Computer-implemented method and device for designing a data collection campaign for a motor vehicle

Abstract

The invention relates to a computer-implemented method for designing a data collection campaign for a motor vehicle, the method comprising: determining a maximum storage capacity of a ring memory of a motor vehicle; determining information which is needed to achieve a predefined objective of the data collection campaign; determining data which are present in the motor vehicle; selecting the data to be stored in the ring memory by means of the data collection campaign from the data present in the motor vehicle based on the maximum storage capacity of the ring memory and the information needed to achieve the predefined objective of the data collection campaign; and defining the data collection campaign based on the selected data to be stored in the ring memory by means of the data collection campaign.

Description

[0001] COMPUTER-IMPLEMENTED METHOD AND DEVICE FOR DESIGNING A DATA COLLECTION CAMPAIGN FOR A MOTOR VEHICLE

[0002] The present disclosure relates to a computer-implemented method for designing a data collection campaign for a motor vehicle. Additionally or alternatively, a data processing device is provided which is configured to at least partially carry out the method. Additionally or alternatively, an (optionally automated) motor vehicle with the data processing device is provided. Additionally or alternatively, a computer program is provided which comprises instructions which, when executed by a computer, cause the computer to at least partially carry out the method. Additionally or alternatively, a computer-readable medium is provided which comprises instructions which, when executed by a computer, cause the computer to at least partially carry out the method.

[0003] US2021271259A1 describes systems and methods for obtaining training data. An example method includes receiving sensor data and applying a neural network to the sensor data. A trigger classifier is applied to an intermediate result of the neural network to determine a classifier score for the sensor data. Based at least in part on the classifier score, a decision is made as to whether at least a portion of the sensor data should be transmitted over a computer network. If the decision is positive, the sensor data is transmitted and used to generate training data.

[0004] Such systems and methods can be used in motor vehicles as a so-called data collection mechanism to provide a motor vehicle manufacturer with sensor data for the further development of partially automated or fully automated driving functions.

[0005] This means that such a data collection mechanism can be implemented as software in the motor vehicle. The purpose of data collection is not only to read sensor and function information directly from or in the motor vehicle, but also to store this information wirelessly, particularly via the mobile network, in a backend system of a motor vehicle manufacturer so that a functional development team at the motor vehicle manufacturer can use the collected data.

[0006] A data collection task is triggered by a campaign that can be rolled out over-the-air or wirelessly to the vehicle in the field. These campaigns vary in terms of the required signals. Differentiating features include, among others, the number of required signals, the recording duration of the signals, the signal resolution, and / or the sampling of the signals.

[0007] Since the signals are sent to the backend with a time delay, a ring buffer must be implemented in the vehicle, which, however, cannot be expanded indefinitely, ie it has a maximum size due to hardware design.

[0008] Against the background of this prior art, the object of the present invention is to provide a device and a method each suitable for overcoming at least the above-mentioned disadvantages of the prior art. In particular, a solution is to be provided to ensure optimal utilization of the ring buffer for each campaign.

[0009] The problem is solved by the features of the independent claim. The subclaims contain preferred developments of the invention.

[0010] The task is then solved by a computer-implemented method for designing a data collection campaign for a motor vehicle.

[0011] A computer-implemented method can be understood as a method that is at least partially carried out by a data processing device or a computer.

[0012] The method includes determining the maximum storage capacity of a motor vehicle's ring buffer and determining the information required to achieve a predefined goal of the data collection campaign. The maximum storage capacity of the ring buffer can be understood as the maximum amount of data that an empty ring buffer can store. This means that the maximum storage capacity is reached when new data added to or to be stored in the ring buffer must overwrite other data already stored in the ring buffer.

[0013] The predefined goal can be determined, for example, based on user input. This means that a user, such as a developer in a vehicle manufacturer's development department, can specify, for example, via a programming interface (also called an application programming interface or application programming interface, API), which driver assistance function should be tested for functionality with the data collection campaign.

[0014] The method further comprises determining data present in the motor vehicle.

[0015] The data present in a motor vehicle can be understood as a sum of information present in the vehicle in the form of signals that can be accessed via an on-board network or used as variables within control units for program execution. This can, for example, be the output of entire driver assistance systems and / or individual sensors.

[0016] The method further comprises selecting the data to be stored in the ring buffer by means of the data collection campaign from the data present in the motor vehicle based on the maximum storage capacity of the ring buffer and the information required to achieve the predefined goal of the data collection campaign.

[0017] Based on the user input described above, the procedure can be used to define, e.g., based on expert knowledge or predefined data collection campaigns, which data or signals should be collected from the entire volume of available data. For example, if the functionality of the driver assistance function specified by the user is to be tested using the data collected by the data collection campaign, the procedure can be used to determine which data is received and output by the driver assistance function. This data can then be selected as the data to be collected.

[0018] Finally, the method comprises defining the data collection campaign based on the selected data to be stored in the ring buffer by means of the data collection campaign.

[0019] The data collection campaign is defined based on the previously selected data and is incorporated into the data collection campaign, which itself represents an algorithm or software component, in the form of rules. The data collection campaign can be specified, for example, using a so-called LUA script (a lightweight, high-level, multi-paradigm programming language developed primarily for embedded applications). The data to be collected can be defined in these scripts.

[0020] The method offers the advantage that data collection campaigns can be defined that make the best possible use of the storage capacity of a ring buffer without the data collection campaign having to be known at the time of development of the vehicle.

[0021] Possible further developments of the procedure described above are explained in detail below.

[0022] The data can be selected so that the maximum storage capacity of the ring buffer is not exceeded. To select the data to be stored in the ring buffer using the data collection campaign from the data available in the vehicle, based on the maximum storage capacity of the ring buffer and the information required to achieve the predefined goal of the data collection campaign, it is possible to determine which internal signals of the vehicle and / or the on-board network need to be tapped, a recording duration of the required signals, a signal resolution of the required signals, and / or sampling of the required signals.

[0023] This means that in the scripts mentioned above, not only the data or signals that are required can be defined, but also which specific signals are to be tapped internally and from the on-board network, and in what form. For example, it may be the case that the signals only have to be recorded or collected over a predetermined period of time if a predetermined condition is met (e.g. the driver assistance function to be tested issues an error). Furthermore, it may be sufficient to only collect every Xth frame of a signal, or to scale down the collected frames to reduce the storage space required for each frame. The method therefore offers a solution for how the previously mentioned attributes are to be assigned so that the ring buffer capacity is not exceeded.

[0024] The method may comprise sending the defined data collection campaign, in particular by means of wireless communication, from a data processing device that has defined the data collection campaign to the motor vehicle.

[0025] The data processing device that defined the data collection campaign can be, for example, a backend of the motor vehicle manufacturer. The campaigns can be distributed to a customer and / or development fleet, for example, using a so-called CDC (crowd data collection, CDC) mechanism. This means that the motor vehicle can be part of a vehicle fleet to which the defined data collection campaign is distributed. The method can include storing data in the ring buffer of the motor vehicle according to the defined data collection campaign, controlled by a data processing device of the motor vehicle.

[0026] The method may include transmitting, in particular via wireless communication, the data stored in the ring buffer of the motor vehicle from the motor vehicle to a backend. The backend may also be referred to as a cloud and may comprise a data processing device operated by the motor vehicle manufacturer.

[0027] Furthermore, a system for data processing is described, comprising means for carrying out the computer-implemented method described above.

[0028] The system may be a distributed system comprising a data processing device operated, for example, by the motor vehicle manufacturer and, if necessary, a data processing device connected thereto (in particular wirelessly).

[0029] The latter data processing device can be part of a motor vehicle. The data processing device can be, for example, a data logger and / or an electronic control unit (ECU). The data processing device can be an intelligent processor-controlled unit that can communicate with other modules, for example, via a central gateway (CGW), and can form the vehicle's on-board network, for example, via fieldbuses such as the CAN bus, LIN bus, MOST bus, and FlexRay, or via automotive Ethernet, e.g., together with telematics control units.

[0030] It is conceivable that the data processing device comprises a storage unit in which signals from the vehicle electrical system and internal signals of the motor vehicle are stored according to the data collection campaign defined by the above method. It is conceivable that the data processing device sends the collected data to the data processing device operated by the motor vehicle manufacturer. The above description with reference to the method also applies analogously to the data processing system, and vice versa.

[0031] Furthermore, a motor vehicle comprising a data processing device and a ring buffer is provided, wherein the data processing device is designed to control storage of data in the ring buffer of the motor vehicle according to the data collection campaign defined by means of the computer-implemented method described above.

[0032] The motor vehicle may be a passenger car, in particular an automobile. The motor vehicle may be an automated motor vehicle designed to at least partially and / or completely assume longitudinal and / or lateral guidance during automated driving of the motor vehicle. Automated driving may be implemented in such a way that the motor vehicle's movement is (largely) autonomous.

[0033] The motor vehicle may be a motor vehicle with autonomy level 0, i.e. the driver assumes the dynamic driving task, even if supporting systems (e.g. ABS or ESP) are present.

[0034] The motor vehicle may be a Level 1 autonomy motor vehicle, i.e. it may have certain driver assistance systems that support the driver in operating the vehicle, such as adaptive cruise control (ACC).

[0035] The motor vehicle may be a motor vehicle of autonomy level 2, i.e. be so partially automated that functions such as automatic parking, lane keeping or lateral guidance, general longitudinal guidance, acceleration and / or braking are taken over by driver assistance systems.

[0036] The motor vehicle can be a Level 3 autonomy vehicle, meaning it is so conditionally automated that the driver does not need to continuously monitor the vehicle system. The vehicle performs functions such as activating the turn signal, changing lanes, and / or keeping in lane independently. The driver can attend to other tasks but will be prompted by the system to take over control within a pre-warning period if necessary.

[0037] The motor vehicle can be a Level 4 autonomy vehicle, meaning it is so highly automated that the vehicle system permanently assumes control of the vehicle. If the system can no longer handle the driving tasks, the driver can be requested to take over.

[0038] The motor vehicle can be a Level 5 autonomy vehicle, meaning it is so fully automated that the driver is not required to perform the driving task. No human intervention is required other than setting the destination and starting the system.

[0039] What has been described above with reference to the method and the data processing device also applies analogously to the motor vehicle and vice versa.

[0040] Furthermore, a computer program can be provided. The computer program is characterized in that it comprises instructions which, when executed by a computer, cause the computer to at least partially execute the method described above.

[0041] It is conceivable that the computer program comprises, in particular exclusively, instructions which, when the program is executed by a computer, cause the computer to carry out a data collection campaign defined by means of the method described above.

[0042] A program code of the computer program can be in any code, in particular in a code that is suitable for controlling motor vehicles, e.g. comprising LUA scripts.

[0043] Furthermore, a computer-readable medium, in particular a computer-readable storage medium, is provided. The computer-readable medium is characterized in that it comprises instructions that, when the program is executed by a computer, cause the computer to at least partially execute the method described above.

[0044] It is conceivable that the computer-readable medium comprises, in particular exclusively, instructions which, when executed by a computer, cause the computer to carry out a data collection campaign defined by means of the method described above.

[0045] This means that a computer-readable medium can be provided that contains a computer program as defined above. The computer-readable medium can be any digital data storage device, such as a USB flash drive, a hard disk, a CD-ROM, an SD card, or an SSD card.

[0046] The computer program does not necessarily have to be stored on such a computer-readable storage medium in order to be made available to the motor vehicle, but can also be obtained via the Internet or otherwise externally.

[0047] Furthermore, the present disclosure relates to a use of a data collection campaign in a motor vehicle defined by the method described above.

[0048] What has been described above with reference to the method, the data processing device and the motor vehicle also applies analogously to the computer program, the computer-readable medium and the use, and vice versa.

[0049] An embodiment is described below with reference to Figures 1 and 2.

[0050] Fig. 1 schematically shows a data processing system comprising means for executing a computer-implemented method for designing a data collection campaign for a motor vehicle, and Fig. 2 schematically shows a flow chart of the computer-implemented method for designing the data collection campaign for the motor vehicle.

[0051] The distributed data processing system 5 shown in Figure 1 comprises a data processing device 1, presently located in the cloud, and a motor vehicle 2 having a data processing device 3 and a ring buffer 4. The data processing system 5 is configured to execute the computer-implemented method for designing a data collection campaign for the motor vehicle 2, comprising collecting the data with the motor vehicle 2. This is described in detail below, also with reference to Figure 2.

[0052] In a first step S1 of the method, a maximum storage capacity of the ring buffer 4 of the motor vehicle 2 in the cloud 1 is determined. It is conceivable that this information is stored in a database of the cloud 1 and / or retrieved by the motor vehicle 2.

[0053] In a second step S2 of the method, information required to achieve a predefined goal of the data collection campaign is determined in Cloud 1.

[0054] In a third step S3 of the method, data present in the motor vehicle 2 is determined in the cloud 1. It is also conceivable that this information is stored in a database in the cloud 1 and / or retrieved by the motor vehicle 2.

[0055] In a fourth step S4 of the method, the data to be stored in the ring buffer 4 by means of the data collection campaign is selected in the cloud 1 from the data available in the motor vehicle 2 based on the maximum storage capacity of the ring buffer 4 and the information required to achieve the predefined goal of the data collection campaign. The data is selected such that the maximum storage capacity of the ring buffer 4 is not exceeded. In particular, this involves determining which signals from the vehicle electrical system of the motor vehicle 2 need to be tapped, a recording duration of the required signals, a signal resolution of the required signals, and / or sampling of the required signals.

[0056] In a fifth step S5 of the method, the data collection campaign is defined in the cloud 1 based on the selected data to be stored in the ring buffer 4 by means of the data collection campaign.

[0057] In a sixth step S6 of the method, the defined data collection campaign is sent, in particular by means of wireless communication, from the cloud 1 that defined the data collection campaign to the motor vehicle 2.

[0058] In a seventh step S7 of the method, data is stored in the ring buffer 4 of the motor vehicle according to the defined data collection campaign controlled by the data processing device 3 of the motor vehicle 2.

[0059] In an eighth step S8 of the method, the data stored in the ring buffer 4 of the motor vehicle 2 are sent, in particular by means of wireless communication, from the motor vehicle 2 to the cloud 1 under the control of the data processing device 3 of the motor vehicle 2.

[0060] List of reference symbols

[0061] 1 Cloud 2 Motor vehicle

[0062] 3 Data processing device

[0063] 4 ring buffers

[0064] 5 Data processing system S1 - S8 Steps of the computer-implemented procedure

Claims

Patent claims Computer-implemented method for designing a data collection campaign for a motor vehicle (2), wherein the method comprises: - Determining a maximum storage capacity of a motor vehicle ring storage system (2), - Identifying information needed to achieve a predefined goal of the data collection campaign, - Determining data that is present in the motor vehicle (2), Selection of the data to be stored in the ring buffer (4) by means of the data collection campaign from the data present in the motor vehicle (2) based on the maximum storage capacity of the ring buffer (4) and the information required to achieve the predefined goal of the data collection campaign, and - Defining the data collection campaign based on the selected data to be stored in the ring buffer (4) by means of the data collection campaign. Computer-implemented method according to claim 1, wherein the data are selected such that the maximum storage capacity of the ring buffer (4) is not exceeded. Computer-implemented method according to claim 1 or 2, wherein, for the selection of the data to be stored in the ring buffer (4) by means of the data collection campaign, the following is determined from the data present in the motor vehicle (2), based on the maximum storage capacity of the ring buffer (4) and the information required to achieve the predefined goal of the data collection campaign: which signals of the vehicle electrical system must be tapped, a recording duration of the required signals, a signal resolution of the required signals, and / or a sampling of the required signals. A computer-implemented method according to any one of claims 1 to 3, wherein the method comprises sending the defined data collection campaign, in particular by means of wireless communication, from a data processing device (1) that defined the data collection campaign to the motor vehicle (2). A computer-implemented method according to claim 4, wherein the method comprises storing data in the ring buffer (4) of the motor vehicle (2) according to the defined data collection campaign, controlled by a data processing device (3) of the motor vehicle (2). A computer-implemented method according to claim 5, wherein the method comprises sending the data stored in the ring buffer (4) of the motor vehicle (2) from the motor vehicle (2) to a backend, in particular by means of wireless communication. A data processing system comprising means for executing the computer-implemented method according to any one of claims 1 to 6.Motor vehicle (2) comprising a data processing device (3) and a ring buffer (4), wherein the data processing device (3) is configured to control the storage of data in the ring buffer (4) of the motor vehicle (2) in accordance with the data collection campaign defined by the computer-implemented method according to any one of claims 1 to 3. Computer program comprising instructions which, when the program is executed by a computer, cause the computer to execute the method according to any one of claims 1 to 6. A computer-readable medium comprising instructions which, when executed by a computer, cause the computer to execute the method according to any one of claims 1 to 6.

Images