle.

[0147] This function tree can include control functions for autonomous vehicles, such as AEB automatic emergency braking, ACC adaptive cruise control, LKA lane keeping assist, and TSR traffic sign recognition. The parameters of each control function are associated with related functions.

[0148] Step F2: In response to the simulation request for the target function, obtain the data for the target function from the function tree.

[0149] In this context, a simulation request involves using code to retrieve data from the target platform in a manner permitted by the platform. Simply put, it involves using code to repeatedly retrieve data from other platforms for its own use. In this embodiment, the simulation request is specifically for retrieving data information about the target function from the function tree.

[0150] Step F3: Conduct simulation experiments on the target function based on the data of the target function.

[0151] In this simulation experiment, the equipment used in the conventional sense is not employed. Instead, simulation software is used on a computer to mimic real-world effects and experimental conditions. The simulation software connects theoretical conditions with the experimental process through a graphical interface, and utilizes programming to achieve the desired realistic simulation.

[0152] In this embodiment of the disclosure, the simulation experiments include, for example, vehicle dynamics simulation, environmental perception sensor simulation, and traffic scene simulation.

[0153] Specifically, vehicle dynamics simulation is based on a multibody dynamics model, which parametrically models multiple real components, including the vehicle body, steering, suspension, tires, brakes, and I / O hardware interfaces, to simulate the attitude and kinematics of the vehicle model during its motion. Environmental perception sensor simulation mainly includes modeling and simulating sensors such as cameras, LiDAR, millimeter-wave radar, and GPS / IMU. Traffic scene simulation includes two parts: static scene reconstruction and dynamic scene simulation.

[0154] This disclosure primarily focuses on the simulation of autonomous driving control functions. Before updating the autonomous vehicle, the update results can be verified through simulation, and the effect of the update can also be verified through simulation after updating the autonomous vehicle.

[0155] In this embodiment of the disclosure, simulation experiments on the target function are conducted based on the data of the target function, which avoids the drawback of long road testing cycles, is conducive to conducting relevant experiments on autonomous vehicles, and is beneficial to the technological development in the field of autonomous driving.

[0156] To facilitate understanding of the overall solution content of the embodiments of this disclosure, as follows: Figure 7 The diagram shown illustrates the interaction process between autonomous vehicles and the cloud. The following section will combine... Figure 7 Explanation:

[0157] S701 responds to upgrade operations for the target function in the cloud and obtains the upgrade data for the target function.

[0158] S702 updates the first global description information of the set of autonomous driving control functions in the cloud, and updates the first local description information of the target's capabilities.

[0159] S703: When the autonomous vehicle is activated, it requests the cloud to send a test file.

[0160] S704, in response to the autonomous vehicle's request, sends the detection files to the autonomous vehicle.

[0161] S705: Autonomous vehicles determine whether an upgrade to the autonomous driving function is needed based on the detection files sent from the cloud and the first global description information in the detection files.

[0162] S706, when it is determined that an autonomous vehicle needs to upgrade its autonomous driving functions, the target functions that need to be upgraded are identified.

[0163] S707, Autonomous vehicles acquire upgrade data for target functions.

[0164] S708, autonomous vehicles upgrade target functions based on upgrade data.

[0165] S709, for autonomous vehicles, periodically checks for the next target function that needs upgrading. If an upgrade is determined, ground staff can be notified to restart the autonomous vehicle so that it can return to execute S703.

[0166] In addition, if an upgrade is deemed necessary, autonomous vehicles can notify the cloud control platform so that the platform can perform corresponding operations, such as suspending the dispatch of orders to autonomous vehicles.

[0167] After upgrading the target functions, autonomous vehicles can complete autonomous driving tasks based on instructions from the cloud, such as... Figure 8 As shown, it includes:

[0168] S801, based on the autonomous driving tasks of autonomous vehicles, determines the target scenario in the cloud.

[0169] S802, the cloud sends the target scene to the autonomous vehicle.

[0170] S803: Based on the target scenario, the autonomous vehicle acquires the control sub-data corresponding to the target scenario for the target function.

[0171] S804, autonomous vehicles perform autonomous driving tasks based on control sub-data.

[0172] Based on the same technical concept, this disclosure also provides a data processing device for autonomous vehicles, applied to autonomous vehicles, such as... Figure 9 As shown, it includes:

[0173] The first determining module 901 is used to determine the target function that needs to be incrementally updated for the autonomous vehicle; the target function is any control function that needs to be updated in the set of autonomous driving control functions.

[0174] The first acquisition module 902 is used to acquire upgrade data for updating the target function;

[0175] Update module 903 is used to incrementally update the target function based on the target function upgrade data and the current version of the autonomous driving system.

[0176] In some embodiments, the first determining module includes:

[0177] The request submodule is used to request the cloud to send the test file;

[0178] The first parsing submodule is used to obtain the first global description information of the set of autonomous driving control functions from the detection file;

[0179] The first determining submodule is used to determine the first local description information of the control functions in the set of autonomous driving control functions when the first global description information and the second global description information of the set of autonomous driving control functions stored in the autonomous vehicle do not match.

[0180] The second determining submodule is used to determine the control function as the target function when the first partial description information of the control function and the second partial description information of the control function stored in the autonomous vehicle do not match.

[0181] In some embodiments, the first determining submodule is used to obtain first partial description information of the control function from the detection file.

[0182] In some embodiments, the first determining module includes:

[0183] The second parsing submodule is used to obtain the second local description information of each control function in the set of autonomous driving control functions;

[0184] The sending submodule is used to send the second partial description information of each control function to the cloud, so that the cloud can determine the target function based on the first partial description information of each control function stored in the cloud.

[0185] The receiving submodule is used to receive the function identifier of the target function sent from the cloud.

[0186] The third determination submodule is used to determine the control function corresponding to the function identifier as the target function.

[0187] In some embodiments, the first acquisition module includes:

[0188] The first acquisition submodule is used to obtain the download path of the upgrade data from the detection file;

[0189] The second acquisition submodule is used to acquire upgrade data based on the download path.

[0190] In some embodiments, the upgrade data is a custom structure, which includes control data for various autonomous driving tasks. The data processing device for the autonomous vehicle further includes:

[0191] The second acquisition module is used to acquire control data of the first target task when determining the first target task among multiple autonomous driving tasks.

[0192] The first control module is used to control the target function to execute the first target task based on the control data of the first target task.

[0193] The third acquisition module is used to acquire control data of the second target task when it is determined that the task is switched to the second target task among multiple autonomous driving tasks.

[0194] The second control module is used to control the target function to execute the second target task based on the control data of the second target task.

[0195] In some embodiments, the control data for each autonomous driving task includes control sub-data for at least one operating scenario, and the apparatus further includes:

[0196] The first receiving module is used to receive the target scenario sent from the cloud.

[0197] The third control module is used to control the target function to execute autonomous driving tasks based on the control sub-data of the target scenario.

[0198] This disclosure also provides another data processing device for autonomous vehicles, applied in the cloud, such as... Figure 10 As shown, it includes:

[0199] The response module 1001 is used to respond to the incremental update operation of the target function and obtain the upgrade data of the target function; the target function is any control function in the set of autonomous driving control functions that needs to be updated.

[0200] The first sending module 1002 is used to send upgrade data of the target function to the autonomous vehicle when the target function needs to be upgraded, so that the autonomous vehicle can incrementally update the target function based on the current version of the autonomous driving system.

[0201] In some embodiments, the data processing apparatus for an autonomous vehicle further includes:

[0202] The first generation module is used to generate first local description information of each control function in the set of autonomous driving control functions; and to generate first global description information of the set of autonomous driving control functions.

[0203] The second generation module is used to generate a detection file based on the first local description information and the first global description information of each control function.

[0204] The second sending module is used to send the detection file to the autonomous vehicle when it receives a detection request from the autonomous vehicle for detecting functions that require incremental updates.

[0205] In some embodiments, it also includes:

[0206] The second receiving module is used to receive the second partial description information of each control function sent by the autonomous vehicle;

[0207] The matching module is used to match the first local description information of each stored control function with the corresponding second local description information;

[0208] The second determining module is used to determine that the target function needs to be upgraded when the second local description information and the first local description information of the target function do not match.

[0209] In some embodiments, the upgrade data is a custom structure that includes control data for various autonomous driving tasks.

[0210] In some embodiments, the control data for each autonomous driving task includes control sub-data for at least one operating scenario, and the data processing device for the autonomous vehicle includes:

[0211] The third determination module is used to determine the target scenario in which the autonomous vehicle is located;

[0212] The third sending module is used to send the target scene to the autonomous vehicle.

[0213] In some embodiments, the data processing apparatus for an autonomous vehicle further includes:

[0214] The construction module is used to build the data corresponding to each control function of the autonomous vehicle, and obtain the function tree of the autonomous vehicle.

[0215] The response module is used to respond to simulation requests for the target function by retrieving data for the target function from the function tree.

[0216] The experimental module is used to conduct simulation experiments on the target function based on the data of the target function.

[0217] The specific functions and examples of each module and submodule of the apparatus in this disclosure can be found in the relevant descriptions of the corresponding steps in the above method embodiments, and will not be repeated here.

[0218] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0219] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0220] Figure 11A schematic block diagram of an example electronic device 1100 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0221] like Figure 11 As shown, device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in read-only memory (ROM) 1102 or a computer program loaded from storage unit 1108 into random access memory (RAM) 1103. The RAM 1103 may also store various programs and data required for the operation of device 1100. The computing unit 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. Input / output (I / O) interface 1105 is also connected to bus 1104.

[0222] Multiple components in device 1100 are connected to I / O interface 1105, including: input unit 1106, such as keyboard, mouse, etc.; output unit 1107, such as various types of monitors, speakers, etc.; storage unit 1108, such as disk, optical disk, etc.; and communication unit 1109, such as network card, modem, wireless transceiver, etc. Communication unit 1109 allows device 1100 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0223] The computing unit 1101 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1101 performs the various methods and processes described above, such as the data processing method for an autonomous vehicle. For example, in some embodiments, the data processing method for an autonomous vehicle may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1100 via ROM 1102 and / or communication unit 1109. When the computer program is loaded into RAM 1103 and executed by the computing unit 1101, one or more steps of the data processing method for an autonomous vehicle described above may be performed. Alternatively, in other embodiments, computing unit 1101 may be configured to perform data processing methods for autonomous vehicles by any other suitable means (e.g., by means of firmware).

[0224] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0225] Based on the aforementioned electronic devices, this disclosure also provides an autonomous driving vehicle, which may include electronic devices, and may further include communication components, a display screen for implementing a human-machine interface, and information collection devices for collecting information about the surrounding environment, etc., with the communication components, display screen, information collection devices, and electronic devices communicating with each other. The electronic devices included in the autonomous driving vehicle can incrementally update the target functions based on upgrade data of the target functions, on the basis of the current version of the autonomous driving system.

[0226] According to embodiments of this disclosure, the electronic device can be integrated with the communication component, display screen, and information acquisition device, or it can be separately configured with the communication component, display screen, and information acquisition device.

[0227] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0228] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0229] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0230] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0231] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0232] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0233] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A data processing method for an autonomous vehicle, applied to an autonomous vehicle, comprising: Identify the target functions that require incremental updates for autonomous vehicles, wherein the target functions are control functions whose first partial description information generated by the cloud and the second partial description information generated by the autonomous vehicle do not match; and the target functions are any control functions in the set of autonomous driving control functions that need to be updated. Obtain upgrade data for updating the target function; Based on the upgrade data of the target function, the target function is incrementally updated on the basis of the current version of the autonomous driving system; The upgrade data is a custom structure, which includes control data for various autonomous driving tasks. Each autonomous driving task's control data includes control sub-data for at least one operating scenario. The method further includes: The target scenario for receiving data sent from the cloud; The target function is controlled to perform autonomous driving tasks based on the control sub-data of the target scenario.

2. The method according to claim 1, wherein, When the target function is determined by the autonomous vehicle, the target function that needs incremental updates by the autonomous vehicle includes: Request the cloud to send the test file; Obtain the first global description information of the set of autonomous driving control functions from the detection file; If the first global description information and the second global description information of the set of autonomous driving control functions stored in the autonomous vehicle do not match, the first local description information of the control function in the set of autonomous driving control functions is determined. If the first partial description information of the control function does not match the second partial description information of the control function stored in the autonomous vehicle, the control function is determined to be the target function.

3. The method according to claim 2, wherein, The determination of the first partial description information of the control functions in the set of autonomous driving control functions includes: Obtain the first partial description information of the control function from the detection file.

4. The method according to claim 1, wherein, When the target function is determined by the cloud, the step of determining the target function that needs incremental updates for the autonomous vehicle includes: Obtain the second partial description information of each control function in the set of autonomous driving control functions; Send the second partial description information of each control function to the cloud; Receive the function identifier of the target function sent from the cloud; The control function corresponding to the function identifier is determined as the target function.

5. The method according to claim 2, wherein, The step of obtaining upgrade data for updating the target function includes: Obtain the download path of the upgrade data from the detection file; The upgrade data is obtained based on the download path.

6. The method according to any one of claims 2-5, further comprising: If a first target task among the various autonomous driving tasks is determined to be to be executed, control data for the first target task is acquired. The target function is controlled to execute the first target task based on the control data of the first target task; If it is determined that the switch to the second target task among the multiple autonomous driving tasks is to be made, the control data of the second target task shall be obtained; The target function is controlled to execute the second target task based on the control data of the second target task.

7. A data processing method for autonomous vehicles, applied in the cloud, comprising: In response to incremental update operations on the target function, upgrade data for the target function is obtained; The target function is any control function in the set of autonomous driving control functions that needs to be updated; the target function is a control function in which the first partial description information generated by the cloud and the second partial description information generated by the autonomous vehicle do not match. When an upgrade to the target function is required, the upgrade data for the target function is sent to the autonomous vehicle so that the autonomous vehicle can incrementally update the target function based on the current version of the autonomous driving system. The upgrade data is a custom structure, which includes control data for various autonomous driving tasks. Each autonomous driving task's control data includes control sub-data for at least one operating scenario. The method further includes: Determine the target scenario in which the autonomous vehicle is located; The target scenario is sent to the autonomous vehicle.

8. The method according to claim 7, further comprising: Generate first partial description information for each control function in the set of autonomous driving control functions; as well as, Generate the first global description information of the set of autonomous driving control functions; A detection file is generated based on the first local description information and the first global description information of each control function. Upon receiving a detection request from the autonomous vehicle for detecting functions requiring incremental updates, the detection file is sent to the autonomous vehicle.

9. The method according to claim 7, wherein, In the case where the target function is determined by the cloud, it also includes: Receive second partial description information of each control function sent by the autonomous vehicle; Match the first local description information of each stored control function with the corresponding second local description information; If the second partial description information and the first partial description information of the target function do not match, it is determined that the target function needs to be upgraded.

10. The method according to any one of claims 7-9, further comprising: The data corresponding to each control function of the autonomous vehicle are constructed to obtain the function tree of the autonomous vehicle; In response to a simulation request for the target function, data for the target function is obtained from the function tree; Simulation experiments were conducted on the target function based on the data of the target function.

11. A data processing device for an autonomous vehicle, applied to an autonomous vehicle, comprising: The first determining module is used to determine the target function that needs incremental updates for the autonomous vehicle. The target function is a control function whose first partial description information generated by the cloud and the second partial description information generated by the autonomous vehicle do not match. The target function is any control function in the set of autonomous driving control functions that needs to be updated. The first acquisition module is used to acquire upgrade data for updating the target function; The update module is used to incrementally update the target function based on the upgrade data of the target function, on the basis of the current version of the autonomous driving system. The upgrade data is a custom structure, which includes control data for various autonomous driving tasks. Each autonomous driving task's control data includes control sub-data for at least one operating scenario. The device also includes: The first receiving module is used to receive the target scenario sent from the cloud. The third control module is used to control the target function to perform autonomous driving tasks based on the control sub-data of the target scenario.

12. The apparatus according to claim 11, wherein, When the target function is determined by an autonomous vehicle, the first determining module includes: The request submodule is used to request the cloud to send the test file; The first parsing submodule is used to obtain the first global description information of the set of autonomous driving control functions from the detection file; The first determining submodule is used to determine the first local description information of the control function in the set of autonomous driving control functions when the first global description information and the second global description information of the set of autonomous driving control functions stored in the autonomous vehicle do not match. The second determining submodule is used to determine the control function as the target function when the first partial description information of the control function and the second partial description information of the control function stored in the autonomous vehicle do not match.

13. The apparatus according to claim 12, wherein, The first determining submodule is used to obtain first partial description information of the control function from the detection file.

14. The apparatus according to claim 11, wherein, When the target function is determined by the cloud, the first determining module includes: The second parsing submodule is used to obtain the second partial description information of each control function in the set of autonomous driving control functions; The sending submodule is used to send the second partial description information of each control function to the cloud, so that the cloud can determine the target function based on the first partial description information of each control function stored in the cloud. The receiving submodule is used to receive the function identifier of the target function sent from the cloud; The third determining submodule is used to determine the control function corresponding to the function identifier as the target function.

15. The apparatus according to claim 12, wherein, The first acquisition module includes: The first acquisition submodule is used to obtain the download path of the upgrade data from the detection file; The second acquisition submodule is used to acquire the upgrade data based on the download path.

16. The apparatus according to any one of claims 12-15, further comprising: The second acquisition module is used to acquire control data of the first target task when determining that the first target task among the multiple autonomous driving tasks is being executed. A first control module is used to control the target function to execute the first target task based on the control data of the first target task; The third acquisition module is used to acquire control data of the second target task when it is determined that the task is switched to the second target task among the multiple autonomous driving tasks; The second control module is used to control the target function to execute the second target task based on the control data of the second target task.

17. A data processing device for an autonomous vehicle, applied in the cloud, comprising: The response module is used to respond to incremental update operations on the target function and obtain upgrade data for the target function; The target function is any control function in the set of autonomous driving control functions that needs to be updated; the target function is a control function in which the first partial description information generated by the cloud and the second partial description information generated by the autonomous vehicle do not match. The first sending module is used to send the upgrade data of the target function to the autonomous vehicle when the target function needs to be upgraded, so that the autonomous vehicle can incrementally update the target function based on the current version of the autonomous driving system. The upgrade data is a custom structure, which includes control data for various autonomous driving tasks. Each autonomous driving task's control data includes control sub-data for at least one operating scenario. The device also includes: The third determining module is used to determine the target scene where the autonomous vehicle is located; The third sending module is used to send the target scene to the autonomous vehicle.

18. The apparatus of claim 17, further comprising: The first generation module is used to generate first partial description information of each control function in the set of autonomous driving control functions; And, generate first global description information for the set of autonomous driving control functions; The second generation module is used to generate a detection file based on the first local description information and the first global description information of each control function. The second sending module is used to send the detection file to the autonomous vehicle upon receiving a detection request from the autonomous vehicle for detecting functions that require incremental updates.

19. The apparatus of claim 17, further comprising: The second receiving module is used to receive the second partial description information of each control function sent by the autonomous vehicle; The matching module is used to match the first local description information of each stored control function with the corresponding second local description information; The second determining module is used to determine that the target function needs to be upgraded if the second partial description information and the first partial description information of the target function do not match.

20. The apparatus according to any one of claims 17-19, further comprising: The construction module is used to construct the data corresponding to each control function of the autonomous vehicle, thereby obtaining the function tree of the autonomous vehicle. A response module is used to obtain data of the target function from the function tree in response to a simulation request for the target function; The experimental module is used to conduct simulation experiments on the target function based on the data of the target function.

21. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method of any one of claims 1-10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-10.

23. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-10.

24. An autonomous vehicle, including the electronic equipment as claimed in claim 21.

Images