Autonomous vehicle object detection

• US 10,095,238 B2
• Filed: 12/14/2016
• Issued: 10/09/2018
• Est. Priority Date: 12/14/2016
• Status: Expired due to Fees

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Miller, Kenneth James, Martin, Douglas Raymond, Dudar, Aed M., Perkins, William Paul
• Primary Examiner(s): Shaawat, Mussa A
• Application Number:
  US15/378,934
• Publication Number:
  US 20180164833A1
• Time in Patent Office: 664 Days
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 2556/65 Data transmitted between vehicles
• CPC Class Codes: B60W 2720/10 Longitudinal speed
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/10 Path keeping cruise control for automatically following a preceding vehicle B60W30/165
• CPC Class Codes: B60W 40/04 Traffic conditions
• CPC Class Codes: B60W 50/038 Limiting the input power, torque or speed
• CPC Class Codes: G05D 1/0077 using redundant signals or controls
• CPC Class Codes: G05D 1/0251 extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision stereoscopic image analysis H04N13/00; depth recovery from images G06T7/593
• CPC Class Codes: G05D 1/028 using a RF signal
• CPC Class Codes: G08G 1/163 involving continuous checking
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

A computer in a vehicle can determine a first distance from a vehicle to a traffic object and receive, via a network interface, a second distance from a second vehicle to the traffic object and a third distance from the second vehicle to the vehicle. The computer can determine a fourth distance by triangulation based on the second distance and the third distance and pilot the vehicle based on combining the first distance and the fourth distance.

Claims

1. A method, comprising:

determining a first distance from a first vehicle to a traffic object;

receiving, via a network interface, a second distance from a second vehicle to the traffic object and a third distance from the second vehicle to the first vehicle;

determining a fourth distance by triangulation based on the second distance and the third distance;

piloting the first vehicle based on combining the first and fourth distances;

receiving, via the network interface, one or more additional second distances from one or more additional second vehicles to the traffic object, and one or more additional third distances from one or more additional second vehicles to the first vehicle;

determining an average fourth distance and a standard deviation based on the second distance, the additional second distances, the third distance, and the additional third distances; and

piloting the first vehicle based on combining the first distance, the average fourth distance and the standard deviation.

2. The method of claim 1, wherein the traffic object is one or more of a roadway, a barrier, an abutment, a pillar, a sign, a post, a railing, a signal, a marking, a parked vehicle and a moving vehicle.

3. The method of claim 1 wherein the network interface includes a local area network and the Internet.

4. The method of claim 1 wherein the first distance, second distances, third distances and fourth distances are determined as vector distances.

5. The method of claim 1 wherein combining the first distance with the fourth distance includes comparing the first distance with the fourth distance and, if the first and fourth distances differ, selecting the distance associated with a higher accuracy value.

6. The method of claim 1, further comprising:

determining probability functions based on the second distances and determined sizes and angles of the traffic object relative to the second vehicles; and

combining the probability functions and the third distances to determine the average fourth distance and the standard deviation.

7. The method of claim 6, wherein the probability functions are adapted based on accuracy values.

8. The method of claim 1, wherein piloting the vehicle includes slowing down proportionally to output of an error function based on combining the first distance with the average fourth distance and the standard deviation.

9. The method of claim 8, wherein slowing down proportionally to the error function includes comparing the error function to a predetermined threshold, and, if the error function exceeds the predetermined threshold, reducing speed proportional to the error function.

17. The apparatus of claim 1, wherein pilot the vehicle includes slowing down proportionally to output of an error function based on combining the first distance with the average fourth distance and the standard deviation.

18. The apparatus of claim 17, wherein slowing down proportionally to the error function includes comparing the error function to a predetermined threshold, and, if the error function exceeds the predetermined threshold, reducing speed proportional to the error function.

10. An apparatus, comprising:

a processor; and

a memory, the memory storing instructions executable by the processor to;

determine a first distance from a vehicle to a traffic object;

receive, via a network interface, a second distance from a second vehicle to the traffic object and a third distance from the second vehicle to the vehicle;

determine a fourth distance by triangulation based on the second distance and the third distance;

pilot the vehicle based on combining the first distance and the fourth distance;

receive, via the network interface, one or more additional second distances from one or more additional second vehicles to the traffic object, and one or more additional third distances from one or more additional second vehicles to the vehicle;

determine an average fourth distance and a standard deviation based on the second distance, the additional second distances, the third distance, and the additional third distances; and

pilot the vehicle based on combining the first distance, the average fourth distance and the standard deviation.

11. The apparatus of claim 10, wherein the traffic object is one or more of a roadway, a barrier, an abutment, a pillar, a sign, a post, a railing, a signal, a marking, a parked vehicle and a moving vehicle.

12. The apparatus of claim 10 wherein the network interface includes a local area network and the Internet.

13. The apparatus of claim 10 wherein the first distance, second distances, third distances and fourth distances are determined as vector distances.

14. The apparatus of claim 10 wherein combining the first distance with the fourth distance includes comparing the first distance with the fourth distance and, if the first and fourth distances differ, selecting the distance associated with a higher accuracy value.

15. The apparatus of claim 10, further comprising:

determine probability functions based on the second distances and determined sizes and angles of the traffic object relative to the second vehicles; and

combine the probability functions and the third distances to determine the average fourth distance and the standard deviation.

16. The apparatus of claim 15, wherein the probability functions are adapted based on accuracy values.