System and method for identifying redundant road lane detections

Patent metadata

Field	Value
Publication number	US-2023096065-A1
Application number	US-202117472273-A
Country	US
Kind code	A1
Filing date	Sep 10, 2021
Priority date	Sep 10, 2021
Publication date	Mar 30, 2023
Grant date	—

Abstract

A system for identifying redundant road lane detections in map data and subsequently updating the map data to remove the redundant road lane detections is provided. The system may be configured to determine, based on sensor data, a plurality of road lane detections associated with a road link represented by the map data. The system is further configured to determine a cluster for the road link based on a clustering criterion. The system is further configured to establish a plurality of road lane detection groups based on connectivity of the road lane detections in the cluster. The plurality of road lane detection groups is evaluated to identify one or more redundant road lane detections based on one or more of a parallel-detection criterion or a heading difference criterion. The identified redundant road lane detections are used to update the map data by a computer-implemented update process.

First claim

We claim:

1 . A system for identifying redundant road lane detections, the system comprising:
a memory configured to store computer-executable instructions; and at least one processor configured to execute the computer-executable instructions to:
determine, based on sensor data, a plurality of road lane detections associated with a road link represented by map data;
determine a cluster associated with the road link in accordance with a clustering criterion, the cluster including at least some of the plurality of road lane detections;
establish a plurality of road lane detection groups by one or more of (i) respectively grouping any road lane detections of the cluster that are connected with one another, or (ii) establishing a given road lane detection group respectively for each unconnected road lane detection of the cluster;
identify, from among the plurality of road lane detections, one or more redundant road lane detections by evaluating one or more of the plurality of road lane detection groups according to one or more of a parallel-detection criterion or a heading-difference criterion; and
perform a computer-implemented update process to remove the identified one or more redundant road lane detections from the map data.

2 . The system of claim 1 , wherein determining the cluster associated with the road link comprises:
determining, for each road lane detection in the plurality of road lane detections, a corresponding matched distance based on a distance of separation of the road lane detection from the road link, wherein the distance of separation is identified based on the map data; and determining the cluster associated with the road link by using the matched distance as the clustering criterion, such that the cluster includes at least some of the plurality of road lane detections which have the same matched distance.

3 . The system of claim 1 , wherein identifying the one or more redundant road lane detections by evaluating one or more of the plurality of road lane detection groups according to the parallel-detection criterion comprises:
identifying at least two road lane detection groups in the plurality of road lane detection groups that are parallel to each other; determining a respective length associated with each of the at least two road lane detection groups; and identifying the one or more redundant road lane detections based on the respective length associated with each of the at least two road lane detection groups.

4 . The system of claim 3 , wherein identifying the one or more redundant road lane detections comprises identifying the road lane detections associated with road lane detection group with shorter respective length as the one or more redundant road lane detections.

5 . The system of claim 3 , wherein identifying the one or more redundant road lane detections comprises identifying the road lane detections associated with road lane detection group with longer respective length as the one or more redundant road lane detections.

6 . The system of claim 1 , wherein identifying the one or more redundant road lane detections by evaluating one or more of the plurality of road lane detection groups according to the heading difference criterion comprises:
determining, for each road lane detection in a road lane detection group of the plurality of road lane detection groups, a road lane detection heading value; determining, for the road lane detection group, a group heading value; calculating, a heading difference value between the road lane detection heading value of each road lane detection and the group heading value; and detecting the road lane detection having the heading difference value more than a predetermined heading difference value threshold as the redundant road lane detection.

7 . The system of claim 1 , wherein identifying the one or more redundant road lane detections comprises: evaluating the one or more of the plurality of road lane detection groups according to a lateral position criterion associated with lateral placement of each road lane detection on the road link.

8 . The system of claim 1 , wherein the at least one processor is further configured to generate one or more navigation instructions based on the updated map data.

9 . A method performed by at least one or more processors, the at least one or more processors configured to execute computer-executable instructions associated with the method for identifying redundant road lane detections, the method comprising:
determining, based on sensor data, a plurality of road lane detections associated with a road link represented by map data; determining a cluster associated with the road link in accordance with a clustering criterion, the cluster including at least some of the plurality of road lane detections; establishing a plurality of road lane detection groups by one or more of (i) respectively grouping any road lane detections of the cluster that are connected with one another, or (ii) establishing a given road lane detection group respectively for each unconnected road lane detection of the cluster; identifying, from among the plurality of road lane detections, one or more redundant road lane detections by evaluating one or more of the plurality of road lane detection groups according to one or more of a parallel-detection criterion or a heading-difference criterion; and performing a computer-implemented update process to remove the identified one or more redundant road lane detections from the map data.

10 . The method of claim 9 , wherein determining the cluster associated with the road link comprises:
determining, for each road lane detection in the plurality of road lane detections, a corresponding matched distance based on a distance of separation of the road lane detection from the road link, wherein the distance of separation is identified based on the map data; and determining the cluster associated with the road link by using the matched distance as the clustering criterion, such that cluster includes at least some of the plurality of road lane detections which have the same matched distance.

11 . The method of claim 9 , wherein identifying the one or more redundant road lane detections by evaluating one or more of the plurality of road lane detection groups according to the parallel-detection criterion, comprises:
identifying at least two road lane detection groups in the plurality of road lane detection groups that are parallel to each other; determining a respective length associated with each of the at least two road lane detection groups; and identifying the one or more redundant road lane detections based on the respective length associated with each of the at least two road lane detection groups.

12 . The method of claim 11 , further comprising:
identifying the road lane detections associated with road lane detection group with shorter respective length as the one or more redundant road lane detections.

13 . The method of claim 11 , further comprising identifying the road lane detections associated with road lane detection group with longer respective length as the one or more redundant road lane detections.

14 . The method of claim 9 , wherein identifying the one or more redundant road lane detections by evaluating one or more of the plurality of road lane detection groups according to the heading difference criterion, comprises:
determining, for each road lane detection in a road lane detection group of the plurality of road lane detection groups, a road lane detection heading value; determining, for the road lane detection group, a group heading value; calcu

Assignees

• Here Global Bv

Inventors

• Zhang Zhenhua

Classifications

• G08G1/09626

  where the origin of the information is within the own vehicle, e.g. a local storage device, digital map · CPC title

• G06V20/588 Primary

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

• G01C21/3833 Primary

  characterised by the source of data · CPC title

• G01C21/20

  Instruments for performing navigational calculations (G01C21/24, G01C21/26 take precedence) · CPC title

• G08G1/056

  with provision for distinguishing direction of travel · CPC title