Automatic driving function adaptation method, expandable multi-board system, device and equipment

Abstract

The present application provides an autonomous driving function adaptation method, an expandable multi-board system, a device and equipment, by obtaining board assembly information, the board assembly information is used to characterize the computing power of the detachable board assembled in the expandable multi-board system; determining the target autonomous driving level according to the board assembly information; and running the target autonomous driving function corresponding to the target autonomous driving level based on at least two of the detachable boards. By determining the target autonomous driving level that matches the expandable multi-board system with multiple detachable boards based on the board assembly information corresponding to the expandable multi-board system, and then running the target autonomous driving function under the target autonomous driving level, the expandable multi-board system can execute the autonomous driving function corresponding to its own hardware capabilities, realize automatic adaptation of the hardware system and software functions, avoid time-consuming manual adaptation, and reduce the production cost of the vehicle.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to an autonomous driving function adaptation method, an expandable multi-board system, a device and equipment. Background Art

[0002] At present, as the autonomous driving function gradually improves and matures, more and more mass-produced vehicles are equipped with autonomous driving systems to achieve different levels of autonomous driving functions. For different models, based on product positioning considerations, different levels of autonomous driving systems are usually configured to enable them to run the corresponding levels of autonomous driving functions and applications.

[0003] In the prior art, in order to achieve the above-mentioned purpose, it is necessary to configure corresponding software and hardware systems for specific vehicle models. However, with the increase in the number of vehicle models and the refinement of vehicle models, the solutions in the prior art have led to problems such as cumbersome and time-consuming vehicle configuration process, thereby increasing the production cost of the vehicle. Summary of the invention

[0004] The present application provides an autonomous driving function adaptation method, an expandable multi-board system, a device and equipment, which are used to solve the problems in the prior art of cumbersome vehicle configuration process and increased time consumption caused by the need to design corresponding hardware and software systems for specific vehicle models.

[0005] In a first aspect, the present application provides an autonomous driving function adaptation method, which is applied to an expandable multi-board system, wherein the expandable multi-board system includes multiple detachable boards, and the method includes:

[0006] Obtain board assembly information, where the board assembly information is used to characterize the computing power of the detachable board assembled in the expandable multi-board system; determine a target autonomous driving level based on the board assembly information; and run a target autonomous driving function corresponding to the target autonomous driving level based on at least two of the detachable boards.

[0007] In one possible implementation, the board assembly information includes multiple first board information, and the first board information is used to characterize the board type of the detachable board; determining the target autonomous driving level based on the board assembly information includes: obtaining first board information of each detachable board assembled in the expandable multi-board system; and determining the target autonomous driving level based on each first board information.

[0008] In one possible implementation, at least one computing unit is provided in the detachable board, and the first board information includes core number information and / or core type information; wherein the core number information represents the number of the computing units, and the core type information represents the type of the computing units; determining the target autonomous driving level according to each of the first board information comprises: acquiring the core number information and / or core type information corresponding to each of the detachable boards; determining the target autonomous driving level based on the core number information and / or core type information corresponding to each of the detachable boards.

[0009] In one possible implementation, the target autonomous driving level is determined based on the core number information and / or core type information corresponding to each of the detachable boards, including: determining a target core based on the core type information corresponding to each of the detachable boards, the target core being used to implement a target autonomous driving function; and determining the target autonomous driving level according to the number of the target cores.

[0010] In one possible implementation, the target autonomous driving function corresponding to the target autonomous driving level is run based on at least two of the detachable boards, including: determining the target autonomous driving function corresponding to the target autonomous driving level based on a first trigger instruction; determining task information according to the core number information and / or core type information corresponding to each of the detachable boards, the task information representing the functional tasks corresponding to each of the detachable boards when running the target autonomous driving function; and calling each corresponding detachable board to run the target autonomous driving function according to the task information.

[0011] In one possible implementation, the expandable multi-board system includes a first board and a second board, wherein the first board is used to receive and distribute sensor data, and the second board is used to process the sensor data; running the target autonomous driving function corresponding to the target autonomous driving level based on at least two of the detachable boards includes: obtaining target sensor data corresponding to the target autonomous driving function through the first board; determining a target second board for processing the target sensor data based on the target autonomous driving function, and sending the target sensor data to the target second board; processing the target sensor data through the target second board to run the target autonomous driving function corresponding to the target autonomous driving level.

[0012] In a possible implementation, a plurality of computing units are provided in the second board, and sending the target sensor data to the target second board includes: acquiring core type information corresponding to each of the target second boards, wherein the core type information represents the type of the computing unit; and sending the target sensor data to the target computing unit of the target second board based on the core type information corresponding to each of the target second boards.

[0013] In the second aspect, the present application provides an expandable multi-board system, which is applied to smart cars. The expandable multi-board system includes multiple detachable boards, and the detachable boards are communicatively connected with each other; the detachable boards are used to implement at least one sub-function corresponding to a target autonomous driving level; the expandable multi-board system is used to use at least two of the detachable boards to run the target autonomous driving function corresponding to the target autonomous driving level.

[0014] In a third aspect, the present application provides an autonomous driving function adaptation device, which is applied to an expandable multi-board system, wherein the expandable multi-board system includes multiple detachable boards, including:

[0015] An acquisition module, used for acquiring board assembly information, wherein the board assembly information is used for characterizing the computing capability of the detachable board assembled in the scalable multi-board system;

[0016] A determination module, used to determine a target autonomous driving level according to the board assembly information;

[0017] An operation module is used to operate the target autonomous driving function corresponding to the target autonomous driving level based on at least two of the detachable boards.

[0018] In a possible implementation, the board assembly information includes multiple first board information, and the first board information is used to characterize the board type of the detachable board; the determination module is specifically used to: obtain the first board information of each detachable board assembled in the expandable multi-board system; determine the target autonomous driving level based on each first board information.

[0019] In one possible implementation, at least one computing unit is provided in the detachable board, and the first board information includes core number information and / or core type information; wherein the core number information represents the number of the computing units, and the core type information represents the type of the computing unit; when the determination module determines the target autonomous driving level according to each of the first board information, it is specifically used to: obtain the core number information and / or core type information corresponding to each of the detachable boards; determine the target autonomous driving level based on the core number information and / or core type information corresponding to each of the detachable boards.

[0020] In one possible implementation, when the determination module determines the target autonomous driving level based on the core number information and / or core type information corresponding to each of the detachable boards, it is specifically used to: determine the target core based on the core type information corresponding to each of the detachable boards, and the target core is used to implement the target autonomous driving function; determine the target autonomous driving level according to the number of the target cores.

[0021] In one possible implementation, the running module is specifically used to: determine the target autonomous driving function corresponding to the target autonomous driving level based on the first trigger instruction; determine task information according to the core number information and / or core type information corresponding to each of the detachable boards, the task information representing the functional tasks corresponding to each of the detachable boards when running the target autonomous driving function; and call each corresponding detachable board to run the target autonomous driving function according to the task information.

[0022] In one possible implementation, the expandable multi-board system includes a first board and a second board, wherein the first board is used to receive and distribute sensor data, and the second board is used to process the sensor data; the operation module is specifically used to: obtain target sensor data corresponding to the target autonomous driving function through the first board; determine a target second board for processing the target sensor data based on the target autonomous driving function, and send the target sensor data to the target second board; process the target sensor data through the target second board to run the target autonomous driving function corresponding to the target autonomous driving level.

[0023] In a possible implementation, a plurality of computing units are provided in the second board, and when the running module sends the target sensor data to the target second board, the running module is specifically used to: obtain core type information corresponding to each of the target second boards, where the core type information represents the type of the computing unit; and send the target sensor data to the target computing unit of the target second board based on the core type information corresponding to each of the target second boards.

[0024] In a fourth aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0025] The memory stores computer-executable instructions;

[0026] The processor executes the computer-executable instructions stored in the memory to implement the autonomous driving function adaptation method as described in any one of the first aspects of the embodiments of the present application.

[0027] In a fifth aspect, the present application provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the autonomous driving function adaptation method as described in any one of the first aspects of the embodiments of the present application.

[0028] According to the sixth aspect of the embodiments of the present application, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the autonomous driving function adaptation method as described in any one of the first aspects above.

[0029] The automatic driving function adaptation method, expandable multi-board system, device and equipment provided by the present application obtain board assembly information, the board assembly information is used to characterize the computing power of the detachable board assembled in the scalable multi-board system; determine the target automatic driving level according to the board assembly information; and run the target automatic driving function corresponding to the target automatic driving level based on at least two detachable boards. By determining the target automatic driving level that matches the scalable multi-board system with multiple detachable boards based on the board assembly information corresponding to the scalable multi-board system, and then running the target automatic driving function under the target automatic driving level, the scalable multi-board system can execute the automatic driving function corresponding to its own hardware capability, realize the automatic adaptation of the hardware system and the software function, and avoid the time-consuming manual adaptation. At the same time, combined with the rapid assembly characteristics of the scalable multi-board system itself, the rapid configuration of the software and hardware of the automatic driving system for different vehicles is realized, simplifying the vehicle configuration process, reducing time consumption, and reducing the production cost of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0031] Figure 1 A schematic diagram of an adaptation of an automatic driving function in the prior art;

[0032] Figure 2 A flowchart of an autonomous driving function adaptation method provided in one embodiment of the present application;

[0033] Figure 3 A schematic diagram of an expandable multi-board system provided by an embodiment of the present disclosure;

[0034] Figure 4 for Figure 3 A flowchart of specific implementation steps of step S102 in the illustrated embodiment;

[0035] Figure 5A schematic diagram of an operating target automatic driving function provided in an embodiment of the present application;

[0036] Figure 6 A flowchart of an autonomous driving function adaptation method provided in another embodiment of the present application;

[0037] Figure 7 A schematic diagram of a detachable board provided in an embodiment of the present application;

[0038] Figure 8 for Figure 6 A flowchart of specific implementation steps of step S203 in the illustrated embodiment;

[0039] Fig. 9 A schematic diagram of a functional task allocation provided in an embodiment of the present application;

[0040] Fig.10 for Figure 6 A flowchart of specific implementation steps of step S206 in the illustrated embodiment;

[0041] Fig.11 A schematic diagram of the structure of an automatic driving function adaptation device provided in one embodiment of the present application;

[0042] Fig.12 A schematic diagram of an electronic device provided by an embodiment of the present application;

[0043] Fig.13 It is a block diagram of a terminal device shown in an exemplary embodiment of the present application.

[0044] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0045] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0046] The application scenarios of the embodiments of the present application are explained below:

[0047] The automatic driving function adaptation method provided in the embodiment of the present application can be applied to the scenario of vehicle automatic driving. By way of example, the executor of the method provided in the embodiment of the present application can be a vehicle-mounted system, wherein the vehicle-mounted system is arranged in a smart car, and obtains sensor data by communicating with various sensor units arranged on the smart car, and implements various levels of automatic driving functions based on the sensor data, such as vehicle navigation, obstacle avoidance, lane keeping, etc.

[0048] Currently, different levels of autonomous driving systems are usually configured for different models before the vehicle leaves the factory, so that it can run the corresponding level of autonomous driving functions and applications. Since the computing power and data processing capabilities required for different levels of autonomous driving functions are very different, it is often necessary to deploy corresponding quantities and categories of hardware resources on the vehicle to achieve them. Therefore, in the prior art, for different models of smart cars, it is necessary to first design the corresponding hardware system for the specific vehicle model, and then install and adapt the corresponding software system for it, so as to achieve the corresponding level of autonomous driving function. Figure 1 A schematic diagram of an adaptation of an automatic driving function in the prior art is shown in FIG. Figure 1 As shown, before the vehicle leaves the factory, for the three types of vehicles A, B, and C (shown in the figure as vehicle A, vehicle B, and vehicle C), based on their respective fixed configured hardware resources, such as sensors, computing units, etc. Correspondingly, each vehicle needs to install software resources that match its hardware resources (shown in the figure as App1, App2, and App3), so as to complete the process of functional adaptation of the vehicle. Afterwards, during the actual operation of the vehicle, illustratively, the configured vehicle A can realize the L2 level of autonomous driving function based on the configured hardware resources and software resources; the configured vehicle B can realize the L3 level of autonomous driving function based on the configured hardware resources and software resources; the configured vehicle C can realize the L4 level of autonomous driving function based on the configured hardware resources and software resources.

[0049] Based on the introduction of the adaptation of the autonomous driving function in the above prior art, it can be seen that in the prior art, it is necessary to configure the corresponding software resources based on the hardware resources of the specific vehicle model to achieve the corresponding level of autonomous driving. However, with the increase in the number of vehicle models and the refinement of vehicle models, the process of configuring software resources for different vehicles will cause a lot of time consumption, thereby increasing the production cost of the vehicle.

[0050] It should be noted that the description of the autonomous driving level in this embodiment and the following embodiments is exemplary. It is a customized level based on the meaning of the autonomous driving level (from L0 to L5) proposed by the International Automobile Engineering. The specific functions corresponding to each level may be consistent with the autonomous driving level proposed by the International Automobile Engineering, or may not be consistent, and no specific restrictions are made here.

[0051] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0052] Figure 2 A flowchart of an automatic driving function adaptation method provided in one embodiment of the present application is shown in FIG. Figure 2 As shown, the autonomous driving function adaptation method provided in this embodiment is applied to an expandable multi-board system, and the expandable multi-board system includes multiple detachable boards. This embodiment includes the following steps:

[0053] Step S101 , obtaining board assembly information, where the board assembly information is used to characterize the computing capability of the detachable boards assembled in the expandable multi-board system.

[0054] Figure 3 A schematic diagram of an expandable multi-card system provided by an embodiment of the present disclosure, referring to Figure 3 As shown, exemplarily, the expandable multi-board system includes multiple detachable boards, and each detachable board is connected by a high-speed bus communication; the detachable board is used to implement at least one sub-function corresponding to the target autonomous driving level; the expandable multi-board system is used to use at least two detachable boards to run the target autonomous driving function corresponding to the target autonomous driving level. Further, in a possible implementation, the expandable multi-board system includes a base plate and multiple board installation interfaces for installing detachable boards, and the detachable board and the expansion multi-board system form a detachable connection through the board installation interface. Among them, the board installation interface is, for example, a high-speed bus interface. The board installation interfaces are connected by a bus, so as to realize the communication between the detachable boards installed in the board installation interface. Among them, exemplarily, the detachable board can be a hardware unit for realizing a dedicated function, for example, a board for realizing image target recognition. It can also be a hardware unit for realizing a general function, that is, the detachable board provides general computing resources, and realizes the corresponding function by executing specific tasks. Among them, the expandable multi-board system can correspond to the vehicle system, or constitute a part of the vehicle system.

[0055] Based on the above introduction to the expandable multi-board system and the detachable board, the board assembly information is information that characterizes the computing capability of the detachable board currently assembled in the expandable multi-board system. Specifically, for example, it may include descriptive information such as the identification mark, model, and quantity of the detachable board. When corresponding to different identification marks, models, and quantities, the computing capability of the detachable board is also different.

[0056] In a possible implementation, the board assembly information characterizes the total computing power of all detachable boards, that is, the total computing power of the expandable multi-board system, which can be expressed as a specific value. Accordingly, the higher the value, the higher the total computing power of the expandable multi-board system. Therefore, in the subsequent steps, the higher the corresponding target autonomous driving level, that is, the higher the level of autonomous driving function can be achieved; conversely, the lower the total computing power of the expandable multi-board system, and accordingly, only a lower level of autonomous driving function can be achieved.

[0057] In another possible implementation, the board assembly information includes multiple first board information, each of which represents the computing power of an expandable multi-board. For example, if the expandable multi-board system currently has four detachable boards installed, the board assembly information includes four first board information, which are respectively used to represent the computing power of the four currently installed detachable boards. Among them, the computing power referred to in the steps of this embodiment can represent the size of the computing resources corresponding to the expandable multi-board, such as memory, processor occupancy, etc.; it can also represent the functions that the expandable multi-board can achieve, such as image recognition function, image denoising function, path planning function, etc.

[0058] Among them, illustratively, since the scalable multi-board system is a hardware system that can be flexibly and quickly configured through a detachable card board, it can be quickly configured for different models of vehicles through the form of quick plug-in installation. In this application scenario, the board assembly information can be obtained by detecting and scanning the relevant information of the detachable board currently installed in the scalable multi-board system, and the specific implementation method will not be repeated.

[0059] Step S102, determining the target autonomous driving level according to the board assembly information.

[0060] Exemplarily, after obtaining the board assembly information based on the above steps, the corresponding target autonomous driving level can be determined based on the computing power represented by the board assembly information. For example, the computing power represented by the board assembly information is the available computing resources, more specifically, for example, the number of available cores. When the available computing resources are more, the corresponding target autonomous driving level is higher. For example, when the number of cores is 8, it corresponds to the L2 autonomous driving level; when the number of cores is 16, it corresponds to the L3 autonomous driving level. For another example, the computing power represented by the board assembly information is the function that can be realized by the expandable multi-board. More specifically, for example, when the board assembly information represents that the expandable multi-board can only realize the function of camera image recognition, it corresponds to the L2 autonomous driving level; when the board assembly information represents that the expandable multi-board can realize the function of lidar imaging, it corresponds to the L3 autonomous driving level.

[0061] Among them, exemplarily, when the board assembly information is a specific identifier or a set of identifiers, the corresponding target autonomous driving level can be determined based on a preset autonomous driving level mapping relationship. The autonomous driving level mapping relationship can be preset locally. The above examples are only exemplary, and the specific implementation can be set as needed.

[0062] In a possible implementation, the board assembly information includes a plurality of first board information, and the first board information is used to characterize the board type of the detachable board. Figure 4 As shown, the specific implementation steps of step S102 include:

[0063] Step S1021: Acquire first board information of each detachable board installed in the expandable multi-board system.

[0064] Step S1022: Determine the target autonomous driving level according to the information of each first board.

[0065] Exemplarily, the first board information may be an identifier of the board type that characterizes the detachable board. For example, the first board information is #1, which characterizes that the corresponding detachable board is an image processing board for performing image recognition calculations; the first board information is #2, which characterizes that the corresponding detachable board is a lidar processing board for performing recognition calculations on lidar data. When it is determined according to the first board information that a specific category of detachable boards is included, for example, a detachable board for performing recognition calculations on lidar data is included, the target autonomous driving level is determined to be L3. Since the hardware resources required for different autonomous driving levels are different, some essential hardware resource support is required to achieve a high level of autonomous driving. Therefore, in this embodiment, by characterizing the first board information of the board type of the detachable board, the target autonomous driving level can be quickly determined and the adaptation speed can be improved.

[0066] Step S103: Running a target autonomous driving function corresponding to a target autonomous driving level based on at least two detachable boards.

[0067] Exemplarily, after determining the target autonomous driving level, the corresponding function program can be called based on the corresponding detachable board to implement the corresponding target autonomous driving function according to the target autonomous driving level. For example, taking the adaptive cruise function as an example, the required cruise function is different for different autonomous driving levels. More specifically, for example, when the target autonomous driving level is L2, during the implementation of the adaptive cruise function, it is only necessary to receive and process the forward-looking monocular camera or forward millimeter-wave radar data, and then perform forward target recognition based on the forward-looking monocular camera or forward millimeter-wave radar data, so as to control the vehicle to complete the adaptive cruise function. Exemplarily, the target autonomous driving function can be implemented by calling the function program L2_autDrive_fun(); and when the target autonomous driving level is L3, it is necessary to receive and process lidar data, side and rear-view camera and millimeter-wave radar data, GPS data, inertial measurement unit (IMU) data and high-precision map data, and complete forward and side target recognition based on the above data, so as to control the vehicle to complete the adaptive cruise function. Exemplarily, the target autonomous driving function can be implemented by calling the function program L3_autDrive_fun().

[0068] At the same time, the hardware resources required to be called during this process are also different. Figure 5 A schematic diagram of an operating target automatic driving function provided in an embodiment of the present application, with reference to Figure 5 As shown, for example, when the target autonomous driving level is L2, the expandable multi-board system includes a detachable board #1 and a detachable board #2 (shown as #1 and #2 in the figure); wherein, detachable board #1 is used to obtain and process the forward monocular camera data to realize forward target recognition; detachable board #2 is used to output the vehicle control signal based on the forward target recognition result to perform vehicle control (i.e., the process of running the function program L2_autDrive_fun()). Afterwards, by expanding the board, the expandable board system can run the L3 level autonomous driving function. When the target autonomous driving level is L3, the expandable multi-board system includes a detachable board #1, a detachable board #2, a detachable board #3, and a detachable board #4, wherein the detachable board #1 is used to obtain and process the forward monocular camera data to realize forward target recognition, the detachable board #3 is used to obtain and process the lidar data, and fuse the forward target recognition results to obtain multi-directional target recognition results; the detachable board #4 is used to obtain high-precision map data and GPS data; the detachable board #2 is used to output the vehicle control signal based on the fusion of high-precision map data, GPS data and multi-directional target recognition results, and perform vehicle control (i.e., the process of running the function program L3_autDrive_fun()).

[0069] For example, the functional programs corresponding to different levels of autonomous driving are fully stored in the scalable multi-board system (vehicle system) or in the cloud server, and the scalable multi-board system (vehicle system) can be obtained through the method server. Therefore, there is no need to configure software resources separately for different vehicle models. The scalable multi-board system (vehicle system) can directly determine the corresponding autonomous driving level and the corresponding functional program by detecting the detachable board currently installed on the scalable multi-board system, without having to adapt the corresponding software resources separately for each model of vehicle, thereby shortening the time consumption of the vehicle adaptation process and reducing the production cost of the vehicle.

[0070] In this embodiment, by obtaining board assembly information, the board assembly information is used to characterize the computing power of the detachable boards assembled in the scalable multi-board system; according to the board assembly information, the target autonomous driving level is determined; based on at least two detachable boards, the target autonomous driving function corresponding to the target autonomous driving level is run. By determining the target autonomous driving level that matches the scalable multi-board system with multiple detachable boards based on the board assembly information corresponding to the scalable multi-board system, and then running the target autonomous driving function under the target autonomous driving level, the scalable multi-board system can execute the autonomous driving function corresponding to its own hardware capabilities, realize the automatic adaptation of the hardware system and the software function, and avoid the time-consuming manual adaptation. At the same time, combined with the rapid assembly characteristics of the scalable multi-board system itself, the rapid configuration of the hardware and software of the autonomous driving system for different vehicles is realized, simplifying the vehicle configuration process, reducing time consumption, and reducing the production cost of the vehicle.

[0071] Figure 6 A flowchart of an autonomous driving function adaptation method provided in another embodiment of the present application is shown in FIG. Figure 6 As shown, the automatic driving function adaptation method provided in this embodiment is Figure 2 On the basis of the automatic driving function adaptation method provided in the illustrated embodiment, steps S102-S103 are further refined, and the automatic driving function adaptation method provided in this embodiment includes the following steps:

[0072] Step S201, obtaining board assembly information, the board assembly information including multiple first board information, at least one computing unit is arranged in the detachable board, the first board information includes core number information and / or core type information; wherein the core number information represents the number of computing units, and the core type information represents the type of computing unit.

[0073] Figure 7 A schematic diagram of a detachable board provided in an embodiment of the present application, wherein the detachable board includes one or more computing units, such as Figure 7As shown, exemplarily, the detachable board #1 includes 3 computing units, namely S1-1, S1-2, and S1-3; the detachable board #2 includes 2 computing units, namely S2-1 and S2-2, and the detachable board #3 includes 1 computing unit, namely S3-1. The computing units interact with each other through the PCIe switch chip (PCIe switch), thereby realizing the aggregation and distribution of computing power. Among them, the computing unit is, for example, a chip or component with computing power such as a system-on-chip (System on Chip, SOC) and a field programmable gate array (Field Programmable Gate Array, FPGA). Different computing units are used to execute one or more sub-functions in the target autonomous driving function. For example, radar data processing, image data processing, multi-data fusion, vehicle control, etc. The first board information of each detachable board pair contains information describing the number of computing units and / or the type of computing units, that is, the number of cores information and the core type information. Among them, the type of computing unit is, for example, a CPU chip, an NPU chip, an image processing chip, etc.

[0074] Step S202, obtaining core number information and / or core type information corresponding to each detachable board.

[0075] Step S203, determining the target autonomous driving level based on the core number information and / or core type information corresponding to each detachable board.

[0076] Furthermore, after obtaining the core number information and / or core type information corresponding to each detachable board, the computing power corresponding to each detachable board can be determined based on the core number information and / or core type information corresponding to each detachable board, thereby determining the corresponding target autonomous driving level. Specifically, for example, the more the number of computing units (i.e., the number of cores), the stronger the computing power of the detachable board. According to the core number information, when the number of computing units is in the target interval, the target autonomous driving level corresponding to the target interval is obtained based on a preset mapping relationship. For another example, the type information of the computing unit can be used to determine a certain specific capability of the detachable board. According to the core type information, when the type of the computing unit is a target type, the target autonomous driving level corresponding to the target type is obtained based on a preset mapping relationship; when the type of the computing unit is not a target type, the target autonomous driving level corresponding to the target type is the default level.

[0077] In one possible implementation, Figure 8 As shown, the specific implementation of step S203 includes:

[0078] Step S2031, based on the core type information corresponding to each detachable board, determine the target core, the target core is used to realize the target autonomous driving function.

[0079] Step S2032, determining the target autonomous driving level according to the number of target cores.

[0080] Exemplarily, firstly, based on the first board information obtained through scanning and detecting each detachable board, the type of computing unit on each detachable board is determined. For example, computing unit S1 is arranged on detachable board #1, and S1 is FPGA, which is used for data distribution; computing unit S2 and computing unit S3 are arranged on detachable board #2, and both S2 and S3 are lidar processing chips for processing corresponding lidar data; computing unit S4 and computing unit S5 are arranged on detachable board #3, and computing unit S4 is a general-purpose processor chip; computing unit S6 is a control chip. In the above example, according to the preset detection rules, the chip used to process the lidar is determined as the target core, that is, S2 and S3 are determined as the target cores. Then, based on the number of target cores (2), the corresponding target autonomous driving level is determined. For example, when the number of target cores is greater than or equal to 4, the corresponding target autonomous driving level is L3; when the number of target cores is greater than or equal to 2 and less than 4, the corresponding target autonomous driving level is L2; ​​when the number of target cores is greater than or equal to 2 and less than 4, the corresponding target autonomous driving level is L2; ​​when the number of target cores is greater than or equal to 2 and less than 4, the corresponding target autonomous driving level is L2; ​​when the number of target cores is less than 2, the corresponding target autonomous driving level is L1.

[0081] To realize different levels of autonomous driving functions, the support of corresponding hardware resources is required. In this embodiment, in an autonomous driving system implemented based on an expandable multi-board system composed of detachable boards, the corresponding target autonomous driving level is determined by scanning the core number information and core type information of each detachable board, thereby achieving accurate mapping between the expandable multi-board system and the corresponding autonomous driving level, and improving the accuracy and efficiency of autonomous driving function adaptation.

[0082] Step S204: Determine a target autonomous driving function corresponding to the target autonomous driving level based on the first trigger instruction.

[0083] Step S205, determining task information according to the core number information and / or core type information corresponding to each detachable board, where the task information represents the functional tasks corresponding to each detachable board when running the target autonomous driving function.

[0084] Exemplarily, the first trigger instruction is an instruction for triggering an autonomous driving function. The first trigger instruction may be an instruction generated in response to a user instruction, a task plan, or other linked functional instructions, which will not be described in detail here. The first trigger instruction includes information representing a specific autonomous driving function, such as a function identifier corresponding to the "vehicle navigation" function, a function identifier corresponding to the "automatic cruise" function, and the like. Exemplarily, the first trigger instruction is used to indicate a certain specific autonomous driving function, but indicates the corresponding autonomous driving level. After obtaining the first trigger instruction, the target autonomous driving function corresponding to the target autonomous driving level is determined based on the target autonomous driving level obtained in the previous step. For example, the first trigger instruction contains a function identifier autDrive representing the "automatic cruise" function. Afterwards, based on the obtained target autonomous driving level L2, the function program L2_autDrive_fun() corresponding to the corresponding target autonomous driving function is obtained.

[0085] Furthermore, in order to realize the functional program corresponding to the target autonomous driving function, different hardware resources need to be called for data processing and control. Fig. 9 A schematic diagram of functional task allocation provided for an embodiment of the present application, exemplarily, implements L2_autDrive_fun() corresponding to four processing tasks: task1, task2, task3, and task4, wherein task1 is used to acquire camera images and perform target recognition, task2 is used to acquire millimeter-wave radar data and perform target recognition, task3 is used to fuse the target recognition result corresponding to the millimeter-wave radar data with the target recognition result corresponding to the camera image; task4 is used to control the vehicle based on the fusion result. According to the core number information and core type information corresponding to each detachable board, that is, the type and number of computing units in each detachable board, determine the computing units that can execute the above-mentioned processing tasks (task1, task2, task3, task4), and perform task allocation, for example, refer to Fig. 9 As shown, according to the core number information and core type information corresponding to each detachable board, the computing unit S1 in the detachable board #1 is determined to execute task 1; the computing unit S2 in the detachable board #2 is determined to execute task 2, and the computing unit S3 is determined to execute task 3; the computing unit S4 in the detachable board #3 executes task 4, and the computing unit S5 is a redundant safety unit. Referring to the above, the information describing the task allocation of the computing units of the above-mentioned detachable boards, i.e., the task information. The above-mentioned processing tasks can be randomly allocated based on the number of computing units alone, or allocated based on the type of computing units; or allocated by considering both the number and type of computing units at the same time. The specific implementation method can be set as needed, and will not be described one by one here.

[0086] Step S206: Based on the task information, call each corresponding detachable board to run the target automatic driving function.

[0087] Exemplarily, after obtaining the task information, the corresponding computing unit in the corresponding detachable board is called based on the task information, thereby realizing the operation of the target autonomous driving function.

[0088] In a possible implementation, the task information only indicates the computing units corresponding to some functions, that is, only some functional tasks are allocated, and other functional tasks can be dynamically allocated according to the specific available resources of the computing units, thereby improving the utilization of computing resources and the overall efficiency of the system. Exemplarily, the scalable multi-board system includes a first board and a second board, wherein the first board is used to receive and distribute sensor data, and the second board is used to process sensor data; Fig.10 As shown, the specific implementation steps of step S206 include:

[0089] Step S2061: Determine the first board based on the task information, and obtain target sensor data corresponding to the target autonomous driving function through the first board.

[0090] Step S2062: Based on the target autonomous driving function, determine the target second board for processing the target sensor data, and send the target sensor data to the target second board.

[0091] Exemplarily, based on the task information, a detachable board for receiving target sensor data corresponding to the target autonomous driving function, i.e., a first board, can be determined. The first board is used for data distribution, for example, distributing each frame of image data to different second boards for processing. In a possible implementation, the second board is a detachable board that provides general-purpose computing resources. The first board determines an idle second board as a target second board based on the available computing resources of other second boards, and sends the target sensor data to the target second board for processing, thereby improving the utilization of board resources.

[0092] Furthermore, a specific implementation method of sending the target sensor data to the target second board includes: obtaining core type information corresponding to each target second board, and sending the target sensor data to the target computing unit of the target second board based on the core type information corresponding to each target second board.

[0093] In the steps of this embodiment, after determining the target second board, the target sensor data is sent to a computing unit of the corresponding type (and the target computing unit) based on the core type information of the target second board. Considering that different types of computing units process different data, there are differences in processing efficiency. Therefore, sending the target sensor data to a computing unit of the corresponding type can further improve the data processing efficiency of the target second board, thereby improving the operating performance of the target autonomous driving function.

[0094] Step S2063: Process the target sensor data through the target second board to run the target autonomous driving function corresponding to the target autonomous driving level.

[0095] Example action: After the target second board obtains the corresponding target sensor data, it processes it according to the specific needs of the target autonomous driving function, and the target autonomous driving function corresponding to the target autonomous driving level can be realized. The specific implementation process is in Figure 2 The details have been introduced in the embodiments and will not be described again here.

[0096] In this embodiment, by further refining and allocating the data transmission path and making full use of the computing power of the computing units in each detachable board, it is possible to ensure the redundancy of computing resources, improve system stability and vehicle driving safety, and make full use of computing resources to improve the real-time operation of the target autonomous driving function.

[0097] Fig.11 This is a schematic diagram of the structure of an automatic driving function adaptation device provided by an embodiment of the present application. The automatic driving function adaptation device 3 is applied to an expandable multi-board system. The expandable multi-board system includes multiple detachable boards, such as Fig.11 As shown, the automatic driving function adaptation device 3 provided in this embodiment includes:

[0098] An acquisition module 31 is used to acquire board assembly information, where the board assembly information is used to characterize the computing capability of the detachable boards assembled in the scalable multi-board system;

[0099] A determination module 32, used to determine a target autonomous driving level according to the board assembly information;

[0100] The running module 33 is used to run the target autonomous driving function corresponding to the target autonomous driving level based on at least two detachable boards.

[0101] In one possible implementation, the board assembly information includes multiple first board information, and the first board information is used to characterize the board type of the detachable board; the determination module 32 is specifically used to: obtain the first board information of each detachable board assembled in the expandable multi-board system; determine the target autonomous driving level based on each first board information.

[0102] In one possible implementation, at least one computing unit is provided in the detachable board, and the first board information includes core number information and / or core type information; wherein the core number information represents the number of computing units, and the core type information represents the type of computing units; when the determination module 32 determines the target autonomous driving level according to each first board information, it is specifically used to: obtain the core number information and / or core type information corresponding to each detachable board; determine the target autonomous driving level based on the core number information and / or core type information corresponding to each detachable board.

[0103] In one possible implementation, when determining the target autonomous driving level based on the core number information and / or core type information corresponding to each detachable board, the determination module 32 is specifically used to: determine the target core based on the core type information corresponding to each detachable board, and the target core is used to implement the target autonomous driving function; determine the target autonomous driving level according to the number of target cores.

[0104] In one possible implementation, the running module 33 is specifically used to: determine the target autonomous driving function corresponding to the target autonomous driving level based on the first trigger instruction; determine the task information according to the core number information and / or core type information corresponding to each detachable board, the task information representing the functional tasks corresponding to each detachable board when running the target autonomous driving function; and call each detachable board to run the target autonomous driving function according to the task information.

[0105] In one possible implementation, the expandable multi-board system includes a first board and a second board, wherein the first board is used to receive and distribute sensor data, and the second board is used to process the sensor data; the operation module 33 is specifically used to: obtain target sensor data corresponding to the target autonomous driving function through the first board; determine a target second board for processing the target sensor data based on the target autonomous driving function, and send the target sensor data to the target second board; process the target sensor data through the target second board to run the target autonomous driving function corresponding to the target autonomous driving level.

[0106] In a possible implementation, a plurality of computing units are provided in the second board, and when the running module 33 sends the target sensor data to the target second board, it is specifically used to: obtain core type information corresponding to each target second board, where the core type information represents the type of the computing unit; and send the target sensor data to the target computing unit of the target second board based on the core type information corresponding to each target second board.

[0107] The acquisition module 31, the determination module 32 and the operation module 33 are connected in sequence. The automatic driving function adaptation device 3 provided in this embodiment can execute the following steps: Figure 2-Figure 10The technical solutions of any of the method embodiments shown have similar implementation principles and technical effects, which will not be described in detail here.

[0108] Fig.12 A schematic diagram of an electronic device provided by an embodiment of the present application, such as Fig.12 As shown, the electronic device 4 provided in this embodiment includes: a processor 41, and a memory 42 communicatively connected to the processor 41.

[0109] Wherein, the memory 42 stores computer-executable instructions;

[0110] The processor 41 executes the computer execution instructions stored in the memory 42 to implement the present application. Figure 2-Figure 10 The autonomous driving function adaptation method provided in any one of the corresponding embodiments.

[0111] The memory 42 and the processor 41 are connected via a bus 43 .

[0112] For related instructions, please refer to Figure 2-Figure 10 The relevant descriptions and effects corresponding to the steps in the corresponding embodiments can be understood, and no further elaboration is made here.

[0113] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the present application. Figure 2-Figure 10 The autonomous driving function adaptation method provided in any one of the corresponding embodiments.

[0114] Among them, the computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0115] One embodiment of the present application provides a computer program product, including a computer program, which implements the present application when executed by a processor. Figure 2-Figure 10 The autonomous driving function adaptation method provided in any one of the corresponding embodiments.

[0116] Fig.13 It is a block diagram of a terminal device shown in an exemplary embodiment of the present application. The terminal device 800 can be a vehicle-mounted terminal, a vehicle system, a computer, a digital broadcast terminal, a message transceiver device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0117] The terminal device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0118] The processing component 802 generally controls the overall operation of the terminal device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0119] The memory 804 is configured to store various types of data to support operations on the terminal device 800. Examples of such data include instructions for any application or method operating on the terminal device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage 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.

[0120] The power supply component 806 provides power to various components of the terminal device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the terminal device 800.

[0121] The multimedia component 808 includes a screen that provides an output interface between the terminal device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the terminal device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0122] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the terminal device 800 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0123] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0124] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the terminal device 800. For example, the sensor assembly 814 can detect the open / closed state of the terminal device 800, the relative positioning of the components, such as the display and keypad of the terminal device 800, and the sensor assembly 814 can also detect the position change of the terminal device 800 or a component of the terminal device 800, the presence or absence of contact between the user and the terminal device 800, the orientation or acceleration / deceleration of the terminal device 800, and the temperature change of the terminal device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0125] The communication component 816 is configured to facilitate wired or wireless communication between the terminal device 800 and other devices. The terminal device 800 can access a wireless network based on a communication standard, such as WiFi, 3G, 4G, 5G or other standard communication networks, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0126] In an exemplary embodiment, the terminal device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-mentioned embodiments of the present invention. Figure 2-Figure 10 The method provided in any one of the corresponding embodiments.

[0127] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by a processor 820 of a terminal device 800 to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0128] The embodiment of the present application also provides a non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the terminal device, the terminal device 800 can execute the above-mentioned present application Figure 2-Figure 10 The method provided in any one of the corresponding embodiments.

[0129] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0130] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the application disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0131] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for adapting an autonomous driving function, It is characterized in that Applied to an expandable multi-board system, the expandable multi-board system includes a plurality of detachable boards, and the method includes: Acquire board assembly information, where the board assembly information is used to characterize the computing capability of the detachable board assembled in the scalable multi-board system; the board assembly information includes a plurality of first board information, where the first board information includes core number information and / or core type information, where at least one computing unit is arranged in the detachable board, the core number information characterizes the number of the computing unit, and the core type information characterizes the type of the computing unit; Determining a target autonomous driving level according to the board assembly information; Based on at least two of the detachable boards, running a target autonomous driving function corresponding to the target autonomous driving level; The scalable multi-board system includes a first board and a second board, wherein the first board is used to receive and distribute sensor data, and the second board is used to process the sensor data; The operating the target autonomous driving function corresponding to the target autonomous driving level based on at least two of the detachable boards includes: Obtaining target sensor data corresponding to the target autonomous driving function through the first board; Based on the target autonomous driving function, determining a target second board for processing the target sensor data, and sending the target sensor data to the target second board, where the target second board is an idle second board determined based on available computing resources of the second board; Processing the target sensor data through the target second board to run the target autonomous driving function corresponding to the target autonomous driving level; The first board information is used to characterize the board type of the detachable board; and determining the target autonomous driving level according to the board assembly information includes: Acquire first board information of each detachable board installed in the expandable multi-board system; The target autonomous driving level is determined according to the information of each of the first boards.

2. The method according to claim 1, It is characterized in that The step of determining the target autonomous driving level according to the first board information includes: Obtaining core number information and / or core type information corresponding to each of the detachable boards; The target autonomous driving level is determined based on the core number information and / or core type information corresponding to each of the detachable boards.

3. The method according to claim 2, It is characterized in that The determining the target autonomous driving level based on the core number information and / or core type information corresponding to each of the detachable boards includes: Determining a target core based on the core type information corresponding to each of the detachable boards, wherein the target core is used to implement a target autonomous driving function; The target autonomous driving level is determined according to the number of the target cores.

4. The method according to claim 2, It is characterized in that The operating the target autonomous driving function corresponding to the target autonomous driving level based on at least two of the detachable boards includes: Determining a target autonomous driving function corresponding to the target autonomous driving level based on the first trigger instruction; Determine task information according to the core number information and / or core type information corresponding to each of the detachable boards, wherein the task information represents the functional tasks corresponding to each of the detachable boards when running the target autonomous driving function; According to the task information, each corresponding detachable board is called to run the target automatic driving function.

5. The method according to claim 1, It is characterized in that The second board is provided with a plurality of computing units, and the sending of the target sensor data to the target second board includes: Acquire core type information corresponding to each of the target second boards, wherein the core type information represents the type of the computing unit; Based on the core type information corresponding to each of the target second boards, the target sensor data is sent to a target computing unit of the target second board.

6. An expandable multi-board system, It is characterized in that Applied to a smart car, the expandable multi-board system includes a plurality of detachable boards, and each of the detachable boards is communicatively connected to each other; The detachable board is used to obtain board assembly information, and the board assembly information is used to characterize the computing capability of the detachable board assembled in the scalable multi-board system; The board assembly information includes a plurality of first board information, wherein the first board information includes core number information and / or core type information, the detachable board is provided with at least one computing unit, the core number information represents the number of the computing units, and the core type information represents the type of the computing unit; The detachable board is used to determine the target autonomous driving level according to the board assembly information; The detachable board is used to implement at least one sub-function corresponding to the target autonomous driving level; The scalable multi-board system is used to use at least two of the detachable boards to run the target autonomous driving function corresponding to the target autonomous driving level; The scalable multi-board system includes a first board and a second board, wherein the first board is used to receive and distribute sensor data, and the second board is used to process the sensor data; The using at least two of the detachable boards to run the target autonomous driving function corresponding to the target autonomous driving level includes: Obtaining target sensor data corresponding to the target autonomous driving function through the first board; Based on the target autonomous driving function, determining a target second board for processing the target sensor data, and sending the target sensor data to the target second board, where the target second board is an idle second board determined based on available computing resources of the second board; Processing the target sensor data through the target second board to run the target autonomous driving function corresponding to the target autonomous driving level; The first board information is used to characterize the board type of the detachable board; and determining the target autonomous driving level according to the board assembly information includes: Acquire first board information of each detachable board installed in the expandable multi-board system; The target autonomous driving level is determined according to the information of each of the first boards.

7. An automatic driving function adaptation device, It is characterized in that Applicable to an expandable multi-board system, the expandable multi-board system includes a plurality of detachable boards, including: an acquisition module, configured to acquire board assembly information, wherein the board assembly information is used to characterize the computing capability of the detachable board assembled in the scalable multi-board system; the board assembly information includes a plurality of first board information, wherein the first board information includes core number information and / or core type information, wherein at least one computing unit is arranged in the detachable board, the core number information characterizes the number of the computing unit, and the core type information characterizes the type of the computing unit; A determination module, used to determine a target autonomous driving level according to the board assembly information; An operating module, configured to operate a target autonomous driving function corresponding to the target autonomous driving level based on at least two of the detachable boards; The scalable multi-board system includes a first board and a second board, wherein the first board is used to receive and distribute sensor data, and the second board is used to process the sensor data; The operation module is specifically used for: Obtaining target sensor data corresponding to the target autonomous driving function through the first board; Based on the target autonomous driving function, determining a target second board for processing the target sensor data, and sending the target sensor data to the target second board, where the target second board is an idle second board determined based on available computing resources of the second board; Processing the target sensor data through the target second board to run the target autonomous driving function corresponding to the target autonomous driving level; The first board information is used to characterize the board type of the detachable board; The determination module is specifically used for: Acquire first board information of each detachable board installed in the expandable multi-board system; The target autonomous driving level is determined according to the information of each of the first boards.

8. An electronic device, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 5.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the automatic driving function adaptation method according to any one of claims 1 to 5.

10. A computer program product, comprising a computer program, which, when executed by a processor, implements the autonomous driving function adaptation method described in any one of claims 1 to 5.

Images