Methods and system for determining a location of an object

Patent metadata

Field	Value
Publication number	US-12188780-B2
Application number	US-202217647306-A
Country	US
Kind code	B2
Filing date	Jan 6, 2022
Priority date	Jan 11, 2021
Publication date	Jan 7, 2025
Grant date	Jan 7, 2025

Abstract

A computer implemented method for determining a location of an object comprises the following steps carried out by computer hardware components: determining a pre-stored map of a vicinity of the object; acquiring sensor data related to the vicinity of the object; determining an actual map based on the acquired sensor data; carrying out image registration based on the pre-stored map and the actual map; carrying out image registration based on the image retrieval; and determining a location of the object based on the image registration.

First claim

What is claimed is:

1. A method comprising:
determining, by computer hardware components, a location of an object by at least:
determining a pre-stored map of a vicinity of the object;
acquiring sensor data related to the vicinity of the object;
determining an actual map based on the acquired sensor data;
carrying out image retrieval based on the pre-stored map and the actual map;
carrying out image registration based on the image retrieval; and
determining the location of the object based on the image registration.

2. The method of claim 1 ,
wherein the sensor data comprises radar sensor data.

3. The method of claim 1 ,
wherein the sensor data comprises Global Positioning System sensor data.

4. The method of claim 1 ,
wherein the pre-stored map is generated based on a plurality of sub-maps.

5. The method of claim 1 ,
wherein the pre-stored map is generated using a recurrent neural network.

6. The method of claim 1 ,
wherein the pre-stored map is trained in a machine learning method together with training of at least one of determining the actual map, carrying out the image registration, and determining the location of the object.

7. The method of claim 1 ,
wherein the pre-stored map is generated using a Differential Global Positioning System.

8. The method of claim 1 ,
wherein the pre-stored map is generated using a radar sensor.

9. The method of claim 1 ,
wherein the image registration comprises matching the pre-stored map and the actual map.

10. The method of claim 1 ,
wherein the image registration comprises determining a translation and/or a rotation so that the actual map matches the pre-stored map; and
wherein the location of the object is determined based on the translation and/or the rotation.

11. A system comprising:
computer hardware components configured to determine a location of an object by at least:
determining a pre-stored map of a vicinity of the object;
acquiring sensor data related to the vicinity of the object;
determining an actual map based on the acquired sensor data;
carrying out image retrieval based on the pre-stored map and the actual map;
carrying out image registration based on the image retrieval; and
determining the location of the object based on the image registration.

12. The system of claim 11 , further comprising a vehicle, wherein the computer hardware components are part of the vehicle.

13. The system of claim 11 , wherein the computer hardware components are configured to acquire the sensor data from a sensor of a vehicle.

14. The system of claim 11 , wherein the computer hardware components are configured to retrieve the pre-stored map of the vicinity of the object from a map storage that is part of a vehicle.

15. The system of claim 11 , wherein the computer hardware components are further configured to:
generate, based on a plurality of sub-maps, the pre-stored map.

16. The system of claim 11 , wherein the computer hardware components are further configured to:
generate, using a recurrent neural network, the pre-stored map.

17. The system of claim 11 , wherein the computer hardware components are further configured to:
generate, using a recurrent neural network and based on a plurality of sub-maps, the pre-stored map.

18. The system of claim 11 , wherein the computer hardware components are further configured to:
generate, using a radar sensor, the pre-stored map.

19. The system of claim 11 , wherein the computer hardware components are further configured to:
generate, using a Differential Global Positioning System, the pre-stored map.

20. A non-transitory computer readable medium comprising executable instructions for configuring computer hardware components to determine a location of an object by at least:
determining a pre-stored map of a vicinity of the object;
acquiring sensor data related to the vicinity of the object;
determining an actual map based on the acquired sensor data;
carrying out image retrieval based on the pre-stored map and the actual map;
carrying out image registration based on the image retrieval; and
determining the location of the object based on the image registration.

Assignees

• Aptiv Technologies AG

Inventors

• Meuter Mirko
• Nunn Christian
• Zhu Weimeng
• Kaestner Florian
• Becker Adrian
• Schoeler Markus

Classifications

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title

• G06N3/0455

  Auto-encoder networks; Encoder-decoder networks · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/0495

  Quantised networks; Sparse networks; Compressed networks · CPC title

• G06N3/09

  Supervised learning · CPC title