RAPID TRAFFIC PARAMETER ESTIMATION

• US 20160379126A1
• Filed: 06/23/2015
• Published: 12/29/2016
• Est. Priority Date: 06/23/2015
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Ozatay, Engin, Filev, Dimitar Petrov, Michelini, John Ottavio
• Granted Patent: US 10,495,469 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G08G 1/0962 having an indicator mounted inside the vehicle, e.g. giving voice messages
• CPC Class Codes: G08G 1/096783 where the origin of the information is a roadside individual element

Abstract

Data about vehicle movement at a stoplight are collected. A stoplight cycle time is predicted with a probability model. The data are compared to the predicted stoplight cycle time. A noise function is applied to the data to generate noise-applied data. The probability model for the predicted stoplight cycle time is updated by scaling the probability model with the noise-applied data to generate a new probability model. A recommended vehicle operation is provided via a network to at least one vehicle computer based on the predicted stoplight cycle time determined by the new probability model.

Claims

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

collect data about vehicle movement at a stoplight;

predict a first stoplight cycle time with a first probability model of the stoplight cycle time, the probability model indicating a first range of probabilities of the first predicted stoplight cycle time for;

compare the collected data to the predicted stoplight cycle time to generate a second probability model, based on the first probability model, that specifies a second range of probabilities of a second predicted stoplight cycle time;

apply a noise function to the collected data to generate noise-applied data;

update the second probability model for the predicted stoplight cycle time by adjusting a set of probabilities of the second probability model with the noise-applied data to generate an updated second probability model; and

provide, via a network to at least one vehicle computer, a recommended vehicle operation based, at least in part, on the predicted stoplight cycle time determined by the updated second probability model.

2. The system of claim 1, wherein the recommended vehicle operation includes recommended driving patterns for reduced fuel usage.

3. The system of claim 2, wherein the recommended driving pattern includes a recommended operating speed determined so that a vehicle reaches the stoplight during a specified portion during the stoplight cycle time.

4. The system of claim 3, wherein the recommended driving pattern includes a route to a destination determined so that the vehicle reaches the stoplight at specified portions of the stoplight cycle time.

5. The system of claim 1, wherein the recommended vehicle operation is determined, at least in part, by the current time.

6. The system of claim 1, wherein the instructions further include instructions to send a notification with the recommended vehicle operation to a handheld user device.

7. The system of claim 1, wherein the instructions further include instructions to determine an offset and a duty cycle for the stoplight based on the stoplight cycle time.

8. The system of claim 1, further comprising a data collector to collect the data on vehicle movement timing.

9. The system of claim 1, wherein the stoplight cycle time is determined, at least in part, by the vehicle movement timing data.

10. The system of claim 1, wherein the probability model is one of a plurality of probability models, each probability model being configured to predict the stoplight time for a specific time range during a day.

11. The system of claim 10, wherein the instructions further include instructions to, if after comparing the data to the predicted stoplight cycle time, the data are not within a threshold of the predicted stoplight time, select the next of the plurality of probability models, predict the stoplight cycle time with the probability model, and compare the data to the new predicted stoplight cycle time.

12. The system of claim 1, wherein the instructions further include instructions to, if none of the plurality of probability models generate a predicted stoplight time for which the data fall within the threshold, generate a new probability model and append to the plurality of probability models.

13. A method, comprising:

collecting data about vehicle movement at a stoplight;

predicting a first stoplight cycle time with a first probability model of the stoplight cycle time, the probability model indicating a first range of probabilities of the first predicted stoplight cycle time for,

comparing the collected data to the predicted stoplight cycle time to generate a second probability model, based on the first probability model, that specifies a second range of probabilities of a second predicted stoplight cycle time;

applying a noise function to the collected data to generate noise-applied data;

updating the second probability model for the predicted stoplight cycle time by adjusting a set of probabilities of the second probability model with the noise-applied data to generate an updated second probability model; and

providing, via a network to at least one vehicle computer, a recommended vehicle operation based, at least in part, on the predicted stoplight cycle time determined by the updated second probability model.

14. The method of claim 13, wherein the recommended vehicle operation includes recommended driving patterns for reduced fuel usage.

15. The method of claim 14, wherein the recommended driving pattern includes a recommended operating speed determined so that a vehicle reaches the stoplight during a specified part of the stoplight cycle time.

16. The method of claim 15, wherein the recommended driving pattern includes a route to a destination determined so that the vehicle reaches the stoplights at specified parts of the stoplight cycle time.

17. The method of claim 13, further comprising determining an offset and a duty cycle for the stoplight based on the stoplight cycle time.

18. The method of claim 13, wherein the probability model is one of a plurality of probability models, each probability model being configured to predict the stoplight time for a specific time range during a day.

19. The method of claim 13, wherein the stoplight cycle time is determined, at least in part, by the vehicle movement timing data.

20. The method of claim 13, wherein the probability model is one of a plurality of probability models, each probability model being configured to predict the stoplight time for a specific time range during a day.