IP Library › Granted Patent US 11,499,833
Granted Patent B2
US 11,499,833 · App. 16/582,672 · Granted Nov 15, 2022

Inferring lane boundaries via high speed vehicle telemetry

Inventors: Orhan Bulan (Novi, MI); Sheetal Mahesh (Pflugerville, TX); Yehenew G. Mengistu (Sterling Heights, MI); David H. Clifford (Royal Oak, MI)
Assignee: GM Global Technology Operations LLC
G01C21/32G06T7/70G06T19/006G06V20/588H04W4/44G06T2207/30256
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,499,833
App. No.
16/582,672
Granted
Nov 15, 2022
Kind
B2
Abstract

A system for inferring lane boundaries via vehicle telemetry for a road section is provided. The system includes a computerized remote server device operable to receive through a communications network sensor data describing lane markings upon roads bordering the road section, determine established lanes upon roads bordering the road section based upon the sensor data, receive through the communications network the vehicle telemetry generated by a plurality of vehicles traversing the road section, generate inferred lanes for the road section based upon the vehicle telemetry, match the inferred lanes to the established lanes to generate unified lane geometries, and publish the unified lane geometries.

Claims (50)

1. A system for inferring lane boundaries via vehicle telemetry for a road section, comprising:

a computerized remote server device operable to:

receive through a communications network sensor data describing lane markings upon roads bordering the road section, wherein the lane markings indicate lane geometries intersecting the road section;

determine established lanes upon roads bordering the road section based upon the lane markings described by the sensor data;

receive through the communications network the vehicle telemetry generated by a plurality of vehicles traversing the road section;

generate inferred lanes for the road section based upon the vehicle telemetry;

match the inferred lanes to the established lanes to generate unified lane geometries; and

publish the unified lane geometries.

2. The system of claim 1 , wherein generating the inferred lanes for the road section based upon the vehicle telemetry comprises aggregating the vehicle telemetry.

3. The system of claim 2 , wherein generating the inferred lanes for the road section based upon the vehicle telemetry further comprises normalizing the vehicle telemetry.

4. The system of claim 3 , wherein generating the inferred lanes for the road section based upon the vehicle telemetry further comprises denoising the vehicle telemetry.

5. The system of claim 4 , wherein generating the inferred lanes for the road section based upon the vehicle telemetry further comprises converting the vehicle telemetry to normal vectors representing vehicle paths.

6. The system of claim 1 , wherein generating the inferred lanes for the road section based upon the vehicle telemetry comprises identifying trajectories that originate from each of the established lanes entering the road section, analyzing the trajectories across the road section, and selecting a most common trajectory that originates from each of the established lanes as an inferred lane for the road section.

7. The system of claim 1 , wherein the computerized remote server device is further operable to identify the road section as a road section including insufficient lane markings to determine the established lanes.

8. The system of claim 1 , wherein the computerized remote server device is further operable to identify the road section as a road section including obscured lane markings.

9. The system of claim 1 , further comprising a vehicle navigating across the road section based upon one of the unified lane geometries.

10. The system of claim 1 , wherein generating the inferred lanes for the road section based upon the vehicle telemetry comprises adjusting a lane boundary for one of the inferred lanes based upon a lane boundary for a second of the inferred lanes.

11. A system for generating inferred lanes for a road section, comprising:

a vehicle comprising a computerized navigation control module operable to:

generate vehicle telemetry for the vehicle; and

transmit the vehicle telemetry over a communications network;

a computerized remote server device operable to:

receive through the communications network sensor data describing lane markings upon roads bordering the road section, wherein the lane markings indicate lane geometries intersecting the road section;

determine established lanes upon roads bordering the road section based upon the lane markings described by the sensor data;

receive through the communications network vehicle telemetry generated by a plurality of vehicles traversing the road section;

generate inferred lanes for the road section based upon the vehicle telemetry;

match the inferred lanes to the established lanes to generate a unified lane geometry; and

transmit through the communications network the unified lane geometry to the vehicle; and

wherein the computerized navigation control module is further operable to:

receive the unified lane geometry; and

navigate the vehicle across the road section based upon unified lane geometry.

12. The system of claim 11 , wherein generating the inferred lanes for the road section based upon the vehicle telemetry comprises aggregating the vehicle telemetry, normalizing the vehicle telemetry, and denoising the vehicle telemetry.

13. The system of claim 12 , wherein generating the inferred lanes for the road section based upon the vehicle telemetry further comprises converting the vehicle telemetry to normal vectors representing vehicle paths.

14. The system of claim 11 , wherein generating the inferred lanes for the road section based upon the vehicle telemetry comprises identifying trajectories that originate from each of the established lanes entering the road section, analyzing the trajectories across the road section, and selecting a most common trajectory that originates from each of the established lanes as an inferred lane for the road section.

15. A system for generating inferred lanes for a road section, comprising:

a computerized remote server device operable to:

receive through a communications network sensor data describing lane markings upon roads bordering the road section, wherein the lane markings indicate lane geometries intersecting the road section;

determine established lanes upon roads bordering the road section based upon the lane markings described by the sensor data;

receive through the communications network vehicle telemetry generated by a plurality of vehicles traversing the road section;

generate inferred lanes for the road section based upon the vehicle telemetry;

match the inferred lanes to the established lanes to generate unified lane geometries; and

transmit the unified lane geometries over the communications network; and

a remote computing platform operable to:

receive the unified lane geometries; and

provide navigation guidance based upon the unified lane geometries.

16. The system of claim 15 , wherein the remote computing platform comprises a smart phone.

17. The system of claim 15 , wherein the remote computing platform comprises a virtual reality device.

18. The system of claim 15 , wherein the remote computing platform comprises an augmented reality device.

19. The system of claim 15 wherein the remote computing platform comprises an infrastructure device.

20. The system of claim 19 , wherein providing navigation guidance based upon the unified lane geometries comprises projecting graphics upon the road section.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 10, 2019
From: BULAN, ORHAN; MAHESH, SHEETAL; MENGISTU, YEHENEW G.; CLIFFORD, DAVID H.
To: GM GLOBAL TECHNOLOGY OPERATIONS LLC
Reel/Frame 050682/0134 →
Continuity (1)
Related Publication 20210088340A1 · Mar 25, 2021
Cited By (1)
US 12,631,458