Approach for estimating the geometry of roads and lanes by using vehicle trajectories

• US 9,460,622 B1
• Filed: 10/16/2014
• Issued: 10/04/2016
• Est. Priority Date: 03/16/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Ferguson, David Ian Franklin, Dolgov, Dmitri A.
• Primary Examiner(s): Hilgendorf, Dale W
• Application Number:
  US14/516,044
• Time in Patent Office: 719 Days
• US Class Current: 1/1
• CPC Class Codes: B60W 10/04 including control of propulsion units
• CPC Class Codes: B60W 10/18 including control of braking systems
• CPC Class Codes: B60W 10/184 with wheel brakes
• CPC Class Codes: B60W 10/20 including control of steering systems
• CPC Class Codes: B60W 2050/0075 Automatic parameter input, automatic initialising or calibrating means
• CPC Class Codes: B60W 2552/20 Road profile, i.e. the change in elevation or curvature of a plurality of continuous road segments
• CPC Class Codes: B60W 2554/4041 Position
• CPC Class Codes: B60W 2554/4049 Relationship among other objects, e.g. converging dynamic objects
• CPC Class Codes: B60W 2554/801 Lateral distance
• CPC Class Codes: B60W 2556/45 External transmission of data to or from the vehicle
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 2710/18 Braking system
• CPC Class Codes: B60W 2710/20 Steering systems
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 30/10 Path keeping cruise control for automatically following a preceding vehicle B60W30/165
• CPC Class Codes: B60W 30/16 Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
• CPC Class Codes: B60W 30/18163 Lane change; Overtaking manoeuvres
• CPC Class Codes: B60W 40/072 Curvature of the road
• CPC Class Codes: B60W 60/001 Planning or execution of driving tasks
• CPC Class Codes: G01C 21/3819 Road shape data, e.g. outline of a route
• CPC Class Codes: G01C 21/3841 : Data obtained from two or more sources, e.g. probe vehicles
• CPC Class Codes: G05D 1/0212 : with means for defining a desired trajectory involving a plurality of land vehicles G05D1/0287
• CPC Class Codes: G05D 1/0246 : using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0257 : using a radar radar systems designed for anti-collision purposes between land vehicles or between land vehicle and fixed obstacles G01S13/931
• CPC Class Codes: G05D 1/0287 : involving a plurality of land vehicles, e.g. fleet or convoy travelling traffic control systems for road vehicles G08G1/00, particularly anticollision systems G08G1/16
• CPC Class Codes: G08G 1/096725 : where the received information generates an automatic action on the vehicle control
• CPC Class Codes: G08G 1/20 : Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
• CPC Class Codes: G08G 1/22 : Platooning, i.e. convoy of communicating vehicles

Abstract

A method and apparatus is provided for controlling the operation of an autonomous vehicle. According to one aspect, the autonomous vehicle may track the trajectories of other vehicles on a road. Based on the other vehicle'"'"'s trajectories, the autonomous vehicle may generate a representative trajectory. Afterwards, the autonomous vehicle may change at least one of its speed or direction based on the representative trajectory.

Claims

1. A method comprising:

identifying, using one or more processors, a base trajectory and a first trajectory, each trajectory including one or more locations, and each trajectory being associated with a particular road vehicle;

selecting, using the one or more processors, a base location from the one or more locations of the base trajectory;

clustering, using the one or more processors, at least one location from the first trajectory, wherein the at least one location is selected based on a measured distance from the base location;

determining, using the one or more processors, a third location based on the clustered locations and the base location, the third location being different from the base location and the clustered locations;

calculating, using the one or more processors, a third trajectory using the third location; and

changing, using the one or more processors, at least one of a speed of a third road vehicle and a direction of the third road vehicle based on the third trajectory.

2. The method of claim 1, wherein the measured distance to select the at least one location is a predetermined distance.

3. The method of claim 1, further comprising:

identifying a second trajectory with one or more locations, wherein the clustered locations includes locations from the second trajectory.

4. The method of claim 3, wherein the clustered locations includes only one location from the first trajectory and only one location from the second trajectory.

5. The method of claim 3, wherein the clustered locations include only the locations that are closest to the base location.

6. The method of claim 1, wherein the third location is calculated by an average between the base location and the clustered locations.

7. The method of claim 1, further comprising:

identifying a fourth trajectory, the fourth trajectory having one or more locations;

selecting the identified fourth trajectory as a new base trajectory; and

calculating a firth trajectory based on the new base trajectory.

8. The method of claim 1, wherein the third location is further based on a set of reliability characteristics of the base trajectory and the first trajectory.

9. A system comprising:

memory; and

one or more processors in communication with the memory, wherein the one or more processors are configured to;

identify a first trajectory associated with a first road vehicle, the first trajectory comprising a first plurality of different locations each associated with different instants in time, wherein at least one location of the first plurality is in a first lane at a first instant in time and at least one location of the first plurality is in a second lane at an instant in time later than the first instant, the first lane and second lane being on the same road;

identify a second trajectory associated with a second road vehicle, the second trajectory comprising a second plurality of different locations each associated with different instants in time, wherein at least one location of the second plurality is in the first lane at a second instant in time and at least one location of the second plurality is in the second lane at an instant in time later than the second instant;

select a location from the second trajectory;

cluster at least one location from the first trajectory, wherein the at least one location is selected based on being within a threshold distance from the location selected from the second trajectory;

determine a third location based on the clustered at least one location and the base location, the third location being different from the base location and the clustered locations; and

indicate to a third vehicle that the first lane is blocked and steer the third vehicle around the blocked lane via the third location.

10. The system of claim 9, wherein the one or more processors are further configured to:

identify a third trajectory with one or more locations, wherein the clustered locations includes locations from the third trajectory.

11. The system of claim 10, wherein the clustered locations includes only one location from the first trajectory and only one location from the third trajectory.

12. The system of claim 10, wherein the clustered locations includes only the locations that are closest to the base location.

13. The system of claim 9, wherein the third location is calculated by an average between the location selected from the second trajectory and the clustered locations.

14. The system of claim 9, wherein the third location is further based on a set of reliability characteristics of the second trajectory and the first trajectory.

15. The system of claim 9 wherein indicating to the third vehicle that the first lane is blocked comprises updating a map used by the third vehicle.

16. The system of claim 15, wherein the third vehicle determines its trajectory based on a model of the geometry of the road derived from the map.

17. The system of claim 9, wherein the third location is in the second lane.

18. A non-transitory, tangible computer-readable storage medium on which computer readable instructions of a program are stored, the instructions, when executed by a processor associated with a road vehicle, cause the processor to perform a method, the method comprising:

identifying a base trajectory and a first trajectory, each trajectory including one or more locations, and each trajectory being associated with a particular road vehicle;

selecting a base location from the one or more locations of the base trajectory;

clustering at least one location from the first trajectory, wherein the at least one location is within a threshold distance from the base location;

determining a representative location based on the clustered locations and the base location, the representative location being different from the base location and the clustered locations; and

calculating a new trajectory using the representative location; and

,

automatically steering a third vehicle based on the new trajectory.

19. The medium of claim 18, further comprising:

identifying a second trajectory with one or more locations, wherein the clustered locations includes locations from the second trajectory.

20. The medium of claim 19, wherein the clustered locations includes only one location from the first trajectory and only one location from the second trajectory.