Mapping lane marks and navigation based on mapped lane marks

Patent metadata

Field	Value
Publication number	US-12091041-B2
Application number	US-202017096279-A
Country	US
Kind code	B2
Filing date	Nov 12, 2020
Priority date	May 15, 2018
Publication date	Sep 17, 2024
Grant date	Sep 17, 2024

Abstract

A system for mapping a lane mark for use in autonomous vehicle navigation is provided. The system includes at least one processor programmed to receive two or more location identifiers associated with a detected lane mark, associate the detected lane mark with a corresponding road segment, update an autonomous vehicle road navigation model relative to the corresponding road segment based on the two or more location identifiers associated with the detected lane mark, and distribute the updated autonomous vehicle road navigation model to a plurality of autonomous vehicles.

First claim

What is claimed is:

1. A system for mapping a lane mark for use in autonomous vehicle navigation, the system comprising:
at least one processor programmed to:
receive, from a vehicle remotely located from the system, two or more location identifiers of two or more points located on a detected lane mark;
associate the detected lane mark with a corresponding road segment based on the two or more location identifiers of the two or more points located on the detected lane mark;
update an autonomous vehicle road navigation model relative to the corresponding road segment based on the two or more location identifiers of the two or more points located on the detected lane mark; and
distribute the updated autonomous vehicle road navigation model to a plurality of autonomous vehicles via one or more networks through one or more wireless communication paths,
wherein the two or more location identifiers are determined based on:
acquisition, from a camera associated with a host vehicle, of at least one image representative of an environment of the host vehicle;
analysis of the at least one image to detect the lane mark in the environment of the host vehicle;
analysis of the at least one image to identify the two or more points located on the detected lane mark; and
analysis of the at least one image to determine a position of each one of the two or more points relative to at least one location associated with the host vehicle.

2. The system of claim 1 , wherein the two or more location identifiers include locations in real world coordinates of points associated with the detected lane mark.

3. The system of claim 2 , wherein the detected lane mark is part of a dashed line marking a lane boundary, and the points associated with the detected lane mark correspond to detected corners of the detected lane mark.

4. The system of claim 2 , wherein the detected lane mark is part of a continuous line marking a lane boundary, and the points associated with the detected lane mark correspond to a detected edge of the detected lane mark.

5. The system of claim 4 , wherein the two or more location identifiers include at least one point per meter of the detected edge of the detected lane mark.

6. The system of claim 4 , wherein the two or more location identifiers include at least one point per five meters of the detected edge of the detected lane mark.

7. The system of claim 2 , wherein the points associated with the detected lane mark correspond to a centerline associated with the detected lane mark.

8. The system of claim 2 , wherein the points associated with the detected lane mark correspond to a vertex between two intersecting lane marks and at least one two other points associated with the intersecting lane marks.

9. The system of claim 1 , wherein the autonomous vehicle road navigation model further includes at least one target trajectory for a vehicle to follow along the corresponding road segment.

10. The system of claim 1 , wherein the at least one processor is further programmed to receive a first communication from a first host vehicle, wherein the first communication includes the two or more location identifiers associated with the detected lane mark, and receive a second communication from a second host vehicle, wherein the second communication includes two or more additional location identifiers associated with the detected lane mark, and wherein the at least one processor is further programmed to refine a determination of at least one position associated with the detected lane mark based on the two or more location identifiers received in the first communication from the first host vehicle and based on the two or more additional location identifiers received in the second communication from the second host vehicle.

11. The system of claim 1 , wherein updating of the autonomous vehicle road navigation model relative to the corresponding road segment based on the two or more identifiers associated with the detected lane mark includes storing one or more indicators of position in real world coordinates of the detected lane mark.

12. A method for mapping a lane mark for use in autonomous vehicle navigation, the method comprising:
receiving, by a system and from a vehicle remotely located from the system, two or more location identifiers of two or more points located on a detected lane mark;
associating the detected lane mark with a corresponding road segment based on the two or more location identifiers of the two or more points located on the detected lane mark;
updating an autonomous vehicle road navigation model relative to the corresponding road segment based on the two or more location identifiers of the two or more points located on the detected lane mark; and
distributing the updated autonomous vehicle road navigation model to a plurality of autonomous vehicles via one or more networks through one or more wireless communication paths,
wherein the two or more location identifiers are determined based on:
acquisition, from a camera associated with a host vehicle, of at least one image representative of an environment of the host vehicle;
analysis of the at least one image to detect the lane mark in the environment of the host vehicle;
analysis of the at least one image to identify the two or more points located on the detected lane mark; and
analysis of the at least one image to determine a position of each one of the two or more points relative to at least one location associated with the host vehicle.

13. The method of claim 12 , wherein the two or more location identifiers include locations in real world coordinates of points associated with the detected lane mark.

14. The method of claim 12 , wherein the method further comprises:
receiving a first communication from a first host vehicle, wherein the first communication includes the two or more location identifiers associated with the detected lane mark;
receiving a second communication from a second host vehicle, wherein the second communication includes two or more additional location identifiers associated with the detected lane mark; and
refining a determination of at least one position associated with the detected lane mark based on the two or more location identifiers received in the first communication from the first host vehicle and based on the two or more additional location identifiers received in the second communication from the second host vehicle.

Assignees

• Mobileye Vision Technologies Ltd

Inventors

• Shapira Dori
• Viente Kfir
• Braunstein Daniel
• Caspi Bnaya
• Hanniel Iddo

Classifications

• G05D2101/15

  using machine learning, e.g. neural networks · CPC title

• G08G1/167

  Driving aids for lane monitoring, lane changing, e.g. blind spot detection · CPC title

• G08G1/09623

  Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle (G08G1/0967 takes precedence) · CPC title

• G01C21/3658

  Lane guidance · CPC title

• G01C21/3602 Primary

  Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera · CPC title