Vehicle lane map estimation

• US 10,121,367 B2
• Filed: 04/29/2016
• Issued: 11/06/2018
• Est. Priority Date: 04/29/2016
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Jammoussi, Hassene, Kumar, Pankaj
• Primary Examiner(s): Smith, Jelani A
• Assistant Examiner(s): Williams, Kelly D
• Application Number:
  US15/142,183
• Publication Number:
  US 20170316684A1
• Time in Patent Office: 921 Days
• Field of Search: None
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G01C 21/3602 Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0125 Traffic data processing
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0141 for traffic information dissemination
• CPC Class Codes: G08G 1/096716 where the received information does not generate an automatic action on the vehicle control
• CPC Class Codes: G08G 1/096725 where the received information generates an automatic action on the vehicle control
• CPC Class Codes: G08G 1/096775 where the origin of the information is a central station

Abstract

A computer can receive, from a vehicle sensor, data about a plurality of second vehicles, define two or more vehicle clusters based on location data of second vehicles, each cluster including two or more of the second vehicles determined to be traveling in a same lane, identify two or more lane boundaries according to clusters, and use lane boundaries to generate a lane map.

Claims

1. A method, comprising:

receiving data, in a first vehicle from each of a plurality of second vehicles, including;

a respective second vehicle geolocation and a second vehicle lateral distance from a lane boundary;

defining two or more vehicle clusters based on the received data, each cluster including two or more second vehicles determined to be traveling in a same lane;

using the defined two or more vehicle clusters, to identify two or more lane boundaries based at least in part on the received respective second vehicle lateral distance from the lane boundary; and

using the identified two or more lane boundaries to generate a lane map.

2. The method of claim 1, wherein defining two or more vehicle clusters further includes:

determining a lane width based on distances of the second vehicles from one another; and

assigning, to a cluster, second vehicles determined to be traveling in a same lane based on the distances of the second vehicles from one another.

3. The method of claim 2, wherein defining two or more vehicle clusters further includes determining a lane curvature.

4. The method of claim 3, wherein determining the lane curvature includes fitting a curve to a plurality of travelled locations of a second vehicle.

5. The method of claim 3, wherein determining the lane curvature is at least based on a statistical forecast of the lane curvature.

6. The method of claim 3, further comprising receiving a yaw angle of the first vehicle, wherein determining the lane curvature is based at least in part on the yaw angle of the first vehicle.

7. The method of claim 2, further comprising:

receiving a geolocation of the first vehicle; and

determining a vehicle cluster that includes the first vehicle.

8. The method of claim 2, further comprising:

generating an updated lane map based on updated vehicle clusters; and

broadcasting the updated lane map to a stationary server.

9. The method of claim 8, wherein generating the updated lane map includes at least one of changing a lane width and changing a number of lanes.

10. The method of claim 8, wherein defining the vehicle clusters is further based on traffic data.

11. The method of claim 8, wherein defining the vehicle clusters is further based on road construction data.

12. A system comprising a computer including a processor and a memory, the memory storing instructions such that the processor is programmed to:

receive, from a vehicle sensor, data about a plurality of second vehicles;

define two or more vehicle clusters based on location data, each cluster including two or more of the second vehicles determined to be traveling in a same lane;

identify two or more lane boundaries, based at least in part on a received respective second vehicle lateral distance from a lane boundary, according to the defined two or more vehicle clusters; and

using the identified two or more lane boundaries to generate a lane map.

13. The system of claim 12, wherein defining two or more vehicle clusters further includes:

determining a lane width based on distances of the second vehicles from one another; and

assigning, to a cluster, second vehicles determined to be traveling in a same lane based on the distances of the second vehicles from one another.

14. The system of claim 12, wherein defining two or more vehicle clusters further includes determining a lane curvature.

15. The system of claim 14, wherein determining the lane curvature includes fitting a curve to a plurality of travelled locations of a second vehicle.

16. The system of claim 14, wherein determining the lane curvature is at least based on a statistical forecast of the lane curvature.

17. The system of claim 14, further comprising a yaw rate sensor operable to determine a yaw angle of a vehicle, wherein determining the lane curvature is based at least in part on the yaw angle of the vehicle.