System and method for generating and communicating lane information from a host vehicle to a vehicle-to-vehicle network

Patent metadata

Field	Value
Publication number	US-10282997-B2
Application number	US-201615197924-A
Country	US
Kind code	B2
Filing date	Jun 30, 2016
Priority date	Jul 20, 2015
Publication date	May 7, 2019
Grant date	May 7, 2019

Abstract

A method of generating and communicating lane information from a host vehicle to a vehicle-to-vehicle (V2V) network includes collecting visual data from a camera, detecting a lane within the visual data, generating a lane classification for the lane based on the visual data, assigning a confidence level to the lane classification, generating a lane distance estimate from the visual data, generating a lane model from the lane classification and the lane distance estimate, and transmitting the lane model and the confidence level to the V2V network.

First claim

What is claimed is:

1. A method of generating and communicating lane information from a host vehicle to a vehicle-to-vehicle (V2V) network, the method comprising:
collecting visual data from a camera;
detecting a lane within the visual data;
generating a lane classification for the lane based on the visual data;
assigning a confidence level to the lane classification;
generating a lane distance estimate from the visual data;
generating a lane model from the lane classification and the lane distance estimate;
scanning a predetermined area for remote V2V equipped vehicles within a predefined range of the host vehicle; and
transmitting the lane model and the confidence level to the V2V network immediately upon determining that the remote V2V equipped vehicle is within the predefined range of the host vehicle.

2. The method of claim 1 wherein the camera comprises a front camera mounted to a front-facing surface of the host vehicle.

3. The method of claim 1 wherein the detecting a plurality of lanes further comprises determining a position, a width, a curvature, a topography, a distance of each of the plurality of lanes relative to a reference position on the host vehicle, and a color and a shape of a plurality of lane markers for the plurality of lanes.

4. The method of claim 3 wherein the generating a lane classification further comprises comparing the color and the shape of the plurality of lane markers to a library of colors and shapes of known lane markers.

5. The method of claim 1 wherein the generating a lane distance estimate further comprises mathematically interpolating from the visual data the distance from a lane edge relative to a reference position on the host vehicle.

6. The method of claim 1 wherein the V2V network includes at least one remote V2V equipped vehicle.

7. The method of claim 1 wherein transmitting the lane model and confidence level further comprises periodically transmitting the lane model and confidence level over the V2V network.

8. A method of generating and communicating lane information from a host to data vehicle-to-vehicle (V2V) network, the method comprising:
optically scanning a predefined area of road surface surrounding the host vehicle;
tracking a plurality of lanes;
detecting target V2V equipped vehicles;
encoding information about the plurality of lanes into a mathematical lane model;
determining for which of any target vehicles the mathematical lane model is relevant; and
communicating the mathematical model over the V2V network to the relevant target vehicles immediately as the relevant target vehicles are identified.

9. The method of claim 8 wherein the optically scanning further comprises collecting optical data from a plurality of cameras mounted to the host vehicle.

10. The method of claim 9 wherein the tracking a plurality of lanes further comprises determining a position, a width, a curvature, a topography, a distance of each of the plurality of lanes relative to a reference position on the host vehicle, and a color and a shape of a plurality of lane markers for the plurality of lanes.

11. The method of claim 10 wherein the tracking further comprises comparing the color and the shape of the plurality of lane markers to a library of colors and shapes of known lane markers.

12. The method of claim 8 wherein the detecting target V2V equipped vehicles comprises transmitting V2V data packets and receiving V2V data packets sent by remote V2V equipped vehicles over the V2V network.

13. The method of claim 12 wherein the communicating the mathematical lane model further comprises encoding the mathematical lane model to create an encoded mathematical lane model that conforms to a communications protocol and transmitting the encoded mathematical lane model over the V2V network.

14. A system for generating and communicating lane information from a host vehicle to a vehicle-to-vehicle (V2V) network, the system comprising:
a camera;
a V2V sub-system having a receiver and a transmitter;
a controller in communication with the camera and the V2V sub-system, the controller having memory for storing control logic and a processor configured to execute the control logic, the control logic including a first control logic for collecting visual data from the camera, a second control logic for detecting a lane within the visual data, a third control logic for generating a lane classification for the lanes based on the visual data, a fourth control logic for assigning a base confidence level to the lane classification, a fifth control logic for generating a lane distance estimate from the visual data, a sixth control logic for generating a base lane model from the lane classification and the lane distance estimate, a seventh control logic for generating a formatted lane model and a formatted confidence level, an eighth control logic for determining for which of any target vehicles the formatted lane model is relevant by analyzing the formatted lane model with respect to locational information retrieved by the V2V sub-system about each of the target vehicles, the locational information including global positioning system (GPS) location information, heading information, and speed information, and a ninth control logic for immediately transmitting the formatted lane model and the confidence level to the relevant target vehicles in the V2V network.

15. The system of claim 14 wherein the camera comprises a plurality of cameras attached to the host vehicle.

16. The system of claim 15 wherein the base and formatted lane models comprise lane positioning, lane markings, lane curvature, speed, and trajectory data for the host vehicle.

17. The system of claim 16 wherein the seventh control logic further comprises aligning the base lane model and base confidence level to a standardized communications protocol.

18. The method of claim 1 further comprising:
determining which of the remote vehicles in the V2V network the lane model is relevant by analyzing the lane model with respect to locational information about each of the remote vehicles, wherein the locational information may include global positioning system (GPS) location information, heading information, or speed information pertaining to each of the remote vehicles, and
wherein transmitting the lane model and the confidence level to the V2V network immediately upon determining that the remote V2V equipped vehicle is within the predefined range of the host vehicle includes immediately transmitting the lane model and the confidence level to the relevant remote vehicles.

19. The method of claim 8 wherein determining for which of any target vehicles the mathematical lane model is relevant includes analyzing the mathematical lane model with respect to locational information about each of the target vehicles, the locational information including global positioning system (GPS) location information, heading information, and speed information.

Assignees

• Dura Operating Llc

Inventors

• Gignac Donald Raymond
• Thompson Aaron Evans
• Siddiqui Danish Uzair
• Patil Rajashekhar
• Thomas Gordon M

Classifications

• G06F18/2413

  based on distances to training or reference patterns · CPC title

• H04W4/46

  for vehicle-to-vehicle communication [V2V] · CPC title

• H04W4/025

  using location based information parameters · CPC title

• G08G1/167 Primary

  Driving aids for lane monitoring, lane changing, e.g. blind spot detection · CPC title

• G08G1/163

  involving continuous checking · CPC title