Method for determining a position of a vehicle

Patent metadata

Field	Value
Publication number	US-11977159-B2
Application number	US-202017087560-A
Country	US
Kind code	B2
Filing date	Nov 2, 2020
Priority date	Nov 7, 2019
Publication date	May 7, 2024
Grant date	May 7, 2024

Abstract

A computer-implemented method for determining a position of a vehicle is disclosed, wherein the vehicle is equipped with a sensor for capturing scans of a vicinity of the vehicle, wherein the method comprises at least the following steps carried out by computer-hardware components: capturing at least one scan by means of the sensor with a plurality of sensor data samples given in a sensor data representation; determining, from a database, a predefined map with at least one element is given in a map data representation; determining a transformed map by transforming the at least one element of the predefined map from the map data representation into the sensor data representation; matching at least a subset of the sensor data samples of the at least one scan and the at least one element of the transformed map; and determining the position of the vehicle based on the matching.

First claim

What is claimed is:

1. A computer-implemented method for determining a position of a vehicle, wherein the vehicle is equipped with a sensor for capturing scans of a vicinity of the vehicle, wherein the method comprises at least the following steps carried out by computer-hardware components:
capturing at least one scan by means of the sensor, wherein the at least one scan represents the vicinity of the vehicle and comprises a plurality of sensor data samples given in a sensor data representation, wherein the sensor data representation comprises a first component and a second component, the first component representing a distance between the sensor and the vicinity of the vehicle, and the second component representing a rate of change of the distance between the sensor and the vicinity of the vehicle;
determining, from a database, a predefined map, wherein the predefined map represents the vicinity of the vehicle and comprises at least one element representing a static landmark, wherein the at least one element is given in a map data representation comprising a plurality of coordinates, wherein the coordinates represent position information of the static landmark;
determining a transformed map by transforming the at least one element of the predefined map from the map data representation into the sensor data representation;
matching at least a subset of the sensor data samples of the at least one scan and the at least one element of the transformed map; and
determining the position of the vehicle based on the matching.

2. The method of claim 1 , wherein at least one of:
the sensor data representation is a native data representation of the sensor; and
the plurality of sensor data samples form raw sensor data of the sensor.

3. The method of claim 1 ,
wherein the first component represents a radial distance between the sensor the vicinity of the vehicle, and
wherein the second component represents a rate of change, in particular velocity, of the radial distance between the sensor and the vicinity of the vehicle.

4. The method of claim 1 ,
wherein the sensor comprises a Doppler sensor including at least one of: a radar sensor, a LiDAR sensor, and a camera.

5. The method of claim 1 ,
wherein transforming the at least one element comprises using a pre-defined transformation rule, the transformation rule being adapted to receive the at least one element of the predefined map and velocity information of the vehicle and to output the at least one element in the sensor data representation in response.

6. The method of claim 1 ,
wherein the at least one element represents a pole object comprising at least one of a streetlamp and a traffic sign.

7. The method of claim 1 , further comprising:
determining the subset of the sensor data samples on the basis of the at least one element of the transformed map.

8. The method of claim 1 ,
wherein determining the subset of the sensor data samples is carried out by using a predefined classification rule comprising a machine-learning based classification rule.

9. The method of claim 1 , further comprising:
determining a subset of the plurality of sensor data samples to be matched, wherein the following steps are carried out by the computer-hardware components for at least some of the sensor data samples:
identifying, from the plurality of sensor data samples, a sensor data sample having maximum similarity with the at least one element of the transformed map; and
assigning the identified sensor data sample to the at least one element of the transformed map.

10. The method of claim 9 , wherein identifying the sensor data sample comprises:
determining candidate sensor data samples from the plurality of sensor data samples, wherein each of the candidate sensor data samples is located in a predefined neighborhood of the at least one element of the transformed map, the predefined neighborhood being defined with respect to the first component and the second component of the sensor data representation;
determining, for each candidate sensor data sample, a difference between the candidate sensor data sample and the at least one element of the transformed map; and
selecting the sensor data sample having a minimum difference.

11. The method of claim 9 ,
wherein the matching comprises determining a rigid transformation function by minimizing a difference between the at least one element of the transformed map and the assigned sensor data sample,
wherein one of the at least one elements and the assigned sensor data sample is transformed by means of the rigid transformation function.

12. The method of claim 11 ,
wherein the method further comprises determining a preliminary position of the vehicle, and wherein determining the position of the vehicle comprises transforming the preliminary position by means of the rigid transformation function.

13. A system comprising:
a sensor configured to capture scans of a vicinity of a vehicle; and
one or more computer-hardware components configured to:
capture at least one scan by means of the sensor, wherein the at least one scan represents the vicinity of the vehicle and comprises a plurality of sensor data samples given in a sensor data representation, wherein the sensor data representation comprises a first component and a second component, the first component representing a distance between the sensor and the vicinity of the vehicle, and the second component representing a rate of change of the distance between the sensor and the vicinity of the vehicle;
determine, from a database, a predefined map, wherein the predefined map represents the vicinity of the vehicle and comprises at least one element representing a static landmark, wherein the at least one element is given in a map data representation comprising a plurality of coordinates, wherein the coordinates represent position information of the static landmark;
determine a transformed map by transforming the at least one element of the predefined map from the map data representation into the sensor data representation;
match at least a subset of the sensor data samples of the at least one scan and the at least one element of the transformed map; and
determine the position of the vehicle based on the matching.

14. The system of claim 13 , further comprising:
the vehicle, the vehicle being equipped with the sensor, wherein:
the sensor comprises a sensor system adapted to receive electro-magnetic radiation emitted from at least one emitter of the sensor system and reflected in a vicinity of the vehicle towards the sensor system; and
the position of the vehicle is determined based on the emitted and the reflected radiation.

15. A non-transitory computer readable medium comprising instructions for carrying out a computer-implemented method comprising the steps of:
capturing at least one scan by means of a sensor configured to capture scans of a vicinity of a vehicle, wherein the at least one scan represents the vicinity of the vehicle and comprises a plurality of sensor data samples given in a sensor data representation, wherein the sensor data representation comprises a first component and a second component, the first component representing a distance between the sensor and the vicinity of the vehicle, and the second component representing a rate of change of the distance between the sensor and the vicinity of the vehicle;
determining, from a database, a predefined map, wherein the predefined map represents the vicinity of the vehicle and comprises at least one element representing a static landmark, wherein the at least one element is given in a map data re

Assignees

• Aptiv Technologies AG

Inventors

• Pishehvari Ahmad
• Iurgel Uri
• Stefer Markus
• Statnikov Konstantin

Classifications

• G01S17/86 Primary

  Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders · CPC title

• G01S7/484

  Transmitters · CPC title

• G01S7/497

  Means for monitoring or calibrating · CPC title

• G01S17/46

  Indirect determination of position data · CPC title

• G01S17/89

  for mapping or imaging · CPC title