Search

CN-115855059-B - Verification method, device, equipment, medium and product of lane-level guidance algorithm

CN115855059BCN 115855059 BCN115855059 BCN 115855059BCN-115855059-B

Abstract

The embodiment of the disclosure relates to a verification method, a device, equipment, a medium and a product of a lane-level guidance algorithm, wherein the obtained first starting point position, first end point position and guidance use case are input into a guidance engine, so that the guidance engine generates a first guidance result based on a first lane-level guidance algorithm of a reference version, generates a second guidance result based on a second lane-level guidance algorithm of an iterative version, and can quickly and accurately judge the difference between the second lane-level guidance algorithm and the first lane-level guidance algorithm on an output result by comparing the second guidance result with the first guidance result, thereby taking the difference as a verification result, accurately judging whether the iterated second lane-level guidance algorithm achieves an expected effect or not, and further realizing quick and effective verification of the lane-level guidance algorithm.

Inventors

  • CHEN ZHICHENG

Assignees

  • 阿里巴巴（中国）有限公司

Dates

Publication Date
20260512
Application Date
20221129

Claims (12)

  1. 1. A method of validating a lane-level guidance algorithm, comprising: Acquiring a first starting point position and a first ending point position; generating a second planned route based on the first starting point position and the first ending point position; Determining a target road scene covered by the high-precision road network data in the second planning route based on the high-precision road network data; Acquiring a guiding case of the target road scene from a preset full scene guiding case database, wherein the guiding case is used for enabling a guiding engine to clearly determine how to guide; Inputting the first starting point position, the first ending point position and the guiding use case into the guiding engine so that the guiding engine generates a first guiding result based on a first lane-level guiding algorithm of a reference version and generates a second guiding result based on a second lane-level guiding algorithm of an iterative version; Comparing the first guiding result with the second guiding result to obtain a first difference between the second guiding result and the first guiding result, and taking the first difference as a first verification result for the second road-level guiding algorithm.
  2. 2. The method of claim 1, wherein prior to the acquiring the first starting point position and the first ending point position, the method further comprises: acquiring log information of a vehicle, wherein the log information comprises a second starting point position and a second ending point position of historical travel; Generating a first planning route according to the second starting point position and the second ending point position; determining a road scene covered by the high-precision road network data in the first planned route based on the high-precision road network data; And adding the guide use cases of the road scene used in the guide test process into a preset full scene guide use case database to serve as the guide use cases of the road scene.
  3. 3. The method of claim 1, wherein the comparing the first guidance result and the second guidance result to obtain a first difference between the second guidance result and the first guidance result comprises: comparing the voice broadcasting contents included in the first guiding result and the second guiding result to obtain the difference of the voice broadcasting contents; And/or Comparing the information of the guide surfaces included in the first guide result and the second guide result to obtain a difference of the guide surfaces; Wherein the guide surface is a lane surface for guiding a lane on which the vehicle is traveling.
  4. 4. The method of claim 1, wherein the inputting the first start position, the first end position, and the guidance use case into a guidance engine such that the guidance engine generates a first guidance result based on a reference version of a first lane-level guidance algorithm and a second guidance result based on an iterative version of a second lane-level guidance algorithm, the method further comprising: Acquiring first guide surface abnormality information and second guide surface abnormality information detected by the guide engine; Comparing the first guide surface abnormal information with the second guide surface abnormal information to obtain a second difference, and taking the second difference as a second verification result aiming at the second road-level guide algorithm; The first guiding surface abnormal information refers to guiding surface abnormal information generated by the first lane-level guiding algorithm, and the second guiding surface abnormal information refers to guiding surface abnormal information generated by the second lane-level guiding algorithm; The first guide surface abnormality information and the second guide surface abnormality information at least comprise information of abnormal conditions of guide surface interruption and partial data missing of the guide surface, wherein the partial data is not interrupted.
  5. 5. The method of claim 1 or 4, wherein the inputting the first start position, the first end position, and the guidance use case into a guidance engine such that the guidance engine generates a first guidance result based on a reference version of a first lane-level guidance algorithm and generates a second guidance result based on an iterative version of a second lane-level guidance algorithm, the method further comprising: Acquiring first guide surface vector data obtained by the guide engine based on the first lane-level guide algorithm and second guide surface vector data obtained by the guide engine based on the second lane-level guide algorithm; Generating a first guide surface based on the first guide surface vector data, and generating a second guide surface based on the second guide surface vector data; determining abnormality information of the first guide surface and abnormality information of the second guide surface based on high-precision road network data; Comparing the abnormal information of the first guide surface with the abnormal information of the second guide surface to obtain a third difference, and taking the third difference as a third verification result of the second road-level guiding algorithm.
  6. 6. The method of claim 5, wherein the inputting the first start position, the first end position, and the guidance use case into a guidance engine such that the guidance engine generates a first guidance result based on a reference version of a first lane-level guidance algorithm and a second guidance result based on an iterative version of a second lane-level guidance algorithm, the method further comprising: Acquiring a first guide surface image rendered by the guide engine based on the first lane-level guide algorithm and a second guide surface image rendered based on the second lane-level guide algorithm; And comparing the guide surfaces determined by the first lane-level guide algorithm and the second lane-level guide algorithm based on the first guide surface image and the second guide surface image to obtain a fourth difference, and taking the fourth difference as a fourth verification result aiming at the second lane-level guide algorithm.
  7. 7. The method of claim 6, wherein comparing the determined guide surfaces of the first and second lane-level guidance algorithms based on the first and second guide surface images to obtain a fourth difference comprises: acquiring gray values of guide surfaces contained in the first guide surface image and the second guide surface image; And comparing the parts of the second guide surface image and the first guide surface image, wherein the gray value of the parts is lower than a preset threshold value, so as to obtain a fourth difference.
  8. 8. The method of any one of claims 1, 4, 6, or 7, wherein the method further comprises: And displaying the verification result of the second lane-level guidance algorithm.
  9. 9. A verification apparatus of a lane-level guidance algorithm, comprising: The first acquisition module is used for acquiring a first starting point position and a first end point position; the method comprises the steps of generating a first planning route based on a first starting point position and a first ending point position, determining a target road scene covered by high-precision road network data in the first planning route based on the high-precision road network data, and acquiring a guiding case of the target road scene from a preset full-scene guiding case database, wherein the guiding case is used for enabling a guiding engine to definitely guide how; The input module is used for inputting the first starting point position, the first ending point position and the guiding use case into the guiding engine so that the guiding engine generates a first guiding result based on a first lane-level guiding algorithm of a reference version and generates a second guiding result based on a second lane-level guiding algorithm of an iterative version; The first comparison module is used for comparing the first guiding result with the second guiding result to obtain a first difference between the second guiding result and the first guiding result, and the first difference is used as a first verification result for the second road-level guiding algorithm.
  10. 10. A computer device comprising a memory and a processor, wherein the memory has stored therein a computer program which, when executed by the processor, implements the method of any of claims 1-8.
  11. 11. A computer readable storage medium, wherein the storage medium has stored therein a computer program which, when executed, implements the method of any of claims 1-8.
  12. 12. A computer program product, wherein the program product is stored in a storage medium, which when run implements the method of any of claims 1-8.

Description

Verification method, device, equipment, medium and product of lane-level guidance algorithm Technical Field The embodiment of the disclosure relates to the technical field of navigation, in particular to a verification method, a device, equipment, a medium and a product of a lane-level guiding algorithm. Background The lane-level guidance algorithm is an algorithm for providing lane guidance for a user, and can clearly inform the user of lane selection and lane change so as to avoid the problems of temporary lane change failure and the like. At present, lane-level guidance algorithms are applied to relatively simple scenes such as highways and urban highways. However, with the development of the traffic and the demands of a large number of users, the lane-level guidance traffic needs to be spread to the urban common road, and then more complex guidance scenes and more complex lane-level guidance algorithms, especially the lane-level guidance algorithms are updated and iterated continuously, and each time the lane-level guidance algorithms are updated and iterated, so how to verify the more and more complex lane-level guidance algorithms is a technical problem to be solved. Disclosure of Invention In order to solve the technical problems, the embodiments of the present disclosure provide a method, an apparatus, a device, a medium, and a product for verifying a lane-level guidance algorithm. A first aspect of the disclosed embodiments provides a verification method of a lane-level guidance algorithm, which includes acquiring a first starting point position, a first end point position and a guidance use case, inputting the first starting point position, the first end point position and the guidance use case into a guidance engine, enabling the guidance engine to generate a first guidance result based on a first lane-level guidance algorithm of a reference version and generate a second guidance result based on a second lane-level guidance algorithm of an iterative version, comparing the first guidance result and the second guidance result to obtain a first difference between the second guidance result and the first guidance result, and taking the first difference as a first verification result for the second lane-level guidance algorithm. A second aspect of an embodiment of the present disclosure provides a verification apparatus of a lane-level guidance algorithm, the apparatus comprising: The first acquisition module is used for acquiring a first starting point position, a first end point position and a guiding use case; The input module is used for inputting the first starting point position, the first ending point position and the guiding use case into the guiding engine so that the guiding engine generates a first guiding result based on a first lane-level guiding algorithm of a reference version and generates a second guiding result based on a second lane-level guiding algorithm of an iterative version; the first comparison module is used for comparing the first guiding result and the second guiding result to obtain a first difference between the second guiding result and the first guiding result, and the first difference is used as a first verification result for the second road-level guiding algorithm. A third aspect of the disclosed embodiments provides a computer device comprising a memory and a processor, wherein the memory stores a computer program which, when executed by the processor, performs the method of the first aspect. A fourth aspect of embodiments of the present disclosure provides a computer program product stored on a storage medium, which when executed, enables the method of the first aspect described above to be carried out. A fifth aspect of the disclosed embodiments provides a computer readable storage medium storing a computer program which, when executed, performs the method of the first aspect. Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages: According to the embodiment of the disclosure, the acquired first starting point position, first end point position and guiding use case are input into the guiding engine, so that the guiding engine generates a first guiding result based on a first lane-level guiding algorithm of a reference version, generates a second guiding result based on a second lane-level guiding algorithm of an iterative version, and can quickly and accurately judge the difference between the second lane-level guiding algorithm and the first lane-level guiding algorithm on an output result by comparing the second guiding result with the first guiding result, and the difference is used as a verification result, so that whether the iterative second lane-level guiding algorithm achieves an expected improvement effect can be accurately judged, and quick and effective verification of the lane-level guiding algorithm is realized. Drawings The accompanying drawings, which are incorporated in and cons