Self-localization of a vehicle in a parking infrastructure

Patent metadata

Field	Value
Publication number	US-12078491-B2
Application number	US-202217861035-A
Country	US
Kind code	B2
Filing date	Jul 8, 2022
Priority date	Jul 9, 2021
Publication date	Sep 3, 2024
Grant date	Sep 3, 2024

Abstract

According to a method for self-localization of a vehicle, a first pose of the vehicle is determined. Environment sensor data are generated by means of an environment sensor device and on the basis of this a landmark is detected in the environment. A position of the landmark is determined and in dependence on this a second pose of the vehicle is determined. A memorized assignment instruction is consulted, matching up the first pose with at last one preferred sensor type or at least one dominant landmark type, and depending on this a first portion of the environment sensor data is selected that was generated by means of a first environment sensor system of the environment sensor device configured according to a first sensor type. For the detecting of the landmark, a first landmark detection algorithm is applied to the first portion of the environment sensor data.

First claim

The invention claimed is:

1. A method for self-localization of a vehicle in a parking structure, comprising:
determining a first pose of the vehicle in a map coordinates system of a digital map stored on a storage medium,
generating environment sensor data by an environment sensor device of the vehicle, representing an environment of the vehicle;
based on the environment sensor data, detecting a landmark in the environment and determining a position of the landmark in the map coordinates system; and
determining a second pose of the vehicle in the map coordinates system, dependent on the position of the landmark;
consulting an assignment instruction stored on the storage medium, the assignment instruction matching the first pose with at least one preferred sensor type or at least one dominant landmark type;
selecting, based on the assignment instruction, a first portion of the environment sensor data that was generated by a first environment sensor system of the environment sensor device configured according to a first sensor type,
wherein, for the detecting of the landmark, a first landmark detection algorithm is applied to the first portion of the environment sensor data; and
driving the vehicle based on the second pose and a second portion of the environment sensor data that was generated by a second environment sensor system of the environment sensor device configured according to a second sensor type that is different from the first sensor type.

2. The method according to claim 1 , wherein a second landmark detection algorithm, adapted for landmark detection based on the second portion of the environment sensor data that was generated by the second environment sensor system of the environment sensor device configured according to the second sensor type, is deactivated in dependence on the assignment instruction.

3. The method according to claim 2 , wherein:
an analysis drive is carried out in the parking structure by the vehicle, wherein during the analysis drive further environment sensor data are generated by the environment sensor device and the first landmark detection algorithm as well as the second landmark detection algorithm are applied to the further environment sensor data in order to determine the assignment instruction; or
an analysis drive is carried out in the parking structure by a further vehicle, wherein during the analysis drive further environment sensor data are generated by a further environment sensor device of the further vehicle and the first landmark detection algorithm as well as the second landmark detection algorithm are applied to the further environment sensor data in order to determine the assignment instruction.

4. The method according to claim 2 , wherein:
the first environment sensor system is activated in dependence on the assignment instruction and the second environment sensor system is deactivated in dependence on the assignment instruction; and
the environment sensor data are generated by the first environment sensor system.

5. The method according to claim 1 , wherein:
the first environment sensor system is configured as an optical sensor system; and
at least one ground marking line or at least one intersection of the at least one ground marking line is detected as the landmark.

6. The method according to claim 1 , wherein:
the first environment sensor system is configured as a radar system; and
at least one metallic structure is detected as the landmark or a building wall or part of a building wall is detected as the landmark.

7. The method according to claim 1 , wherein:
a current speed of the vehicle is determined; and
the first portion of the environment sensor data is determined in dependence on the current speed.

8. The method according to claim 1 , wherein the first portion of the environment sensor data is determined in dependence on a given localization accuracy.

9. A sensor device for a vehicle, the sensor device comprising:
an environment sensor device which, in operation, generates environment sensor data representing an environment of the vehicle,
wherein the environment sensor device contains a first environment sensor system configured according to a first sensor type and a second environment sensor system configured according to a second sensor type that is different from the first sensor type,
wherein the first environment sensor system, in operation, generates a first portion of the environment sensor data, and
wherein the second environment sensor system, in operation, generates a second portion of the environment sensor data;
a storage medium which stores a digital map; and
a control system which, in operation:
determines a first pose of the vehicle in a map coordinates system of the digital map;
based on the environment sensor data, detects a landmark in the environment and a determine a position of the landmark in the map coordinates system;
determines a second pose of the vehicle in the map coordinates system dependent on the position of the landmark,
consults an assignment instruction stored on the storage medium, the assignment instruction matching the first pose with at least one preferred sensor type or at least one dominant landmark type;
selects, based on the assignment instruction, the first portion of the environment sensor data, wherein for detection of the landmark, a first landmark detection algorithm is applied to the first portion of the environment sensor data; and
drives the vehicle based on the second pose and the second portion of the environment sensor data that was generated by the second environment sensor system of the environment sensor device.

Assignees

• Cariad Se
• Volkswagen Ag

Inventors

• Holicki Michael
• Hänsel Ralph
• Iken Timo
• Jördens Christian
• Kube Roland
• Last Carolin
• Wappler Stefan

Classifications

• G06T2207/30256

  Lane; Road marking · CPC title

• G06T7/73

  using feature-based methods · CPC title

• G01C21/30 Primary

  Map- or contour-matching · CPC title

• B60W2420/403

  Image sensing, e.g. optical camera · CPC title

• B60W2420/408

  Radar; Laser, e.g. lidar · CPC title