Free space mapping and navigation

Patent metadata

Field	Value
Publication number	US-12441353-B2
Application number	US-202017096053-A
Country	US
Kind code	B2
Filing date	Nov 12, 2020
Priority date	May 15, 2018
Publication date	Oct 14, 2025
Grant date	Oct 14, 2025

Abstract

A system for mapping road segment free spaces for use in autonomous vehicle navigation. The system includes at least one processor programmed to: receive from a first vehicle one or more location identifiers associated with a lateral region of free space adjacent to a road segment; update an autonomous vehicle road navigation model for the road segment to include a mapped representation of the lateral region of free space based on the received one or more location identifiers; 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 road segment free spaces for use in autonomous vehicle navigation, the system comprising:
at least one processor programmed to:
receive from a first vehicle, one or more location identifiers detected by the first vehicle as the first vehicle navigates along a road segment according to a target trajectory, the one or more location identifiers being associated with a lateral region of free space adjacent to and intersecting with the road segment, wherein each of the one or more location identifiers associated with the lateral region of free space adjacent to and intersecting with the road segment includes coordinates that are relative to the target trajectory according to which the vehicle navigates;
update an autonomous vehicle road navigation model for the road segment to include a mapped representation of the lateral region of free space adjacent to and intersecting with the road segment based on the one or more location identifiers, wherein the autonomous vehicle road navigation model for the road segment includes the target trajectory; and
distribute the updated autonomous vehicle road navigation model to a plurality of autonomous vehicles, at least one of the autonomous vehicles being configured to autonomously navigate along the target trajectory based on the mapped representation of the lateral region of free space adjacent to and intersecting with the road segment included in the updated autonomous vehicle road navigation model, the autonomous navigation including causing implementation of a navigational action to avoid a potential collision based on a determination that the lateral region of free space adjacent to and intersecting with the road segment has a size sufficient to allow a pedestrian or a vehicle to enter the road segment.

2. The system of claim 1 , wherein the lateral region of free space includes one or more of a driveway intersecting the road segment, a parking lot, or a sidewalk.

3. The system of claim 1 , wherein the at least one processor is further programmed to receive an additional characteristic associated with the lateral region of free space adjacent to the road segment.

4. The system of claim 3 , wherein the additional characteristic includes a free space type indicator.

5. The system of claim 4 , wherein the free space type indicator includes at least one of a driveway, a parking lot, or a sidewalk.

6. The system of claim 3 , wherein the additional characteristic is received from the first vehicle.

7. The system of claim 1 , wherein the mapped representation of the lateral region of free space includes location information associated with one or more detected boundaries of the lateral region of free space.

8. The system of claim 7 , wherein the mapped representation of the lateral region of free space further includes a free space type indicator.

9. The system of claim 8 , wherein the free space type indicator includes at least one of a driveway, a parking lot, or a sidewalk.

10. The system of claim 8 , wherein the free space type indicator indicates that the lateral region of free space adjacent to the road segment is a driveway, a parking lot, or a sidewalk.

11. The system of claim 8 , wherein the at least one processor is further programmed to determine the free space type indicator.

12. The system of claim 8 , wherein at least one processor associated with the first vehicle is further programmed to determine the free space type indicator.

13. 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 road segment.

14. The system of claim 13 , wherein the at least one target trajectory is represented by a three-dimensional spline.

15. The system of claim 13 , wherein the at least one target trajectory is adjacent to the lateral region of free space.

16. The system of claim 13 , wherein the at least one target trajectory intersects the lateral region of free space.

17. The system of claim 1 , wherein the one or more location identifiers associated the lateral region of free space include one or more points or lines associated with a detected boundary of the lateral region of free space.

18. The system of claim 1 , wherein the at least one processor is further programmed to:
receive from a second vehicle one or more location identifiers associated the lateral region of free space adjacent to the road segment; and
update the autonomous vehicle road navigation model for the road segment to include a refined mapped representation of the lateral region of free space, wherein the refined mapped representation of the lateral region of free space is based on the one or more location identifiers received from the first vehicle and the one or more location identifiers received from the second vehicle.

19. The system of claim 18 , wherein:
the one or more location identifiers received from the first vehicle represent first lines;
the one or more location identifiers received from the second vehicle represent second lines; and
the at least one processor is further programmed to associate the first and second lines with a single driveway.

20. The system of claim 1 , wherein the at least one processor is further programmed to consolidate or aggregate the one or more location identifiers received from the first vehicle with at least one additional location identifier received from a second vehicle, the at least one additional location identifier being associated with the lateral region of free space adjacent to the road segment.

21. The system of claim 1 , wherein the lateral region of free space is next to the road segment and located outside a road edge of the road segment.

22. The system of claim 21 , wherein the road edge of the road segment is a lane marking.

23. The system of claim 21 , wherein the road edge of the road segment is a physical edge of the road segment.

24. The system of claim 1 , wherein a road edge of the road segment divides the lateral region of free space from the road segment.

25. The system of claim 1 , wherein the lateral region of free space includes a sidewalk bordering the road segment.

26. The system of claim 1 , wherein the lateral region of free space includes another road segment.

27. The system of claim 26 , wherein the road segment is a portion of a first roadway having one or more lanes and the another road segment is a portion of a second roadway having one or more lanes.

28. The system of claim 1 , wherein the road segment includes a portion of a roadway having one or more lanes.

29. The system of claim 1 , wherein the coordinates are relative to a longitudinal position along the target trajectory navigated by the first vehicle and a lateral distance from the target trajectory navigated by the first vehicle.

30. A computer-implemented method for mapping road segment free spaces for use in autonomous vehicle navigation, comprising:
receiving from a first vehicle, one or more location identifiers detected by the first vehicle as the first vehicle navigates along a road segment according to a target trajectory, the one or more location identifiers being associated with a lateral region of free space adjacent to and intersecting with the road segment, wherein each of the one or more location identifiers associated with

Assignees

• Mobileye Vision Technologies Ltd

Inventors

• Braunstein Daniel
• Levi Ishay
• Viente Kfir
• Huberman David
• Argaman Matan

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