Sparse map for autonomous vehicle navigation

Patent metadata

Field	Value
Publication number	US-10317903-B2
Application number	US-201715586243-A
Country	US
Kind code	B2
Filing date	May 3, 2017
Priority date	Feb 10, 2015
Publication date	Jun 11, 2019
Grant date	Jun 11, 2019

Abstract

A non-transitory computer-readable medium is provided. The computer-readable medium includes a sparse map for autonomous vehicle navigation along a road segment. The sparse map includes a polynomial representation of a target trajectory for the autonomous vehicle along the road segment, and a plurality of predetermined landmarks associated with the road segment. The plurality of predetermined landmarks are spaced apart by at least 50 meters, and the sparse map has a data density of no more than 1 megabyte per kilometer.

First claim

What is claimed is:

1. A non-transitory computer-readable medium including instructions that, when executed by a processor, cause the processor to perform a method for providing a sparse map for autonomous vehicle navigation along a road segment, the method comprising:
receiving, from a first autonomous vehicle, a request for a map including a location associated with the first autonomous vehicle;
retrieving, based on the associated location and from the sparse map, data relating to a polynomial representation of a target trajectory for the first autonomous vehicle along a first road segment; and
retrieving, based on the associated location and from the sparse map, data relating to a first plurality of predetermined landmarks associated with the first road segment, wherein the first plurality of predetermined landmarks are spaced apart by at least 50 meters, and wherein the sparse map has a data density of no more than 1 megabyte per kilometer;
providing the data relating to the polynomial representation and the data relating to the predetermined landmarks to the first autonomous vehicle for navigation along the road segment;
receiving, from at least one second autonomous vehicle, an update related to at least one of a polynomial representation of a target trajectory along a second road segment or a predetermined landmark associated with the second road segment; and
when the first road segment comprises the second road segment or the second road segment is included in a planned trip associated with the first autonomous vehicle, providing the update to the first autonomous vehicle.

2. The non-transitory computer-readable medium of claim 1 , wherein the polynomial representation is a three-dimensional polynomial representation.

3. The non-transitory computer-readable medium of claim 1 , wherein the polynomial representation of the target trajectory is determined based on two or more reconstructed trajectories of prior traversals of vehicles along the road segment.

4. The non-transitory computer-readable medium of claim 1 , wherein the plurality of predetermined landmarks include a traffic sign represented in the sparse map by no more than 50 bytes of data.

5. The non-transitory computer-readable medium of claim 1 , wherein the plurality of predetermined landmarks include a directional sign represented in the sparse map by no more than 50 bytes of data.

6. The non-transitory computer-readable medium of claim 1 , wherein the plurality of predetermined landmarks include a general purpose sign represented in the sparse map by no more than 100 bytes of data.

7. The non-transitory computer-readable medium of claim 1 , wherein the plurality of predetermined landmarks include a generally rectangular object represented in the sparse map by no more than 100 bytes of data.

8. The non-transitory computer-readable medium of claim 7 , wherein the representation of the generally rectangular object in the sparse map includes a condensed image signature associated with the generally rectangular object.

9. The non-transitory computer-readable medium of claim 1 , wherein the plurality of predetermined landmarks are represented in the sparse map by parameters including landmark size, distance to previous landmark, landmark type, and landmark position.

10. The non-transitory computer-readable medium of claim 1 , wherein the plurality of predetermined landmarks included in the sparse map are spaced apart by at least 2 kilometers.

11. The non-transitory computer-readable medium of claim 1 , wherein the plurality of predetermined landmarks included in the sparse map are spaced apart by at least 1 kilometer.

12. The non-transitory computer-readable medium of claim 1 , wherein the plurality of predetermined landmarks included in the sparse map are spaced apart by at least 100 meters.

13. The non-transitory computer-readable medium of claim 1 , wherein the sparse map has a data density of no more than 100 kilobytes per kilometer.

14. The non-transitory computer-readable medium of claim 1 , wherein the sparse map has a data density of no more than 10 kilobytes per kilometer.

15. The non-transitory computer-readable medium of claim 1 , wherein the plurality of predetermined landmarks appear in the sparse map at a rate that is above a rate sufficient to maintain a longitudinal position determination accuracy within 1 meter.

Assignees

• Mobileye Vision Technologies Ltd

Inventors

• Shashua Amnon
• Gdalyahu Yoram
• Springer Ofer
• Reisman Aran
• Braunstein Daniel

Classifications

• G01C21/32

  Structuring or formatting of map data · CPC title

• G01C21/30 Primary

  Map- or contour-matching · CPC title

• B60W2555/60

  Traffic rules, e.g. speed limits or right of way · CPC title

• B60W2710/18

  Braking system · CPC title

• G01S19/10

  providing dedicated supplementary positioning signals · CPC title