Automatic driving algorithm parameter updating method and device, electronic equipment and storage medium
Patent Information
- Application Number
- CN202611330166.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-31
- Publication Date
- 2026-10-27
AI Technical Summary
[0005]本发明的目的之一在于提供一种自动驾驶算法参数更新方法，以解决现有技术中的开发周期长、人力成本高、可移植性低的问题；目的之二在于提供一种自动驾驶算法参数更新装置；目的之三在于提供一种电子设备；目的之四在于提供一种计算机可读存储介质；目的之五在于提供一种计算机程序产品
[0032]通过参数更新请求中携带的目标车型标识，可以确定出目标车型文件夹和目标参数库，从目标车型文件夹中获取目标车型的第一标定参数文件，从目标参数库中获取目标车型的第二标定参数文件，根据第一标定参数文件、第二标定参数文件和原始可执行文件，生成更新后可执行文件，将更新后可执行文件发送至目标车型的车辆，从而目标车型的车辆可以更新自动驾驶算法参数，由于针对不同车型，使用同一个原始可执行文件，从而可以将同一自动驾驶算法的算法程序部署到多种车型的车辆上，在多种车型的车辆上，算法程序可以读取到第一标定参数文件和第二标定参数文件，实现自动驾驶算法参数在不同车型的车辆上的应用，无需针对不同车型，设计匹配的辅助驾驶软件，降低了开发周期和人力成本，提高了辅助驾驶系统在不同车型上的可移植性。
Smart Images
Figure CN122985218A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of automotive technology, and more specifically to a method, apparatus, electronic device, and storage medium for updating parameters of an autonomous driving algorithm. Background Technology
[0002] Advanced Driver Assistance Systems (ADAS) are a class of technologies that use sensors and autonomous driving algorithms to assist drivers and improve driving safety and comfort, covering functions such as lane keeping, automatic parking, and adaptive cruise control.
[0003] With the rapid development of driver assistance systems, more and more car models are equipped with them. However, the algorithm parameters of the autonomous driving algorithms in these systems vary across different car models.
[0004] To integrate the same driver assistance system across multiple vehicle models, the current technology involves designing customized driver assistance software for each model and then deploying that software onto the corresponding vehicles. However, this approach results in long development cycles, high labor costs, and reduced portability of the driver assistance system across different vehicle models. Summary of the Invention
[0005] One objective of this invention is to provide a method for updating parameters of an autonomous driving algorithm, in order to solve the problems of long development cycle, high labor cost and low portability in the prior art; a second objective is to provide a device for updating parameters of an autonomous driving algorithm; a third objective is to provide an electronic device; a fourth objective is to provide a computer-readable storage medium; and a fifth objective is to provide a computer program product.
[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:
[0007] A method for updating parameters in an autonomous driving algorithm, the method comprising:
[0008] In response to a parameter update request for the target vehicle model, the target vehicle model folder corresponding to the target vehicle model identifier is determined from multiple vehicle model folders, and the target parameter library corresponding to the target vehicle model identifier is determined from multiple parameter libraries; the parameter update request includes the target vehicle model identifier; wherein, the first calibration parameter file in each of the multiple vehicle model folders is obtained based on the SOC domain parameters in the autonomous driving algorithm parameters of each vehicle model; the second calibration parameter file in each of the multiple parameter libraries is obtained based on the MCU domain parameters in the autonomous driving algorithm parameters of each vehicle model;
[0009] Obtain the original executable file, and generate an updated executable file based on the first calibration parameter file in the target vehicle folder, the second calibration parameter file in the target parameter library, and the original executable file.
[0010] The updated executable file is sent to the target vehicle model; the vehicle uses the updated executable file to update the autonomous driving algorithm parameters.
[0011] Based on the aforementioned technical means, the target vehicle model identifier carried in the parameter update request can identify the target vehicle model folder and the target parameter library. The first calibration parameter file for the target vehicle model is retrieved from the target vehicle model folder, and the second calibration parameter file is retrieved from the target parameter library. An updated executable file is generated based on the first and second calibration parameter files and the original executable file. This updated executable file is then sent to the target vehicle model, allowing the target vehicle model to update its autonomous driving algorithm parameters. Since the same original executable file is used for different vehicle models, the same autonomous driving algorithm can be deployed on multiple vehicle models. On these multiple vehicle models, the algorithm can read the first and second calibration parameter files, enabling the application of autonomous driving algorithm parameters across different vehicle models. This eliminates the need to design matching driver assistance software for different vehicle models, reducing development cycle and manpower costs, and improving the portability of the driver assistance system across different vehicle models.
[0012] Furthermore, the method also includes: obtaining autonomous driving algorithm parameters for multiple vehicle models, and dividing the autonomous driving algorithm parameters for each vehicle model into SOC domain parameters and MCU domain parameters; in response to the parameter calibration of the SOC domain parameters for each vehicle model, obtaining a first calibration parameter file for each vehicle model; storing the first calibration parameter file for each vehicle model in the vehicle model folder corresponding to the vehicle model identifier for each vehicle model; in response to the parameter calibration of the MCU domain parameters for each vehicle model, obtaining a second calibration parameter file for each vehicle model; and storing the second calibration parameter file for each vehicle model in the parameter library corresponding to the vehicle model identifier for each vehicle model.
[0013] Based on the aforementioned technical means, the autonomous driving algorithm parameters of each vehicle model can be classified, calibrated, and stored according to the vehicle model identifier, thereby improving the efficiency of subsequent reading of autonomous driving algorithm parameters.
[0014] Furthermore, in response to the parameter calibration of the SOC domain parameters for each vehicle model, the first calibration parameter file for each vehicle model is obtained, including: dividing the SOC domain parameters of each vehicle model into several first subclasses according to the parameter functions of the SOC domain parameters; in response to the parameter calibration of the SOC domain parameters of each first subclass, obtaining the YAML calibration parameter file corresponding to each first subclass; and using the YAML calibration parameter file corresponding to each first subclass as the first calibration parameter file for each vehicle model.
[0015] Based on the above technical means, the SOC domain parameters of each vehicle model are classified according to their function, and the classified SOC domain parameters are calibrated in YAML file format, which improves the efficiency of reading calibration parameters from the first calibration parameter file.
[0016] Furthermore, in response to the parameter calibration of the MCU domain parameters for each vehicle model, a second calibration parameter file for each vehicle model is obtained, including: dividing the MCU domain parameters of each vehicle model into several second subclasses according to the parameter functions of the MCU domain parameters; in response to the parameter calibration of the MCU domain parameters of each second subclass, obtaining the par calibration parameter file corresponding to each second subclass; and using the par calibration parameter file corresponding to each second subclass as the second calibration parameter file for each vehicle model.
[0017] Based on the above technical means, the MCU domain parameters of each vehicle model are classified according to their function, and the classified MCU domain parameters are calibrated in par file format, which improves the efficiency of reading calibration parameters from the second calibration parameter file.
[0018] Furthermore, based on the first calibration parameter file in the target vehicle model folder, the second calibration parameter file in the target parameter library, and the original executable file, an updated executable file is generated, including: parsing the original executable file to obtain the original autonomous driving algorithm program and the original autonomous driving algorithm parameters; replacing the original autonomous driving algorithm parameters with the first calibration parameter file in the target vehicle model folder and the second calibration parameter file in the target parameter library to obtain new autonomous driving algorithm parameters; and merging the original autonomous driving algorithm program and the new autonomous driving algorithm parameters to generate the updated executable file.
[0019] Based on the aforementioned technical means, by modifying the parameters of the original autonomous driving algorithm without altering the original autonomous driving algorithm program, an updated executable file can be obtained, thus ensuring the security of the original autonomous driving algorithm program.
[0020] Furthermore, after the step of sending the updated executable file to the target vehicle model, the vehicle is configured as follows: the vehicle's MCU chip parses the updated executable file to obtain the original autonomous driving algorithm program, the first calibration parameter file in the target vehicle model folder, and the second calibration parameter file in the target parameter library; the original autonomous driving algorithm program is written into the vehicle's RAM; the first calibration parameter file in the target vehicle model folder is written into the vehicle's NVM; and the second calibration parameter file in the target parameter library is sent to the vehicle's SOC chip; the vehicle's SOC chip writes the second calibration parameter file in the target parameter library into the UFS through the PDM middleware.
[0021] Based on the aforementioned technical means, the target vehicle model can store the original autonomous driving algorithm program, the first calibration parameter file in the target vehicle model folder, and the second calibration parameter file in the target parameter library into the corresponding memory, which facilitates the subsequent updating of autonomous driving algorithm parameters.
[0022] Furthermore, the vehicle is configured to: upon detecting a restart of the vehicle's driving domain control, retrieve a first calibration parameter file from the target model folder in the NVM via the vehicle's cabin diagnostic tool, and retrieve a second calibration parameter file from the target parameter library in the UFS; if the cabin diagnostic tool detects that the calibration parameters of the first calibration parameter file in the target model folder and the second calibration parameter file in the target parameter library are correct, retrieve the original autonomous driving algorithm program from RAM via the driving domain control, and drive the original autonomous driving algorithm program to execute the first calibration parameter file in the target model folder and the second calibration parameter file in the target parameter library.
[0023] Based on the aforementioned technical means, the cockpit diagnostic tool can detect whether the calibration parameters in the first calibration parameter file and the second calibration parameter file are correct. By driving the original autonomous driving algorithm program through the driving domain control, the calibration parameters can be applied to the target vehicle model to update the autonomous driving algorithm parameters of the target vehicle model.
[0024] An autonomous driving algorithm parameter update device, the device comprising:
[0025] The target vehicle folder determination module is used to respond to the parameter update request of the target vehicle, determine the target vehicle folder corresponding to the target vehicle identifier from multiple vehicle folders, and determine the target parameter library corresponding to the target vehicle identifier from multiple parameter libraries; the parameter update request includes the target vehicle identifier; wherein, the first calibration parameter file in each of the multiple vehicle folders is obtained based on the SOC domain parameters in the autonomous driving algorithm parameters of each vehicle; the second calibration parameter file in each of the multiple parameter libraries is obtained based on the MCU domain parameters in the autonomous driving algorithm parameters of each vehicle;
[0026] The updated executable file generation module is used to obtain the original executable file and generate the updated executable file based on the first calibration parameter file in the target vehicle folder, the second calibration parameter file in the target parameter library, and the original executable file.
[0027] The updated executable file sending module is used to send the updated executable file to the target vehicle model; the vehicle uses the updated executable file to update the autonomous driving algorithm parameters.
[0028] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.
[0029] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described above.
[0030] A computer program product includes a computer program that, when executed by a processor, implements the steps of the method described above.
[0031] The beneficial effects of this invention are:
[0032] By using the target vehicle model identifier carried in the parameter update request, the target vehicle model folder and target parameter library can be identified. The first calibration parameter file for the target vehicle model is retrieved from the target vehicle model folder, and the second calibration parameter file is retrieved from the target parameter library. Based on the first and second calibration parameter files and the original executable file, an updated executable file is generated and sent to the target vehicle model. This allows the target vehicle model to update its autonomous driving algorithm parameters. Since the same original executable file is used for different vehicle models, the same autonomous driving algorithm can be deployed on multiple vehicle models. On these vehicles, the algorithm can read the first and second calibration parameter files, enabling the application of autonomous driving algorithm parameters across different vehicle models. This eliminates the need to design matching driver assistance software for different vehicle models, reducing development cycles and manpower costs, and improving the portability of the driver assistance system across different vehicle models. Attached Figure Description
[0033] Figure 1 A flowchart illustrating an autonomous driving algorithm parameter update method provided in one embodiment of this application;
[0034] Figure 2 A flowchart illustrating an autonomous driving algorithm parameter update method provided in another embodiment of this application;
[0035] Figure 3This is a schematic diagram illustrating the application of autonomous driving algorithm parameters in a vehicle according to one embodiment of this application.
[0036] Figure 4 This is a structural block diagram of an autonomous driving algorithm parameter update device provided in one embodiment of this application;
[0037] Figure 5 This is an internal structural diagram of an electronic device provided in one embodiment of this application. Detailed Implementation
[0038] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.
[0039] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.
[0040] like Figure 1 As shown, a method for updating parameters of an autonomous driving algorithm is provided, the method including:
[0041] Step S110: In response to the parameter update request of the target vehicle model, determine the target vehicle model folder corresponding to the target vehicle model identifier from multiple vehicle model folders, and determine the target parameter library corresponding to the target vehicle model identifier from multiple parameter libraries; the parameter update request includes the target vehicle model identifier; wherein, the first calibration parameter file in each of the multiple vehicle model folders is obtained based on the SOC domain parameters in the autonomous driving algorithm parameters of each vehicle model; the second calibration parameter file in each of the multiple parameter libraries is obtained based on the MCU domain parameters in the autonomous driving algorithm parameters of each vehicle model.
[0042] The target vehicle model refers to the vehicle that requires updates to its autonomous driving algorithm parameters. This includes, but is not limited to, gasoline-powered, pure electric, and hybrid versions.
[0043] Among them, the parameter update request is used to request an update to the autonomous driving algorithm parameters of the target vehicle model.
[0044] Among them, the vehicle model identifier refers to the standardized code that uniquely identifies the vehicle model. Each vehicle model folder corresponds to one vehicle model identifier, and each parameter library corresponds to one vehicle model identifier.
[0045] In advanced driver assistance systems (ADAS), the domain controller is generally divided into a System-on-Chip (SOC) domain and an MCU domain. The SOC domain operates on a file-based operating system, and its parameters include configuration file parameters and application software parameters. The MCU domain operates without a file-based operating system, and its parameters include basic software parameters and application software parameters. SOC domain parameters include, but are not limited to, LiDAR parameters, camera parameters, and vehicle dimensions (length, width, and height). MCU domain parameters include, but are not limited to, chassis control parameters, vehicle dynamics parameters, and actuator parameters.
[0046] In this embodiment, the parameter update request is parsed to obtain the target vehicle model identifier. The target vehicle model identifier is matched with the vehicle model identifiers corresponding to each vehicle model folder to determine the target vehicle model folder from multiple vehicle model folders. The target vehicle model identifier is then matched with the vehicle model identifiers corresponding to each parameter library to determine the target parameter library from multiple parameter libraries.
[0047] Step S120: Obtain the original executable file, and generate an updated executable file based on the first calibration parameter file in the target vehicle folder, the second calibration parameter file in the target parameter library, and the original executable file.
[0048] The original executable file includes the original autonomous driving algorithm program and the original autonomous driving algorithm parameters. The original executable file can be a hex file.
[0049] In this embodiment of the application, the original autonomous driving algorithm parameters in the original executable file can be modified using the first calibration parameter file in the target vehicle folder and the second calibration parameter file in the target parameter library to obtain an updated executable file.
[0050] In step S130, the updated executable file is sent to the target vehicle model; the vehicle uses the updated executable file to update the autonomous driving algorithm parameters.
[0051] In this embodiment of the application, the updated executable file is sent to the vehicle of the target model. After receiving the updated executable file, the vehicle drives the original autonomous driving algorithm program to run the first calibration parameter file in the target model folder and the second calibration parameter file in the target parameter library to update the autonomous driving algorithm parameters of the vehicle.
[0052] The aforementioned autonomous driving algorithm update method identifies the target vehicle model folder and target parameter library by using the target vehicle model identifier carried in the parameter update request. It retrieves the first calibration parameter file for the target vehicle model from the folder and the second calibration parameter file from the library. Based on the first and second calibration parameter files and the original executable file, an updated executable file is generated and sent to the target vehicle model. This allows the target vehicle model to update its autonomous driving algorithm parameters. Since the same original executable file is used for different vehicle models, the same autonomous driving algorithm can be deployed on multiple vehicle models. On these vehicles, the algorithm can read the first and second calibration parameter files, enabling the application of autonomous driving algorithm parameters across different vehicle models. This eliminates the need to design matching driver assistance software for different vehicle models, reducing development cycle and manpower costs, and improving the portability of the driver assistance system across different vehicle models.
[0053] In one embodiment, such as Figure 2 As shown, the method also includes:
[0054] Step S210: Obtain autonomous driving algorithm parameters for multiple vehicle models, and divide the autonomous driving algorithm parameters for each vehicle model into SOC domain parameters and MCU domain parameters.
[0055] Among them, multiple models can be multiple models under the same Electrical / Electronic Architecture (EEA), or multiple models under different Electrical / Electronic Architectures.
[0056] In this embodiment, parameter classification rules can be configured based on the autonomous driving algorithm logic, vehicle configuration differences, and domain control hardware characteristics. According to these rules, the autonomous driving algorithm parameters for each vehicle model are divided into SOC domain parameters and MCU domain parameters.
[0057] Step S220: In response to the parameter calibration of the SOC domain parameters for each vehicle model, obtain the first calibration parameter file for each vehicle model; and store the first calibration parameter file for each vehicle model in the vehicle model folder corresponding to the vehicle model identifier for each vehicle model.
[0058] In this embodiment, a parameter calibration tool can be used to calibrate the SOC domain parameters for each vehicle model, obtaining a first calibration parameter file for each model. The parameter calibration tool can be a CANape tool.
[0059] Step S230: In response to the parameter calibration of the MCU domain parameters for each vehicle model, obtain the second calibration parameter file for each vehicle model; store the second calibration parameter file for each vehicle model in the parameter library corresponding to the vehicle model identifier for each vehicle model.
[0060] In this embodiment, a parameter calibration tool can be used to calibrate the MCU domain parameters for each vehicle model, obtaining a second calibration parameter file for each model. The parameter calibration tool can be a CANape tool.
[0061] This application's embodiments improve the efficiency of subsequently reading autonomous driving algorithm parameters by classifying, calibrating, and storing the autonomous driving algorithm parameters of various vehicle models according to vehicle model identifiers.
[0062] In one embodiment, in response to the parameter calibration of the SOC domain parameters for each vehicle model, a first calibration parameter file for each vehicle model is obtained, including:
[0063] Step S310: Based on the parameter functions of the SOC domain parameters, divide the SOC domain parameters of each vehicle model into several first subclasses.
[0064] In this embodiment of the application, at least one SOC domain parameter that implements the same parameter function is divided into a first subclass.
[0065] Step S320: In response to the parameter calibration of the SOC domain parameters of each first subclass, obtain the yaml calibration parameter file corresponding to each first subclass;
[0066] Step S330: Use the YAML calibration parameter file corresponding to each first subclass as the first calibration parameter file for each vehicle model.
[0067] YAML is a highly readable data serialization language commonly used for configuration management and structured data storage. Its syntax is simple, it relies on indentation to represent hierarchical relationships, supports various data types and comment functionality, making it suitable for storing configuration files or data files.
[0068] In this embodiment, a parameter calibration tool is used to calibrate the SOC domain parameters of each first subclass, obtaining the calibrated SOC domain parameters. The calibrated SOC domain parameters are saved in YAML file format to obtain the YAML calibration parameter file corresponding to each first subclass. The parameter calibration tool can be a CANape tool.
[0069] This application embodiment classifies the SOC domain parameters of each vehicle model according to their function, and calibrates the classified SOC domain parameters in YAML file format, thereby improving the efficiency of reading calibration parameters from the first calibration parameter file.
[0070] In one embodiment, in response to the parameter calibration of the MCU domain parameters for each vehicle model, a second calibration parameter file for each vehicle model is obtained, including:
[0071] Step S410: Based on the parameter functions of the MCU domain parameters, divide the MCU domain parameters of each vehicle model into several second subclasses.
[0072] In this application embodiment, at least one MCU domain parameter that implements the same parameter function is divided into a second subclass.
[0073] Step S420: In response to the parameter calibration of the MCU domain parameters of each second subclass, obtain the par calibration parameter file corresponding to each second subclass;
[0074] Step S430: Use the par calibration parameter file corresponding to each second subclass as the second calibration parameter file for each vehicle model.
[0075] Among them, the PAR file is a parameter set file used to save a set of numerical snapshots of a calibration quantity.
[0076] In this embodiment, a parameter calibration tool is used to calibrate the MCU domain parameters of each second subclass, obtaining the calibrated MCU domain parameters. The calibrated MCU domain parameters are saved in par file format to obtain the par calibration parameter file corresponding to each second subclass. The parameter calibration tool can be a CANape tool.
[0077] This application embodiment classifies the MCU domain parameters of each vehicle model according to their function and calibrates the classified MCU domain parameters in par file format, thereby improving the efficiency of reading calibration parameters from the second calibration parameter file.
[0078] In one embodiment, an updated executable file is generated based on a first calibration parameter file in the target vehicle model folder, a second calibration parameter file in the target parameter library, and the original executable file, including:
[0079] Step S510: Parse the original executable file to obtain the original autonomous driving algorithm program and the original autonomous driving algorithm parameters.
[0080] The original autonomous driving algorithm program is an executable code, which includes, but is not limited to, lane keeping algorithm program, automatic parking algorithm program, and adaptive cruise algorithm program.
[0081] Among them, the original autonomous driving algorithm parameters are external configuration parameters that the algorithm program reads, and the logic is executed according to the values of the algorithm parameters.
[0082] Step S520: Replace the original autonomous driving algorithm parameters with the first calibration parameter file in the target vehicle folder and the second calibration parameter file in the target parameter library to obtain new autonomous driving algorithm parameters.
[0083] In this embodiment, the storage address of the original autonomous driving algorithm parameters is obtained, and the first calibration parameter file in the target vehicle folder and the second calibration parameter file in the target parameter library are copied to the storage address of the original autonomous driving algorithm parameters to replace the original autonomous driving algorithm parameters and obtain new autonomous driving algorithm parameters.
[0084] Step S530: Merge the original autonomous driving algorithm program and the new autonomous driving algorithm parameters to generate an updated executable file.
[0085] In this embodiment, the original autonomous driving algorithm program and the new autonomous driving algorithm parameters can be merged based on the address of the original program and the address of the new parameters to generate an updated executable file. Specifically, the original and new algorithms can be copied to the same address and then merged.
[0086] This application's embodiments modify the parameters of the original autonomous driving algorithm without altering the original autonomous driving algorithm program to obtain an updated executable file, thus ensuring the security of the original autonomous driving algorithm program.
[0087] In one embodiment, after the step of sending the updated executable to the target vehicle model, the vehicle is configured as follows:
[0088] In step S610, the vehicle's MCU chip parses the updated executable file to obtain the original autonomous driving algorithm program, the first calibration parameter file in the target vehicle model folder, and the second calibration parameter file in the target parameter library.
[0089] In the embodiments of this application, such as Figure 3 As shown, the vehicle's MCU chip obtains the updated executable file via the UDS protocol, parses the updated executable file to obtain the original autonomous driving algorithm program, the first calibration parameter file in the target vehicle model folder, and the second calibration parameter file in the target parameter library. The UDS (Unified Diagnostic Services) protocol is a general automotive diagnostic protocol.
[0090] Step S620: Write the original autonomous driving algorithm program into the vehicle's RAM.
[0091] RAM stands for Random Access Memory, which is an internal memory that directly exchanges data with the CPU.
[0092] In this embodiment, the vehicle's MCU chip writes the original autonomous driving algorithm program into the vehicle's RAM so that the original autonomous driving algorithm program can be read later.
[0093] Step S630: Write the first calibration parameter file in the target vehicle model folder to the vehicle's NVM, and send the second calibration parameter file in the target parameter library to the vehicle's SOC chip.
[0094] NVM (Non-Volatile Memory) is a type of computer memory that ensures data is not lost even when power is off.
[0095] In this embodiment, the vehicle's MCU chip writes the first calibration parameter file from the target model folder into the vehicle's NVM so that the first calibration parameter file can be read subsequently.
[0096] The vehicle's MCU chip sends the second calibration parameter file from the target parameter library to the vehicle's SOC chip, which typically stores the second calibration parameter file.
[0097] In step S640, the vehicle's SOC chip writes the second calibration parameter file from the target parameter library into the UFS through the PDM middleware.
[0098] Among them, the PDM (Parameter Data Manager) middleware is a unified parameter management component in the SOC domain, used to manage all algorithm running parameters, provide parameter query, and parameter update interfaces.
[0099] UFS (Universal Flash Storage) is a general-purpose flash storage technology designed to replace traditional eMMC and EMCP storage solutions. With its high speed, low power consumption, and high reliability, UFS has become the mainstream storage solution for high-end smart devices.
[0100] In this embodiment, the vehicle's SOC chip sends the second calibration parameter file from the target parameter library to the PDM middleware via the inter-chip IPC protocol. The PDM middleware then writes the second calibration parameter file from the target parameter library to the UFS via a persistent storage module. After successful writing to the UFS, the PDM middleware sends feedback to the MCU chip via the IPC protocol, confirming that the second calibration parameter file in the target parameter library has been correctly saved. The inter-chip IPC protocol is a cross-core communication protocol between the MCU and the SOC, two heterogeneous processors.
[0101] The target vehicle model in this application embodiment can store the original autonomous driving algorithm program, the first calibration parameter file in the target vehicle model folder, and the second calibration parameter file in the target parameter library into the corresponding memory, which facilitates the subsequent updating of autonomous driving algorithm parameters.
[0102] In one embodiment, the vehicle is also configured to:
[0103] In step S710, when a vehicle driving domain control restart is detected, the first calibration parameter file in the target model folder is obtained from the NVM through the vehicle's cabin diagnostic tool, and the second calibration parameter file in the target parameter library is obtained from the UFS.
[0104] Among them, the cockpit diagnostic tool is a UDS / DoIP diagnostic tool for the development, DV testing, and offline debugging of intelligent cockpit domain controllers.
[0105] In this embodiment, after the vehicle's driving domain control is restarted, the cabin diagnostic tool requests to obtain the first calibration parameter file and the second calibration parameter file that have been written. Specifically, the vehicle's cabin diagnostic tool obtains the first calibration parameter file from the target model folder in the NVM and the second calibration parameter file from the target parameter library in the UFS.
[0106] In step S720, if the cabin diagnostic instrument detects that the calibration parameters of the first calibration parameter file in the target vehicle folder and the second calibration parameter file in the target parameter library are correct, the original autonomous driving algorithm program is obtained from RAM through the driving domain control, and the original autonomous driving algorithm program is driven to execute the first calibration parameter file in the target vehicle folder and the second calibration parameter file in the target parameter library.
[0107] In this embodiment, the cockpit diagnostic tool performs calibration parameter diagnosis on the first calibration parameter file in the target vehicle model folder and the second calibration parameter file in the target parameter library to determine whether the calibration parameters are correct. If the calibration parameters are correct, the original autonomous driving algorithm program is driven to execute the first calibration parameter file in the target vehicle model folder and the second calibration parameter file in the target parameter library to update the vehicle's autonomous driving algorithm parameters. If the calibration parameters are incorrect, an abnormal alarm message is sent to the MCU chip, indicating that the calibration parameters are incorrect.
[0108] In one embodiment, the parameter update process for the target vehicle model is initiated by a task triggering a submaster to initiate an upgrade request. The submaster sends a parameter update request with an IPC_msg message body, which is filled by the SOC upgrade interface HAL. `msg_type = 0x1` indicates that calibration upgrade data is being sent from the MCU chip; other reserved fields default to 0. Upon receiving the parameter update request, the MCU chip first determines whether it is requesting calibration upgrade data or version information, based on the `msg_type` field. If it is a request to obtain calibration upgrade data, the received updated executable file is written to NorFlash for storage, and simultaneously fed back to the data upgrade abstract interface (sma_install_mcucalib) via the IPC_ack protocol. After receiving the relevant response parameters, the data upgrade abstract interface feeds back the progress status to the submaster every 2 seconds. Upon receiving the relevant status information, the submaster performs the upgrade processing based on the status information. After the upgrade is complete, the submaster initiates a version information retrieval request, where `msg_type = 0xa` indicates that version number information is being retrieved from the MCU chip; other fields default to 0. After receiving a version information retrieval request, the MCU chip first determines whether it's for upgrade data or version information retrieval, using the `msg_type` field for confirmation. If it's a version information retrieval request, it reads the version information from NorFlash and sends it back to the version retrieval abstract interface (`sma_get_version_info_mcucalib`) via the `IPC_ack_version` protocol. The version retrieval abstract interface then sends it back to the submaster. The submaster performs relevant comparison and judgment. If the retrieved version number matches the expected version number, the upgrade succeeds; otherwise, the upgrade fails.
[0109] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.
[0110] In one exemplary embodiment, such as Figure 4 As shown, an autonomous driving algorithm parameter update device is provided, the device comprising:
[0111] The target vehicle model folder determination module 410 is used to respond to a parameter update request for the target vehicle model, determine the target vehicle model folder corresponding to the target vehicle model identifier from multiple vehicle model folders, and determine the target parameter library corresponding to the target vehicle model identifier from multiple parameter libraries; the parameter update request includes the target vehicle model identifier; wherein, the first calibration parameter file in each of the multiple vehicle model folders is obtained based on the SOC domain parameters in the autonomous driving algorithm parameters of each vehicle model; the second calibration parameter file in each of the multiple parameter libraries is obtained based on the MCU domain parameters in the autonomous driving algorithm parameters of each vehicle model;
[0112] The updated executable file generation module 420 is used to obtain the original executable file and generate the updated executable file based on the first calibration parameter file in the target vehicle folder, the second calibration parameter file in the target parameter library, and the original executable file.
[0113] The updated executable file sending module 430 is used to send the updated executable file to the target vehicle model; the vehicle uses the updated executable file to update the autonomous driving algorithm parameters.
[0114] In one embodiment, the apparatus further includes:
[0115] The algorithm parameter partitioning module is used to obtain the autonomous driving algorithm parameters of multiple vehicle models and partition the autonomous driving algorithm parameters of each vehicle model into SOC domain parameters and MCU domain parameters.
[0116] The first calibration parameter file acquisition module is used to acquire the first calibration parameter file for each vehicle model in response to the parameter calibration of the SOC domain parameters for each vehicle model; and to store the first calibration parameter file for each vehicle model in the vehicle model folder corresponding to the vehicle model identifier for each vehicle model.
[0117] The second calibration parameter file acquisition module is used to acquire the second calibration parameter file for each vehicle model in response to the parameter calibration of the MCU domain parameters for each vehicle model; and to store the second calibration parameter file for each vehicle model in the parameter library corresponding to the vehicle model identifier for each vehicle model.
[0118] In one embodiment, the first calibration parameter file acquisition module includes:
[0119] The SOC domain parameter partitioning unit is used to divide the SOC domain parameters of each vehicle model into several first subclasses according to the parameter functions of the SOC domain parameters.
[0120] The SOC domain parameter calibration unit is used to obtain the YAML calibration parameter file corresponding to each first subclass in response to the parameter calibration of the SOC domain parameters of each first subclass.
[0121] The first calibration parameter file acquisition unit is used to use the YAML calibration parameter file corresponding to each first subclass as the first calibration parameter file for each vehicle model.
[0122] In one embodiment, the second calibration parameter file acquisition module includes:
[0123] The MCU domain parameter partitioning unit is used to divide the MCU domain parameters of each vehicle model into several second subclasses according to the parameter functions of the MCU domain parameters.
[0124] The MCU domain parameter calibration unit is used to obtain the par calibration parameter file corresponding to each second subclass in response to the parameter calibration of the MCU domain parameters of each second subclass.
[0125] The second calibration parameter file acquisition unit is used to use the par calibration parameter file corresponding to each second subclass as the second calibration parameter file for each vehicle model.
[0126] In one embodiment, the updated executable generation module includes:
[0127] The file parsing unit is used to parse the original executable file to obtain the original autonomous driving algorithm program and the original autonomous driving algorithm parameters.
[0128] The parameter replacement unit is used to replace the original autonomous driving algorithm parameters with the first calibration parameter file in the target vehicle folder and the second calibration parameter file in the target parameter library to obtain new autonomous driving algorithm parameters.
[0129] The updated executable file generation unit is used to merge the original autonomous driving algorithm program and the new autonomous driving algorithm parameters to generate the updated executable file.
[0130] Each module in the aforementioned autonomous driving algorithm parameter update device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.
[0131] In one exemplary embodiment, an electronic device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5As shown, this electronic device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores update data for autonomous driving algorithm parameters. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for updating parameters of an autonomous driving algorithm.
[0132] Those skilled in the art will understand that Figure 5 The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the electronic devices to which the present application is applied. Specific electronic devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In one embodiment, an electronic device is provided, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the above-described autonomous driving algorithm parameter update method. The steps of the autonomous driving algorithm parameter update method described here can be steps from the autonomous driving algorithm parameter update methods of the various embodiments described above.
[0133] In one embodiment, a computer-readable storage medium is provided, storing a computer program that, when executed by a processor, causes the processor to perform the steps of the above-described autonomous driving algorithm parameter update method. The steps of the autonomous driving algorithm parameter update method described here can be steps from one of the autonomous driving algorithm parameter update methods in the various embodiments described above.
[0134] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, causes the processor to perform the steps of the above-described autonomous driving algorithm parameter update method. The steps of the autonomous driving algorithm parameter update method described here may be steps from the autonomous driving algorithm parameter update method of the various embodiments described above.
[0135] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.
[0136] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.
[0137] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0138] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for updating parameters in an autonomous driving algorithm, characterized in that, The method includes: In response to a parameter update request for a target vehicle model, the target vehicle model folder corresponding to the target vehicle model identifier is determined from multiple vehicle model folders, and the target parameter library corresponding to the target vehicle model identifier is determined from multiple parameter libraries; the parameter update request includes the target vehicle model identifier; wherein, the first calibration parameter file in each of the multiple vehicle model folders is obtained based on the SOC domain parameters in the autonomous driving algorithm parameters of each vehicle model; the second calibration parameter file in each of the multiple parameter libraries is obtained based on the MCU domain parameters in the autonomous driving algorithm parameters of each vehicle model; Obtain the original executable file, and generate an updated executable file based on the first calibration parameter file in the target vehicle folder, the second calibration parameter file in the target parameter library, and the original executable file; The updated executable file is sent to the target vehicle model; the vehicle is used to update the autonomous driving algorithm parameters according to the updated executable file.
2. The method according to claim 1, characterized in that, The method further includes: The autonomous driving algorithm parameters of multiple vehicle models are obtained, and the autonomous driving algorithm parameters of each vehicle model are divided into SOC domain parameters and MCU domain parameters. In response to the parameter calibration of the SOC domain parameters for each vehicle model, a first calibration parameter file for each vehicle model is obtained; the first calibration parameter file for each vehicle model is stored in the vehicle model folder corresponding to the vehicle model identifier of each vehicle model; In response to the parameter calibration of the MCU domain parameters for each vehicle model, a second calibration parameter file for each vehicle model is obtained; the second calibration parameter file for each vehicle model is stored in the parameter library corresponding to the vehicle model identifier for each vehicle model.
3. The method according to claim 2, characterized in that, The step of obtaining a first calibration parameter file for each vehicle model in response to the parameter calibration of the SOC domain parameters for each vehicle model includes: Based on the parameter functions of the SOC domain parameters, the SOC domain parameters of each vehicle model are divided into several first subclasses; In response to the parameter calibration of the SOC domain parameters of each first subclass, obtain the YAML calibration parameter file corresponding to each first subclass; The YAML calibration parameter file corresponding to each of the first subclasses is used as the first calibration parameter file for each vehicle model.
4. The method according to claim 2, characterized in that, In response to the parameter calibration of the MCU domain parameters for each vehicle model, a second calibration parameter file for each vehicle model is obtained, including: Based on the parameter functions of the MCU domain parameters, the MCU domain parameters of each vehicle model are divided into several second subclasses; In response to the parameter calibration of the MCU domain parameters of each second subclass, obtain the par calibration parameter file corresponding to each second subclass; The par calibration parameter file corresponding to each of the second subclasses is used as the second calibration parameter file for each vehicle model.
5. The method according to claim 1, characterized in that, The step of generating an updated executable file based on the first calibration parameter file in the target vehicle folder, the second calibration parameter file in the target parameter library, and the original executable file includes: The original executable file is parsed to obtain the original autonomous driving algorithm program and the original autonomous driving algorithm parameters. Replace the original autonomous driving algorithm parameters with the first calibration parameter file in the target vehicle folder and the second calibration parameter file in the target parameter library to obtain new autonomous driving algorithm parameters; The original autonomous driving algorithm program and the new autonomous driving algorithm parameters are merged to generate the updated executable file.
6. The method according to claim 5, characterized in that, After the step of sending the updated executable file to the target vehicle model, the vehicle is configured as follows: The vehicle's MCU chip parses the updated executable file to obtain the original autonomous driving algorithm program, the first calibration parameter file in the target vehicle folder, and the second calibration parameter file in the target parameter library; Write the original autonomous driving algorithm program into the vehicle's RAM; Write the first calibration parameter file in the target vehicle model folder into the vehicle's NVM, and send the second calibration parameter file in the target parameter library to the vehicle's SOC chip; The vehicle's SOC chip writes the second calibration parameter file from the target parameter library into the UFS via the PDM middleware.
7. The method according to claim 6, characterized in that, The vehicle is also configured to: When a driver domain control restart is detected in the vehicle, the first calibration parameter file in the target model folder is obtained from the NVM through the vehicle's cabin diagnostic tool, and the second calibration parameter file in the target parameter library is obtained from the UFS. If the cabin diagnostic instrument detects that the calibration parameters of the first calibration parameter file in the target vehicle folder and the second calibration parameter file in the target parameter library are correct, the original autonomous driving algorithm program is obtained from the RAM through the driving domain control, and the original autonomous driving algorithm program is driven to execute the first calibration parameter file in the target vehicle folder and the second calibration parameter file in the target parameter library.
8. An autonomous driving algorithm parameter update device, characterized in that, The device includes: The target vehicle folder determination module is used to respond to a parameter update request for a target vehicle, determine the target vehicle folder corresponding to the target vehicle identifier from multiple vehicle folders, and determine the target parameter library corresponding to the target vehicle identifier from multiple parameter libraries; the parameter update request includes the target vehicle identifier; wherein, the first calibration parameter file in each of the multiple vehicle folders is obtained based on the SOC domain parameters in the autonomous driving algorithm parameters of each vehicle; the second calibration parameter file in each of the multiple parameter libraries is obtained based on the MCU domain parameters in the autonomous driving algorithm parameters of each vehicle. The updated executable file generation module is used to generate an updated executable file based on the first calibration parameter file in the target vehicle folder, the second calibration parameter file in the target parameter library, and the original executable file; The updated executable file sending module is used to send the updated executable file to the target vehicle model; the vehicle is used to update the autonomous driving algorithm parameters according to the updated executable file.
9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.
11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.