Anonymizing navigation information for use in autonomous vehicle navigation

Patent metadata

Field	Value
Publication number	US-11768959-B2
Application number	US-202117210042-A
Country	US
Kind code	B2
Filing date	Mar 23, 2021
Priority date	Mar 5, 2018
Publication date	Sep 26, 2023
Grant date	Sep 26, 2023

Abstract

Systems and methods are provided for processing vehicle navigation information. A processing device may be configured to receive navigation information from a plurality of vehicles associated with a common road section; store the navigation information; generate at least a portion of an autonomous vehicle road navigation model for the common road section; and distribute the autonomous vehicle road navigation model to one or more autonomous vehicles. The navigation information from each of the vehicles may include first road segment information relative to a first portion of the common road section, and second road segment information relative to a second portion of the common road section. The second road segment information may include a motion representation for the vehicle and a road characteristic relative to the second portion of the common road section. The second portion may be different from and spatially separated from the first portion of the road section.

First claim

What is claimed is:

1. A server-based system for processing vehicle navigation information for use in autonomous vehicle navigation, the system comprising:
at least one processor programmed to:
receive navigation information from a plurality of vehicles, wherein the navigation information from the plurality of vehicles is associated with a common road section;
store the navigation information associated with the common road section;
generate at least a portion of an autonomous vehicle road navigation model for the common road section based on the navigation information from the plurality of vehicles; and
distribute the autonomous vehicle road navigation model to one or more autonomous vehicles for use in autonomously navigating the one or more autonomous vehicles along the common road section;
wherein the navigation information from each of the plurality of vehicles includes:
first road segment information relative to a first portion of the common road section, wherein the first road segment information includes a determined at least one motion representation for a host vehicle and a determined at least one road characteristic relative to the first portion of the common road section; and
second road segment information relative to a second portion of the common road section, wherein the second road segment information includes a determined at least one motion representation for the host vehicle and a determined at least one road characteristic relative to the second portion of the common road section, and wherein the second portion of the road section is different from the first portion of the road section and is spatially separated from the first portion of the road section;

wherein the first portion of the common road segment and the second portion of the common road segment are selected by the host vehicle to exclude private information.

2. The server-based system of claim 1 , wherein the at least one motion representation for the host vehicle, relative to the first and second portions of the common road section, includes a determined trajectory for the host vehicle.

3. The server-based system of claim 1 , wherein the at least one motion representation for the host vehicle, relative to the first and second portions of the common road section, is determined based on outputs from at least one of a GPS sensor, a speed sensor, or an accelerometer.

4. The server-based system of claim 1 , wherein the at least one road characteristic, relative to the first and second portions of the common road section, includes an indicator of one or more of a detected lane split, lane merge, dashed lane marking line, solid lane marking line, road surface color within a lane, lane line color, lane direction, lane type, road edge location, or landmark identifier.

5. The server-based system of claim 4 , wherein the landmark identifier includes at least one of a landmark type or a landmark location.

6. The server-based system of claim 5 , wherein the landmark type includes at least one of a traffic signal, pole, road marking, stop line, or sign.

7. The server-based system of claim 1 , wherein the first portion of the common road section is spatially separated from the second portion of the common road section by a distance of at least 1 km.

8. The server-based system of claim 1 , wherein the first portion of the common road section and the second portion of the common road section each have a length of at least 2 km.

9. The server-based system of claim 1 , wherein the at least one motion representation for the host vehicle, relative to the first and second portions of the common road section, includes an ego-motion representation for the host vehicle relative to a predetermined coordinate system.

10. The server-based system of claim 9 , wherein the ego-motion representation for the host vehicle is determined for six degrees of freedom.

11. The server-based system of claim 1 , wherein the at least one road characteristic, relative to the first and second portions of the common road section, includes a temporary road characteristic comprising an indicator of a weather condition along the road section.

12. The server-based system of claim 11 , wherein the indicator of weather condition is associated with at least one of snow, rain, fog, or sun glare.

13. The server-based system of claim 1 , wherein a length of at least one of the first portion of the road section or the second portion of the road section is determined based on a randomized value.

14. The server-based system of claim 13 , wherein the randomized value is constrained to fall within +/−0.5 km of a predetermined length.

15. The server-based system of claim 1 , wherein the autonomous vehicle road navigation model includes at least one line representation of a road surface feature extending along the common road segment.

16. The server-based system of claim 15 , wherein the road surface feature includes at least one of a road edge or a lane marking.

17. The server-based system of claim 1 , wherein the private information is identified based on at least one image captured by the host vehicle.

18. The server-based system of claim 1 , wherein the private information includes at least a portion of a trajectory being in proximity to a private location.

19. The server-based system of claim 18 , wherein the private location includes at least one of a garage, a home of an individual, or a workplace of an individual.

20. A method for processing vehicle navigation information for use in autonomous vehicle navigation, the method comprising:
receiving navigation information from a plurality of vehicles, wherein the navigation information from the plurality of vehicles is associated with a common road section;
storing the navigation information associated with the common road section;
generating at least a portion of an autonomous vehicle road navigation model for the common road section based on the navigation information from the plurality of vehicles; and
distributing the autonomous vehicle road navigation model to one or more autonomous vehicles for use in autonomously navigating the one or more autonomous vehicles along the common road section;
wherein the navigation information from each of the plurality of vehicles includes:
first road segment information relative to a first portion of the common road section, wherein the first road segment information includes a determined at least one motion representation for a host vehicle and a determined at least one road characteristic relative to the first portion of the common road section; and
second road segment information relative to a second portion of the common road section, wherein the second road segment information includes a determined at least one motion representation for the host vehicle and a determined at least one road characteristic relative to the second portion of the common road section, and wherein the second portion of the road section is different from the first portion of the road section and is spatially separated from the first portion of the road section;

wherein the first portion of the common road segment and the second portion of the common road segment are selected by the host vehicle to exclude private information.

21. A non-transitory computer readable medium containing instructions that when executed by at least one processor, cause the at least one processor to:
receive navigation information from a plurality of vehicles, wherein the navigation information from the plurality of v

Assignees

• Mobileye Vision Technologies Ltd

Inventors

• Viente Kfir
• Harel Eli
• Tamir Achiya Tal
• Schwartz Maxim
• Shapira Dori
• Nehushtan Nimrod
• Gdalyahu Yoram
• Braunstein Daniel

Classifications

• G05D2111/10

  Optical signals · CPC title

• G05D2101/10

  using artificial intelligence [AI] techniques · CPC title

• H04W4/44

  for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H] · CPC title

• H04W4/027

  using movement velocity, acceleration information · CPC title

• G06V20/582

  of traffic signs · CPC title