Determining variance factors for complex road segments

• US 10,303,176 B2
• Filed: 10/15/2015
• Issued: 05/28/2019
• Est. Priority Date: 10/15/2015
• Status: Active Grant

• 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
• Primary Examiner(s): Black, Thomas G
• Assistant Examiner(s): Kong, Sze-Hon
• Application Number:
  US14/883,741
• Publication Number:
  US 20170108870A1
• Time in Patent Office: 1,321 Days
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 2556/65 Data transmitted between vehicles
• CPC Class Codes: B60W 60/0013 specially adapted for occupant comfort
• CPC Class Codes: G01C 21/3492 employing speed data or traffic data, e.g. real-time or historical traffic control systems for road vehicles involving transmission of navigation instructions to the vehicle G08G1/0968
• CPC Class Codes: G05D 1/0221 involving a learning process

Abstract

A vehicle computing device includes a data storage medium and a processing circuit. The processing circuit is programmed to receive from the data storage medium, a vehicle characteristic associated with an autonomous vehicle, receive historical data associated with the vehicle characteristic at a first road segment, determine a correction factor for the autonomous vehicle based at least in part on the historical data, and apply the correction factor to the vehicle characteristic to operate the autonomous vehicle in accordance with the historical data.

Claims

1. A vehicle computing device comprising:

a data storage medium; and

a processing circuit programmed to receive from the data storage medium, a vehicle characteristic associated with an autonomous host vehicle, receive historical data associated with the vehicle characteristic at a first road segment, determine a correction factor to apply to the vehicle characteristic based at least in part on the historical data, and apply the correction factor to the vehicle characteristic to operate the autonomous host vehicle in accordance with the historical data,

wherein the correction factor is an amount of correction applied to adjust the vehicle characteristic to a nominal value and wherein the nominal value is crowd-sourced from vehicles other than the autonomous host vehicle, and

wherein the correction factor is a non-linear function of a variance factor, wherein the variance factor is a difference between a magnitude of the vehicle characteristic and the nominal value.

2. The vehicle computing device of claim 1, wherein the processing circuit is programmed to determine the nominal value and a standard deviation of the historical data associated with the first road segment.

3. The vehicle computing device of claim 2, wherein the processing circuit is programmed to determine the variance factor in accordance with the nominal value and the standard deviation.

4. The vehicle computing device of claim 2, wherein the magnitude of the vehicle characteristic includes a magnitude value associated with at least one of a speed control and a steering control, and wherein the processing circuit is programmed to determine the variance factor, at least in part, by comparing the magnitude value to the nominal value.

5. The vehicle computing device of claim 4, wherein the processing circuit is programmed to determine the variance factor, at least in part by comparing the magnitude value to a standard deviation associated with the nominal value and the first road segment.

6. The vehicle computing device of claim 2, wherein the processing circuit is programmed to receive the nominal value from a remote server.

7. The vehicle computing device of claim 1, wherein the processing circuit is programmed to receive historical data associated with the first road segment from a remote server, and wherein the processing circuit is programmed to determine the nominal value from the historical data.

8. The vehicle computing device of claim 1, wherein the vehicle characteristic includes a present vehicle characteristic and wherein the processing circuit is programmed to predict a future vehicle characteristic based at least in part on the present vehicle characteristic.

9. The vehicle computing device of claim 8, wherein the nominal value is one of a first nominal value and a second nominal value, wherein the historical data for the vehicle characteristic at the first road segment includes the first nominal value, and wherein the processing circuit is programmed to receive historical data including the second nominal value for the vehicle characteristic at a second road segment and determine the correction factor based at least in part on the future vehicle characteristic and the second nominal value.

10. A method comprising:

receiving a vehicle characteristic associated with an autonomous host vehicle;

receiving historical data of distributed vehicle characteristics;

determining a nominal value from the historical data, wherein the nominal value is collected from other vehicles and is associated with a first road segment;

determining a correction factor to apply to the vehicle characteristic based at least in part on the historical data, wherein the correction factor is a non-linear function of a variance factor, wherein the variance factor is a difference between a magnitude of the vehicle characteristic and the nominal value; and

applying the correction factor to the vehicle characteristic to autonomously operate the autonomous vehicle in accordance with the historical data, wherein the correction factor is an amount of correction applied to adjust the vehicle characteristic to the nominal value.

11. The method of claim 10, further comprising determining the nominal value and a standard deviation based on the historical data associated with the first road segment.

12. The method of claim 11, wherein the variance factor is determined in accordance with the nominal value and standard deviation.

13. The method of claim 11, wherein the vehicle characteristic includes a magnitude value, and wherein the variance factor is determined, at least in part, by comparing the magnitude value to the nominal value.

14. The method of claim 13, wherein the variance factor is determined, at least in part, by comparing the magnitude value to a standard deviation associated with the nominal value and the first road segment.

15. The method of claim 10, wherein the historical data is received from a remote server.

16. The method of claim 10, wherein the historical data associated with the first road segment is received from a remote server, and wherein the nominal value is determined from the historical data.

17. The method of claim 10, wherein receiving the vehicle characteristic includes receiving a present vehicle characteristic.

18. The method of claim 17, further comprising predicting a future vehicle characteristic based at least in part on the present vehicle characteristic.

19. The method of claim 18, wherein the nominal value is one of a first nominal value and a second nominal value, the method further comprising:

determining the first nominal value associated with the first road segment based on the historical data.

20. The method of claim 19, further comprising:

determining the second nominal value for the vehicle characteristic at a second road segment based at least in part on historical data associated with the second road segment; and

determining the correction factor based at least in part on the future vehicle characteristic and the second nominal value.