Lane mapping and localization using periodically-updated anchor frames

Patent metadata

Field	Value
Publication number	US-11436843-B2
Application number	US-202117154169-A
Country	US
Kind code	B2
Filing date	Jan 21, 2021
Priority date	Jan 21, 2021
Publication date	Sep 6, 2022
Grant date	Sep 6, 2022

Abstract

A hybrid approach for using reference frames is presented in which a series of anchor frames is used, effectively resetting a global frame upon a trigger event. With each new anchor frame, parameter values for lane boundary estimates (known as lane boundary states) can be recalculated with respect to the new anchor frame. Triggering events may a based on a length of time, distance traveled, and/or an uncertainty value.

First claim

What is claimed is:

1. A method of lane mapping and localization of a vehicle on a road, the method comprising:
at a first time, setting a reference frame to a first anchor frame comprising a first frame of reference;
while the reference frame is the first anchor frame:
determining, with respect to the reference frame, a first set of parameter values for a lane boundary state representing a tracked lane boundary;
detecting, along a first portion of the road, a first candidate lane boundary;
updating the tracked lane boundary based on an association of the first candidate lane boundary with the tracked lane boundary; and
determining a position of the vehicle with respect to the tracked lane boundary;

at a second time subsequent to determining the position of the vehicle, in response to a trigger event, changing the reference frame to a second anchor frame comprising a second frame of reference; and
while the reference frame is the second anchor frame:
determining, with respect to the reference frame, a second set of parameter values for the lane boundary state;
detecting, along a second portion of the road, a second candidate lane boundary; and
updating the tracked lane boundary based on an association of the second candidate lane boundary with the tracked lane boundary.

2. The method of claim 1 , wherein the trigger event comprises:
a length of time having elapsed since the first time,
a distance travelled by the vehicle since the first time, or
an uncertainty value having grown since the first time,
or any combination thereof.

3. The method of claim 1 , further comprising providing output information comprising information indicative of the determined position of the vehicle, the second set of parameter values, or both.

4. The method of claim 3 , wherein providing the output information comprises providing the output information to:
an Advanced Driver-Assist System (ADAS) of the vehicle, or
a user interface of the vehicle, or
both.

5. The method of claim 1 , wherein the first portion of the road at least partially overlaps with the second portion of the road.

6. The method of claim 1 , wherein the first set of parameter values and the second set of parameter values include values for parameters comprising:
a heading of the lane boundary,
a curvature of the lane boundary,
an offset of the lane boundary, or
a point on the lane boundary, or
any combination thereof.

7. The method of claim 1 , wherein the determining of the position of the vehicle comprises:
obtaining sensor information, indicative of movement of the vehicle along the road, and
using the sensor information to determine the position of the vehicle.

8. The method of claim 7 , wherein the sensor information comprises movement information from:
an Inertial Measurement Unit (IMU) sensor located on the vehicle,
a wheel-speed sensor located on the vehicle,
wireless signal measurements,
a GNSS sensor located on the vehicle, or
a camera sensor located on the vehicle, or
any combination thereof.

9. The method of claim 1 , wherein the first set of parameter values and the second set of parameter values are descriptive of the lane boundary in two dimensions, such that a projection of the lane boundary from a plane of the anchor frame, onto an image plane of a camera located on the vehicle, overlaps with a projection of the lane boundary from a plane of the anchor frame onto the image plane.

10. A mobile device comprising:
sensors;
a memory; and
one or more processing units communicatively coupled with the sensors and the memory, the one or more processing units configured to:
at a first time, set a reference frame to a first anchor frame comprising a first frame of reference;
while the reference frame is the first anchor frame:
determine, with respect to the reference frame, a first set of parameter values for a lane boundary state representing a tracked lane boundary;
detect, along a first portion of the road, a first candidate lane boundary;
update the tracked lane boundary based on an association of the first candidate lane boundary with the tracked lane boundary; and
determine a position of the vehicle with respect to the tracked lane boundary;

at a second time subsequent to determining the position of the vehicle, in response to a trigger event, change the reference frame to a second anchor frame comprising a second frame of reference; and
while the reference frame is the second anchor frame:
determine, with respect to the reference frame, a second set of parameter values for the lane boundary state;
detect, along a second portion of the road, a second candidate lane boundary; and
update the tracked lane boundary based on an association of the second candidate lane boundary with the tracked lane boundary.

11. The mobile device of claim 10 , wherein the one or more processing units are further configured to detect the trigger event, wherein the trigger event comprises:
a length of time having elapsed since the first time,
a distance travelled by the vehicle since the first time, or
an uncertainty value having grown since the first time,
or any combination thereof.

12. The mobile device of claim 10 , wherein the one or more processing units are further configured to provide output information, the output information indicative of the determined position of the vehicle, the second set of parameter values, or both.

13. The mobile device of claim 12 , wherein the one or more processing units are configured to provide the output information to:
an Advanced Driver-Assist System (ADAS) of the vehicle, or
a user interface of the vehicle, or
both.

14. The mobile device of claim 10 , wherein the first portion of the road at least partially overlaps with the second portion of the road.

15. The mobile device of claim 10 , wherein the first set of parameter values and the second set of parameter values include values for parameters comprising:
a heading of the lane boundary,
a curvature of the lane boundary,
an offset of the lane boundary, or
a point on the lane boundary, or
any combination thereof.

16. The mobile device of claim 10 , wherein, to determine the position of the vehicle, the one or more processing units are configured to:
obtain sensor information from the sensors, the sensor information indicative of movement of the vehicle along the road, and
use the sensor information to determine the position of the vehicle.

17. The mobile device of claim 16 , wherein, to obtain the sensor information, the one or more processing units are configured to obtain movement information from the sensors, the movement information comprising:
an Inertial Measurement Unit (IMU) sensor located on the vehicle,
a wheel-speed sensor located on the vehicle,
wireless signal measurements,
a GNSS sensor located on the vehicle, or
a camera sensor located on the vehicle, or
any combination thereof.

18. The mobile device of claim 10 , wherein the first set of parameter values and the second set of parameter values are descriptive of the lane boundary in two dimensions such that a projection of the lane boundary from a plane of the anchor frame onto an image plane of a camera located on the vehicle overlaps with a projection of the lane boundary from a plane of the anchor frame onto the image plane.

19. A device comprising:
means for, at a first time, setting a reference frame to a first anchor frame comprising a first frame of reference;
means for, while the reference frame is the first anchor fr

Assignees

• Qualcomm Inc

Inventors

• Bande Meghana
• Niesen Urs

Classifications

• G01C21/3819 Primary

  Road shape data, e.g. outline of a route · CPC title

• G01C21/1656

  with passive imaging devices, e.g. cameras · CPC title

• G06T2207/30256

  Lane; Road marking · CPC title

• G06T7/246

  using feature-based methods, e.g. the tracking of corners or segments · CPC title

• G01C21/3848

  Data obtained from both position sensors and additional sensors · CPC title