Vector data encoding of high definition map data for autonomous vehicles

• US 10,359,518 B2
• Filed: 12/28/2017
• Issued: 07/23/2019
• Est. Priority Date: 12/30/2016
• Status: Active Grant

• Current Assignee: NVIDIA Corporation
• Original Assignee: DeepMap, Inc. (NVIDIA Corporation)
• Inventors: Wheeler, Mark Damon
• Primary Examiner(s): Beg, Samah A
• Application Number:
  US15/857,383
• Publication Number:
  US 20180188372A1
• Time in Patent Office: 572 Days
• Field of Search: None
• CPC Class Codes: B60R 11/04 Mounting of cameras operative during drive; Arrangement of controls thereof relative to the vehicle
• CPC Class Codes: G01C 11/025 by scanning the object
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G01C 21/3841 Data obtained from two or more sources, e.g. probe vehicles
• CPC Class Codes: G01C 21/3848 Data obtained from both position sensors and additional sensors
• CPC Class Codes: G01C 21/3867 Geometry of map features, e.g. shape points, polygons or for simplified maps
• CPC Class Codes: G01C 21/3874 Structures specially adapted for data searching and retrieval
• CPC Class Codes: G01S 17/86 Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
• CPC Class Codes: G01S 17/89 for mapping or imaging
• CPC Class Codes: G01S 17/90 using synthetic aperture techniques
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G06F 16/1744 using compression, e.g. sparse files
• CPC Class Codes: G06T 9/001 Model-based coding, e.g. wire frame
• CPC Class Codes: G06T 9/20 Contour coding, e.g. using detection of edges
• CPC Class Codes: G06V 20/582 of traffic signs
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: H04N 19/17 the unit being an image region, e.g. an object

Abstract

Embodiments relate to methods for efficiently encoding sensor data captured by an autonomous vehicle and building a high definition map using the encoded sensor data. The sensor data can be LiDAR data which is expressed as multiple image representations. Image representations that include important LiDAR data undergo a lossless compression while image representations that include LiDAR data that is more error-tolerant undergo a lossy compression. Therefore, the compressed sensor data can be transmitted to an online system for building a high definition map. When building a high definition map, entities, such as road signs and road lines, are constructed such that when encoded and compressed, the high definition map consumes less storage space. The positions of entities are expressed in relation to a reference centerline in the high definition map. Therefore, each position of an entity can be expressed in fewer numerical digits in comparison to conventional methods.

Claims

1. A method comprising:

generating a high definition map using data captured by sensors mounted on one or more autonomous vehicles;

for each of a plurality of geographical regions in the high definition map;

generating a reference centerline that defines an origin point within the geographical region;

for each of a plurality of entities in the geographical region;

determining coordinates of the entity in relation to the origin point of the reference centerline; and

encoding each of the determined coordinates of the entity as one or more bytes;

generating compressed codes for the geographical region, the compressed codes for the geographical region comprising, for each of the plurality of entities in the geographical region, the one or more bytes representing coordinates of the entity; and

storing the compressed codes for the geographical region;

receiving a request for a geographical region of the high definition map from a particular autonomous vehicle; and

responsive to receiving the request, transmitting the compressed codes for the requested geographical region of the high definition map to the particular autonomous vehicle, wherein the particular autonomous vehicle performs navigation using the compressed codes for the requested geographical region.

2. The method of claim 1, wherein generating compressed codes for the geographical region comprises applying a compression algorithm to the one or more bytes representing coordinates of the entity of the geographical region.

3. The method of claim 1, wherein the generated reference centerline traces along a centerline of a road of the geographical region.

4. The method of claim 1, wherein the determined coordinates of the entity are represented by four or fewer bytes.

5. The method of claim 1, wherein the determined coordinates of the entity comprise an x-coordinate, a y-coordinate, and a z-coordinate, wherein the x-coordinate represents a distance between the reference centerline and the entity as measured by a line orthogonal to the reference centerline.

6. The method of claim 5, wherein the y-coordinate represents a distance traced along a length of the reference centerline.

7. The method of claim 1, wherein an entity in the geographical region is one of a lane line, a lane element, a navigable surface boundary, a stop or yield line, a zone, a traffic light, and a road sign.

8. The method of claim 1, further comprising for at least one entity in the geographical region:

determining orientation coordinates of the at least one entity; and

encoding the determined orientation coordinates of the at least one entity in one or more bytes,

wherein the compressed codes for each geographical region further comprise the one or more bytes representing the orientation coordinates of the at least one entity in the geographical region.

9. The method of claim 8, wherein the orientation coordinates of the at least one entity comprise a three dimensional normal vector of the at least one entity and a three dimensional vector representing an up direction of the entity.

10. The method of claim 1, further comprising for at least one entity in the geographical region:

determining semantic information of the at least one entity; and

encoding the determined semantic information of the at least one entity in one or more bytes,

wherein the compressed codes for each geographical region further comprise the one or more bytes representing the semantic information of the at least one entity in the geographical region.

11. The method of claim 10, wherein the semantic information of the at least one entity comprises dimensions of the at least one entity and a descriptive type of the at least one entity.

12. The method of claim 10, wherein the semantic information of the at least one entity comprises a lane relationship between the at least one entity and an additional entity of the geographic region.

13. The method of claim 10, wherein the semantic information of the at least one entity comprises a driving restriction enforced by the at least one entity.

14. The method of claim 1, wherein the compressed codes for the geographical region further comprise a plurality of bytes representing the reference centerline of the road of the geographical region.

15. A non-transitory computer readable storage medium comprising computer instructions that, when executed by a processor, cause the processor to:

generate a high definition map using data captured by sensors mounted on one or more autonomous vehicles;

for each of a plurality of geographical regions in the high definition map;

generate a reference centerline that defines an origin point within the geographical region;

for each of a plurality of entities in the geographical region;

determine coordinates of the entity in relation to the origin point of the reference centerline; and

encode each of the determined coordinates of the entity as one or more bytes;

generate compressed codes for the geographical region, the compressed codes for the geographical region comprising, for each of the plurality of entities in the geographical region, the one or more bytes representing coordinates of the entity; and

store the compressed codes for the geographical region; and

receive a request for a geographical region of the high definition map from a particular autonomous vehicle; and

responsive to receiving the request, transmit the compressed codes for the requested geographical region of the high definition map to the particular autonomous vehicle, wherein the particular autonomous vehicle performs navigation using the compressed codes for the requested geographical region.

16. The non-transitory computer readable storage medium of claim 15, wherein the generated reference centerline traces along a centerline of a road of the geographical region.

17. The non-transitory computer readable storage medium of claim 15, wherein the determined coordinates of the entity are represented by four or fewer bytes.

18. The non-transitory computer readable storage medium of claim 15, wherein the determined coordinates of the entity comprises an x-coordinate, a y-coordinate, and a z-coordinate, wherein the x-coordinate represents a distance between the reference centerline and the entity as measured by a line orthogonal to the reference centerline and wherein the y-coordinate represents a distance traced along a length of the reference centerline from the origin point to the line orthogonal to the reference centerline.

19. The non-transitory computer readable storage medium of claim 15, further comprising computer instructions that, when executed by the processor, cause the processor to:

for at least one entity in the geographical region;

determine orientation coordinates of the at least one entity; and

encode the determined orientation coordinates of the at least one entity in one or more bytes,

wherein the compressed codes for each geographical region further comprise the one or more bytes representing the orientation coordinates of the at least one entity in the geographical region.

20. The non-transitory computer readable storage medium of claim 15, further comprising computer instructions that, when executed by the processor, cause the processor to:

for at least one entity in the geographical region;

determine semantic information of the at least one entity; and

encode the determined semantic information of the at least one entity in one or more bytes,

wherein the compressed codes for each geographical region further comprise the one or more bytes representing the semantic information of the at least one entity in the geographical region.

21. A computer system comprising:

one or more computer processors; and

a non-transitory computer readable storage medium comprising computer instructions that, when executed by a processor, cause the processor to;

generate a high definition map using data captured by sensors mounted on one or more autonomous vehicles;

for each of a plurality of geographical regions in the high definition map;

generate a reference centerline that defines an origin point within the geographical region;

for each of a plurality of entities in the geographical region;

determine coordinates of the entity in relation to the origin point of the reference centerline; and

encode each of the determined coordinates of the entity as one or more bytes;

generate compressed codes for the geographical region, the compressed codes for the geographical region comprising, for each of the plurality of entities in the geographical region, the one or more bytes representing coordinates of the entity; and

store the compressed codes for the geographical region; and

receive a request for a geographical region of the high definition map from a particular autonomous vehicle; and

responsive to receiving the request, transmit the compressed codes for the requested geographical region of the high definition map to the particular autonomous vehicle, wherein the particular autonomous vehicle performs navigation using the compressed codes for the requested geographical region.