Method and apparatus for localization of position data

Patent metadata

Field	Value
Publication number	US-11501463-B2
Application number	US-202117146996-A
Country	US
Kind code	B2
Filing date	Jan 12, 2021
Priority date	Dec 20, 2018
Publication date	Nov 15, 2022
Grant date	Nov 15, 2022

Abstract

Methods, systems, apparatuses, and computer program products are provided that are configured to perform localization of position data, specifically using a trained localization neural network. In the context of an apparatus, the apparatus is caused to receive observed feature representation data. The apparatus is further configured to transform the observed feature representation data into standardized feature representation data utilizing a trained localization neural network. The apparatus is further configured to compare the standardized feature representation data and the map feature representation data and identify local position data based on the comparison.

First claim

What is claimed is:

1. An apparatus for position localization comprising at least one processor and at least one non-transitory memory including computer program code instructions stored thereon, the computer program code instructions configured to, when executed, cause the apparatus to:
receive observed feature representation data captured by a sensor communicatively coupled with the apparatus, the observed feature representation data comprising an environment feature associated with an observed feature decay;
using a trained localization neural network, transform the observed feature representation data to standardized feature representation data, wherein the standardized feature representation data approximates a map feature representation of the environment feature;
compare the standardized feature representation data to map feature representation data that was captured during construction of the map feature representation; and
identify a localized position for the apparatus based on the comparison.

2. The apparatus according to claim 1 , wherein the map feature representation data is subject to a feature decay at a time of capture.

3. The apparatus according to claim 1 , wherein the observed feature representation data is in a raw data format.

4. The apparatus according to claim 1 , wherein the observed feature representation data is in a pre-processed data format.

5. The apparatus according to claim 1 , wherein the computer program code instructions are further configured to, when executed, cause the apparatus to output the localized position.

6. The apparatus according to claim 1 , wherein the trained localization neural network is a trained generative adversarial network.

7. The apparatus according to claim 1 , wherein an overall context of the standardized representation data corresponds to the overall context of the map feature representation.

8. A method for position localization comprising:
receiving observed feature representation data captured by a sensor, the observed feature representation data comprising an environment feature associated with an observed feature decay;
using a trained localization neural network, transform the observed feature representation data to standardized feature representation data, wherein the standardized feature representation data approximates a map feature representation of the environment feature;
comparing the standardized feature representation data to map feature representation data that was captured during construction of the map feature representation; and
identifying a localized position based upon the comparison.

9. The method according to claim 8 , wherein the map feature representation data is subject to a feature decay at a time of capture.

10. The method according to claim 8 , wherein the observed feature representation data is in a raw data format.

11. The method according to claim 8 , wherein the observed feature representation data is in a pre-processed data format.

12. The method according to claim 8 , further comprising outputting the localized position.

13. The method according to claim 8 , wherein the trained localization neural network is a trained generative adversarial network.

14. The method according to claim 8 , wherein an overall context of the standardized representation data corresponds to the overall context of the map feature representation.

15. A computer program product for position localization, the computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising program code instructions for:
receiving observed feature representation data captured by a sensor, the observed feature representation data comprising an environment feature associated with an observed feature decay;
using a trained localization neural network, transform the observed feature representation data to standardized feature representation data, wherein the standardized feature representation data comprises a map feature representation of the environment feature;
comparing the standardized feature representation data to map feature representation data that was captured during construction of the map feature representation; and
identifying a localized position based on the comparison.

16. The computer program product according to claim 15 , wherein the map feature representation data is subject to a feature decay at a time of capture.

17. The computer program product according to claim 15 , wherein the observed feature representation data is in a raw data format.

18. The computer program product according to claim 15 , wherein the observed feature representation data is in a pre-processed data format.

19. The computer program product according to claim 15 , further comprising program code instructions for outputting the localized position.

20. The computer program product according to claim 15 , wherein the trained localization neural network is a trained generative adversarial network.

Assignees

• Here Global Bv

Inventors

• Viswanathan Anirudh

Classifications

• G06V20/588

  Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road · CPC title

• G01C21/26 Primary

  specially adapted for navigation in a road network · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06T7/74 Primary

  involving reference images or patches · CPC title