Adaptive traffic dynamics prediction

• US 10,127,809 B2
• Filed: 12/18/2017
• Issued: 11/13/2018
• Est. Priority Date: 02/10/2014
• Status: Active Grant

• Current Assignee: HERE Global B.V. (Nokia Corporation)
• Original Assignee: HERE Global B.V. (Nokia Corporation)
• Inventors: Macfarlane, Jane, Grossman, Robert, Bennett, Collin, Pivarski, James
• Primary Examiner(s): Lau, Hoi
• Application Number:
  US15/845,197
• Publication Number:
  US 20180108251A1
• Time in Patent Office: 330 Days
• Field of Search: 340936, 340906, 340907, 34099513, 340910, 340917, 340931, 701201, 701117-119, 701202, 701200, 701204, 701 1
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0116 from roadside infrastructure, e.g. beacons
• CPC Class Codes: G08G 1/012 from other sources than vehicle or roadside beacons, e.g. mobile networks
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0141 for traffic information dissemination
• CPC Class Codes: H05K 999/99 dummy group

Abstract

The disclosed embodiments relate to prediction of traffic dynamics. A descriptive model is provided that uses historical probe data to create “tidal-like” patterns for the usual dynamics on the road network and creates a framework for taking a future time, e.g. in terms of month, day, time, and suggesting a typical speed for the specified road network link at that specific time. With this model, better predictions for estimated time of arrival will be derived. As opposed to blindly extrapolating from a static model, the disclosed embodiments dynamically adapt to current conditions using real time data to adapt, based on current conditions, the model from which a predicted speed may be determined.

Claims

1. A computer implemented method comprising:

storing, by a processor in a database stored in a memory coupled with the processor, data indicative of a historical model of traffic conditions of a road network, the historical model comprising a set of patterns indicative of traffic conditions that have occurred during a prior time period for different portions of the road network, wherein the set of patterns include subsets of at least two patterns for the same portion of the road network and the same portion of the prior time period, each of the at least two patterns of a subset defining different traffic conditions that have occurred on the portion of the road network at the portion of the prior time period;

predicting, by the processor based on the historical model, traffic conditions for at least a portion of the road network for a future time period, the predicting further comprising;

adapting, by the processor, the historical model, to account for current traffic conditions along at least the portion of the road network, the adapting comprising obtaining, by the processor, data indicative of real-time traffic conditions along at least the portion of the road network, identifying, by the processor based on the future time period, the subset of the at least two patterns for the particular portion of the road network applicable to the future time period, and selecting, by the processor, one of the at least two patterns of the identified subset based on the obtained data indicative of real-time traffic conditions, wherein different real-time traffic conditions result in selection of a different one of the at least two patterns of the identified subset.

2. The computer implemented method of claim 1 wherein the traffic conditions that have occurred on the portion of the road network at the portion of the prior time period comprise data indicative of observed travel speeds along the portion of the road network at the portion of the prior time period.

3. The computer implemented method of claim 1 wherein each subset comprises patterns indicative of the most frequently occurring traffic conditions along the portion of the road network at the portion of the prior time period.

4. The computer implemented method of claim 1 wherein the adapting further comprises calculating the future time period as an estimated arrival time at the portion of the road network based on a prior prediction of traffic conditions by the processor for another portion of the road network ahead of at least the portion of the road network.

5. The computer implemented method of claim 1 wherein the future time period comprises a calendar date and time of day.

6. The computer implemented method of claim 1 wherein at least the portion of the road network is at least part of a route between a starting location and a destination.

7. The computer implemented method of claim 1 wherein the obtained real-time traffic conditions are derived from one or more traffic data sources which have recently collected traffic data for at least the portion of the road network.

8. The computer implemented method of claim 1 wherein the future time period comprises a future occurrence of a recurring time period, each of the at least two patterns of each subset comprising a speed profile for each of a plurality of frequently recurring travel speed patterns observed during prior occurrences of the recurring time period.

9. The computer implemented method of claim 1 wherein the selecting further comprises computing a weighted average of the at least two patterns of the subset based on the obtained data indicative of real-time traffic conditions.

10. The computer implemented method of claim 1 wherein the selecting further comprises selecting the one of the at least two patterns of the identified subset based on a best fit of the obtained data indicative of real-time traffic conditions.

11. A system comprising:

a processor and a memory coupled therewith;

a database stored in the memory, the database comprising data indicative of a historical model of traffic conditions of a road network, the historical model comprising a set of patterns indicative of traffic conditions that have occurred during a prior time period for different portions of the road network, wherein the set of patterns include subsets of at least two patterns for the same portion of the road network and the same portion of the prior time period, each of the at least two patterns of a subset defining different traffic conditions that have occurred on the portion of the road network at the portion of the prior time period;

logic stored in the memory and executable by the processor to cause the processor to predict, based on the historical model, traffic conditions for at least a portion of the road network for a future time period, the logic being further executable by the processor to cause the processor to adapt the historical model to account for current traffic conditions along at least the portion of the road network via acquisition of data indicative of real-time traffic conditions along at least the portion of the road network, identification, based on the future time period, the subset of the at least two patterns for the particular portion of the road network applicable to the future time period, and selection of one of the at least two patterns of the identified subset based on the obtained data indicative of real-time traffic conditions, wherein different real-time traffic conditions result in selection of a different one of the at least two patterns of the identified subset.

12. The system of claim 11 wherein the traffic conditions that have occurred on the portion of the road network at the portion of the prior time period comprise data indicative of observed travel speeds along the portion of the road network at the portion of the prior time period.

13. The system of claim 11 wherein each subset comprises patterns indicative of the most frequently occurring traffic conditions along the portion of the road network at the portion of the prior time period.

14. The system of claim 11 wherein the logic is further executable by the processor to cause the processor to calculate the future time period as an estimated arrival time at the portion of the road network based on a prior prediction of traffic conditions by the processor for another portion of the road network ahead of at least the portion of the road network.

15. The system of claim 11 wherein the future time period comprises a calendar date and time of day.

16. The system of claim 11 wherein at least the portion of the road network is at least part of a route between a starting location and a destination.

17. The system of claim 11 wherein the obtained real-time traffic conditions are derived from one or more traffic data sources which have recently collected traffic data for at least the portion of the road network.

18. The system of claim 11 wherein the future time period comprises a future occurrence of a recurring time period, each of the at least two patterns of each subset comprising a speed profile for each of a plurality of frequently recurring travel speed patterns observed during prior occurrences of the recurring time period.

19. The system of claim 11 wherein the logic is further executable by the processor to cause the processor to compute a weighted average of the at least two patterns of the subset based on the obtained data indicative of real-time traffic conditions.

20. The system of claim 11 wherein t the logic is further executable by the processor to cause the processor to select the one of the at least two patterns of the identified subset based on a best fit of the obtained data indicative of real-time traffic conditions.

21. A system comprising:

a historical model of traffic conditions of a road network, the historical model comprising a set of patterns indicative of traffic conditions that have occurred during a prior time period for different portions of the road network, wherein the set of patterns include subsets of at least two patterns for the same portion of the road network and the same portion of the prior time period, each of the at least two patterns of a subset defining different traffic conditions that have occurred on the portion of the road network at the portion of the prior time period;

a traffic dynamics predictor coupled with the historical model and operative to predict, based on the historical model, traffic conditions for at least a portion of the road network for a future time period, the traffic dynamics predictor being further operative to adapt the historical model to account for current traffic conditions along at least the portion of the road network via acquisition of data indicative of real-time traffic conditions along at least the portion of the road network, identification, based on the future time period, the subset of the at least two patterns for the particular portion of the road network applicable to the future time period, and selection of one of the at least two patterns of the identified subset based on the obtained data indicative of real-time traffic conditions, wherein different real-time traffic conditions result in selection of a different one of the at least two patterns of the identified subset.