A method for validating map data for a navigation of a motor vehicle by an electronic computer device, a corresponding computer programm product

Abstract

The invention relates to a method for validating map data for a navigation device of a motor vehicle by an electronic computing device (10), comprising the steps of: providing a plurality of test case

Description

[0001] The present invention relates to the field of automobiles. More specifically, the present invention relates to a method for validating map data for a navigation device of a motor vehicle by an electronic computing device. Furthermore, the present invention relates to a corresponding computer program product, a corresponding non-transitory computer readable storage medium as well as to a corresponding electronic computing device. BACKGROUND INFORMATION

[0002] Map data aims to model a virtual reality of the real world with all its corner cases. On the other hand, map data must follow a fixed inherent structure and is provided on a defined interface, such that it can be processed by an ADAS / AD or similar system. The task of map validation ensures that the map specification models the real world with necessary fidelity, that the map data is compatible with the specification, and that it can be processed by ADAS-system. It needs to account for the huge variety on the one hand but also needs to find those map elements or patterns, which do not conform to the specification. Aiming to derive a set of rules manually is very laborious and error-prone. Also it cannot cover more complex patterns in the underlying data. An intelligent approach is needed that can automatically derive those patterns from the underlying structure of the data. On the other hand, a purely automated approach will not always derive correct rules.

[0003] Existing map validation frameworks usually consist of human-defined tests that assert a specific underlying structure and acceptable values in the data. This is a laborious task and covers patterns with very limited complexity only. In business logic, data sets usually have constraints attached. Those however are manually defined and cover patterns with very limited complexity only. SUMMARY OF THE INVENTION

[0004] It is an object of the invention to provide a method, a corresponding computer program product, a corresponding non-transitory computer-readable storage medium, as well as a corresponding electronic computing device, by which an improved validation of map data for a navigation device can be realized.

[0005] This object is solved by a method, a corresponding computer program product, a corresponding non-transitory computer-readable storage medium, as well as a corresponding electronic computing device according to the independent claims. Advantageous embodiments a presented in the dependent claims.

[0006] One aspect of the invention relates to a method for validating map data for a navigation device of a motor vehicle by an electronic computing device. A plurality of test case frameworks is provided for the map data by the electronic computing device. The test case frameworks are applied on specific map data for validation by the electronic computing device. A confidence value for the validation is determined depending on the applied test case frameworks by the electronic computing device. Generating the at least one test case framework for validating by the electronic computing device and providing the test frameworks by an artificial intelligence of the electronic computing device is performed.

[0007] Therefore the electronic computing device can automatically generate a big set of proposal test cases that match the majority of underlying data. This yields a big test coverage. The person / human only evaluates non-conformities to give quick feedback and improve the quality of the test cases. The person may also select a sample of conformities to find potential gaps in the existing test logic. The electronic computing device may improve upon human input in an active-learning setup. The data-driven approach scales with available data.

[0008] In another embodiment the artificial intelligence generates test case frameworks depending on historical data of test case frameworks.

[0009] In another embodiment the artificial intelligence is trained depending on labeled map data and / or existing test case frameworks.

[0010] In another embodiment the artificial intelligence uses self-supervised learning for generating test case frameworks.

[0011] In another embodiment just outliers of the plurality of test case frameworks are provided for the person.

[0012] According to an embodiment the artificial intelligence is learned depending on an input of a person.

[0013] In particular, the provided method is a computer-implemented method. Therefore, another aspect of the invention relates to a computer program product comprising program code means for performing a method according to the preceding aspect.

[0014] A still further aspect of the invention relates to a non-transitory computer-readable storage medium comprising at least the computer program product according to the preceding aspect.

[0015] Furthermore, the present invention relates to an electronic computing device for validating map data for a navigation device of a motor vehicle, wherein the electronic computing device is configured for performing a method according to the preceding aspect. In particular the method is performed by the electronic computing device.

[0016] Advantageous forms of the method are to be regarded as advantageous forms of the computer program product, the non-transitory computer-readable storage medium, as well as the electronic computing device. Therefore, the electronic computing device comprises means for performing the method.

[0017] An artificial neural network / artificial intelligence can be understood as a software code or a compilation of several software code components, wherein the software code may comprise several software modules for different functions, for example one or more encoder modules and one or more decoder modules.

[0018] An artificial neural network can be understood as a non-linear model or algorithm that maps an input to an output, wherein the input is given by an input feature vector or an input sequence and the output may be an output category for a classification task or a predicted sequence.

[0019] For example, the artificial neural network may be provided in a computer-readable way, for example, stored on a storage medium of the vehicle, in particular of the at least one computing unit.

[0020] The neural network comprises several modules including the encoder module and the at least one decoder module. These modules may be understood as software modules or respective parts of the neural network. A software module may be understood as software code functionally connected and combined to a unit. A software module may comprise or implement several processing steps and / or data structures.

[0021] The modules may, in particular, represent neural networks or sub-networks themselves. If not stated otherwise, a module of the neural network may be understood as a trainable and, in particular, trained module of the neural network. For example, the neural network and thus all of its trainable modules may be trained in an end-to-end fashion before the method is carried out. However, in other implementations, different modules may be trained or pre-trained individually. In other words, the method according to the invention corresponds to a deployment phase of the neural network.

[0022] A computing unit / electronic computing device may in particular be understood as a data processing device, which comprises processing circuitry. The computing unit can therefore in particular process data to perform computing operations. This may also include operations to perform indexed accesses to a data structure, for example a look-up table, LUT.

[0023] In particular, the computing unit may include one or more computers, one or more microcontrollers, and / or one or more integrated circuits, for example, one or more application-specific integrated circuits, ASIC, one or more field-programmable gate arrays, FPGA, and / or one or more systems on a chip, SoC. The computing unit may also include one or more processors, for example one or more microprocessors, one or more central processing units, CPU, one or more graphics processing units, GPU, and / or one or more signal processors, in particular one or more digital signal processors, DSP. The computing unit may also include a physical or a virtual cluster of computers or other of said units.

[0024] In various embodiments, the computing unit includes one or more hardware and / or software interfaces and / or one or more memory units.

[0025] A memory unit may be implemented as a volatile data memory, for example a dynamic random access memory, DRAM, or a static random access memory, SRAM, or as a non-volatile data memory, for example a read-only memory, ROM, a programmable read-only memory, PROM, an erasable programmable read-only memory, EPROM, an electrically erasable programmable read-only memory, EEPROM, a flash memory or flash EEPROM, a ferroelectric random access memory, FRAM, a magnetoresistive random access memory, MRAM, or a phase-change random access memory, PCRAM.

[0026] Further advantages, features, and details of the invention derive from the following description of preferred embodiment as well as from the drawing. The features and feature combinations previously mentioned in the description as well as the features and feature combinations mentioned in the following description of the figure and / or shown in the figure alone can be employed not only in the respectively indicated combination but also in any other combination or taken alone without leaving the scope of the invention. BRIEF DESCRIPTION OF THE DRAWING

[0027] The novel features and characteristic of the disclosure are set forth in the appended claims. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and together with the description, serve to explain the disclosed principles. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and / or methods in accordance with embodiments of the present subject matter are now described below, by way of example only, and with reference to the accompanying figures.

[0028] The drawing show in:

[0029] Fig. 1 a schematic flow chart according to an embodiment of the invention

[0030] In the figure the same elements or elements having the same function are indicated by the same reference signs. DETAILED DESCRIPTION

[0031] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration". Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0032] While the disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the drawing and will be described in detail below. It should be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternatives falling within the scope of the disclosure.

[0033] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion so that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus preceded by “comprises” or “comprise” does not or do not, without more constraints, preclude the existence of other elements or additional elements in the system or method.

[0034] In the following detailed description of the embodiment of the disclosure, reference is made to the accompanying drawing that forms part hereof, and in which is shown by way of illustration a specific embodiment in which the disclosure may be practiced. This embodiment is described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

[0035] Fig. 1 shows a schematic flow chart according to an embodiment of the method. In particular, an electronic computing device 10 is shown, which is configured for performing the method.

[0036] Fig. 1 shows a method for validating map data for a navigation device of a motor vehicle by the electronic computing device 10. In a first step S1 a plurality of test case frameworks for map data is provided by the electronic computing device 10. In a second step S2 the test case frameworks are applied on specific map data for validation by the electronic computing device 10. In a third step S3 a confidence value for the validation is determined depending on the applied test case frameworks by the electronic computing device 10. In a fourth step S4 the at least one test case framework is provided for a person for validating depending on the confidence value by the electronic computing device 10.

[0037] In particular Fig. 1 shows further an artificial intelligence 12. In particular the test case frameworks are provided by the artificial intelligence 12 of the electronic computing device 10. The artificial intelligence 12 generates test case frameworks depending on historical data of historical test case frameworks. Furthermore, the artificial intelligence 12 may be trained depending on labeled map data and / or existing test case frameworks. In another embodiment the artificial intelligence 12 uses self-supervised learning for generating test case frameworks.

[0038] In another embodiment just outliers of the plurality of test case frameworks are provided for the person.

[0039] In particular, Fig. 1 shows the artificial-intelligence based test case generation. Modular test case frameworks are built where test cases work as plugins, which makes the framework easily extendable. The artificial intelligence 12 may be trained with labeled map data and existing test logic / test cases to generate new permutations. The artificial intelligence 12 may calculate its confidence levels, to flag for human review of specific permutations. Self-supervised learning as a data-driven approach is used to generate test cases that are plausible for the existing labeled data, for example deriving rules that apply to the majority of the test data. The generated test cases are used to validate map content, for example which may work as an outlier detection, for example what map elements don’t match the general pattern.

[0040] The test case generation is followed by a human in the loop edge-case identification. The person may take advantage of the established test cases. In particular applying the test cases in an automated way which raise the non-conformities in particular seek out the outliers in the map data. The person may review / evaluate the validity / applicability of the generated test cases, either by inspecting the algorithm or by inspecting the non-conformities for example, if the non-conformities are true positive and the test case found valid outlies, or if they are false-positives and the test case did not correctly derive the underlying rules, as well as a sample of conformities, for example the determination if they are false-negatives, in the aspect of such cases may be complicated and should be identified as outliers. Parameters, thresholds and test cases may be adjusted accordingly, for example modifying the valid range, flag for human evaluation of unique cases.

[0041] In particular the method combines the strength of machine, in particular software, and human flexibility to complement each other. The machine is assigned to perform tedious computations, in particular deriving underlying rules from data, permutations, validation and monitoring. The person may review the provided “common sense” feedback to train / steer the artificial intelligence. A sparse guidance is provided by having the artificial intelligence 12 proposes the artificial intelligence test cases that depict the data and the person may decide about usefulness by evaluating non-conformities with a simple binary input. Reference signs 10 12 S1 -S4 electronic computing device artificial intelligence steps of the method

Claims

1. A method for validating map data for a navigation device of a motor vehicle by an electronic computing device (10), comprising the steps of:- providing a plurality of test case frameworks for the map data by the electronic computing device (10); (S1)- applying the test case frameworks on map data for validation by the electronic computing device (10); (S2)- determining a confidence value for the validation depending on the applied test case frameworks by the electronic computing device (10); (S3)- generating the at least one test case framework for validating by the electronic computing device (10); and- providing the test frameworks by an artificial intelligence (12) of the electronic computing device (10).

2. The method according to claim 1, characterized in thatthe artificial intelligence (12) generates test case frameworks depending on historical data of historical test case frameworks.

3. The method according to any one of claims 1 or 2, characterized in thatthe artificial intelligence (12) is trained depending on labeled map data and / or existing test case frameworks.

4. The method according to any one of claims 1 or 3, characterized in thatthe artificial intelligence (12) uses self-supervised learning for generating test case frameworks.

5. The method according to any one of claims 1 or 4, characterized in thatoutliers of the plurality of test case frameworks are provided for a person.

6. The method according to any one of claims 1 or 5, characterized in thatthe artificial intelligence (12) is learned depending on an input of a person.

7. A computer program product comprising program code means for performing a method according to any one of claims 1 to 6.

8. A non-transitory computer-readable storage medium comprising at least the computer program product according to claim 7.

9. An electronic computing device (10) for validating map data for a navigation device of a motor vehicle, wherein the electronic computing device (10) is configured for performing a method according to any one of claims 1 to 6.12

Images