Vehicle collision avoidance

• US 10,629,079 B2
• Filed: 12/05/2016
• Issued: 04/21/2020
• Est. Priority Date: 12/05/2016
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Perez Barrera, Oswaldo, Jimenez Hernandez, Alvaro
• Primary Examiner(s): Lin, Abby Y
• Assistant Examiner(s): Torchinsky, Edward
• Application Number:
  US15/368,926
• Publication Number:
  US 20180158334A1
• Time in Patent Office: 1,233 Days
• Field of Search: None
• CPC Class Codes: B60Q 9/008 for anti-collision purposes
• CPC Class Codes: B60R 2300/804 for lane monitoring
• CPC Class Codes: B60R 2300/8093 for obstacle warning
• CPC Class Codes: B60W 2552/00 Input parameters relating to infrastructure
• CPC Class Codes: B60W 2552/30 Road curve radius
• CPC Class Codes: B60W 2552/35 Road bumpiness, e.g. potholes
• CPC Class Codes: B60W 2554/4041 Position
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 30/165 Automatically following the path of a preceding lead vehicle, e.g. "electronic tow-bar"
• CPC Class Codes: B62D 15/0265 Automatic obstacle avoidance by steering
• CPC Class Codes: B62D 6/001 the torque NOT being among the input parameters
• CPC Class Codes: G01S 19/01 Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
• CPC Class Codes: G05D 1/0253 extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow determining position or orientation from images G06T7/70
• CPC Class Codes: G06V 10/443 by matching or filtering
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G08G 1/16 Anti-collision systems road vehicle drive control systems for predicting or avoiding probable or impending collision otherwise than by control of a particular sub-unit B60W30/08
• CPC Class Codes: G08G 1/165 for passive traffic, e.g. including static obstacles, trees
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

A computer, programmed to: receive image data from a vehicle sensor; associate a plurality of geometric shapes with the image data of a target vehicle; monitor the plurality of geometric shapes for a condition indicative of the target vehicle moving to avoid a roadway obstacle; and in response to the condition, provide a steering instruction to avoid the obstacle.

Claims

1. A computer, comprising a processor and memory storing instructions executable by the processor, the instructions comprising, to:

receive image data from a vehicle sensor;

associate a plurality of geometric shapes with the image data of a target vehicle;

using the image data, monitor the plurality of geometric shapes for a first condition indicative of the target vehicle moving to avoid a roadway obstacle;

using the image data, monitor for a second condition also indicative of the target vehicle moving to avoid the roadway obstacle; and

in response to determining the first and second conditions, provide a steering instruction to avoid the obstacle,

wherein the second condition is an absence of an indicator signal actuation at the target vehicle prior to or during the determination of the target vehicle moving to avoid the roadway obstacle.

2. The computer of claim 1, wherein the plurality of geometric shapes include a first geometric shape associated with an upper rear portion of the target vehicle and a second geometric shape associated with a lower rear portion of the target vehicle.

3. The computer of claim 2, wherein at least one of the first and second geometric shapes is a rectangle.

4. The computer of claim 1, further programmed to map at least a portion of each of the plurality of geometric shapes to a peripheral outline of a rear view of the target vehicle.

5. The computer of claim 1, wherein the first condition is associated with a relative displacement of the plurality of geometric shapes within two or more frames of image data.

6. The computer of claim 5, wherein the relative displacement is in a lateral direction.

7. The computer of claim 1, wherein the instructions further comprise to:

monitor for the first condition by using global positioning data to determine whether a portion of the roadway is straight or curved, wherein the portion is associated with a region where the target vehicle moved to avoid the roadway obstacle.

8. A process, comprising:

receiving image data of a target vehicle from a sensor;

associating at least two geometric shapes with the image data;

using the image data, monitoring the at least two geometric shapes for a first condition indicative of the target vehicle moving to avoid a roadway obstacle;

using the image data, monitoring for a second condition also indicative of the target vehicle moving to avoid the roadway obstacle; and

in response to determining the first and second conditions, providing a steering instruction to avoid the obstacle,

wherein the second condition comprises an absence of an indicator signal actuation at the target vehicle prior to or during the determination of the target vehicle swerving to avoid the roadway obstacle.

9. The process of claim 8, wherein the at least two geometric shapes include a first geometric shape associated with an upper rear portion of the target vehicle and a second geometric shape associated with a lower rear portion of the target vehicle.

10. The process of claim 9, wherein at least one of the first and second geometric shapes is a rectangle.

11. The process of claim 8, wherein associating further comprises mapping at least a portion of each of the at least two geometric shapes to a peripheral outline of a rear view of the target vehicle.

12. The process of claim 8, wherein the determination of the first condition is associated with a relative displacement of the at least two geometric shapes within two or more frames of image data.

13. The process of claim 12, wherein the relative displacement is in a lateral direction.

14. The process of claim 8, wherein monitoring for the first condition further comprises:

using global positioning data, determining whether a portion of the roadway is straight or curved, wherein the portion is associated with a region where the target vehicle moved to avoid the roadway obstacle.

15. A process, comprising:

receiving, in a first vehicle, a plurality of data frames from a sensor in the first vehicle;

determining that a second vehicle is located in front of the first vehicle;

generating a plurality of geometric images associated with a shape of a rear view of the second vehicle, the plurality of geometric images including a first geometric image associated with an upper rear portion of the second vehicle and a second geometric image associated with a lower rear portion thereof;

monitoring the generated first and second geometric images; and

providing a steering control instruction from the processor that causes the first vehicle to follow the second vehicle and also avoid a roadway obstacle when;

(a) the generated first and second geometric images move laterally with respect to another object within the plurality of data frames, and

(b) an absence of an indicator signal actuation is determined when the generated first and second geometric images move laterally,

wherein the steering control instruction is provided independent of the first vehicle identifying the roadway obstacle.

16. The process of claim 15, wherein at least one of the first and second geometric images is a rectangle.

17. The process of claim 15, wherein generating further comprises mapping at least a portion of each of the first and second geometric images to a peripheral outline of a rear view of the second vehicle.

18. The process of claim 15, wherein the steering instruction is provided at least partially in response to the determined absence.