Predicting expected road traffic conditions based on historical and current data

Patent metadata

Field	Value
Publication number	US-9257041-B2
Application number	US-76574210-A
Country	US
Kind code	B2
Filing date	Apr 22, 2010
Priority date	Apr 22, 2009
Publication date	Feb 9, 2016
Grant date	Feb 9, 2016

Abstract

Techniques are described for determining and using information regarding expected road traffic flow conditions information for vehicles traveling on roads. The expected road traffic flow conditions for a particular portion of a road may be generated by combining historical representative information about road traffic flow conditions for that road portion with current information about actual traffic flow on or near that road portion. The combination may, for example, provide benefits for estimating expected traffic flow conditions information for roads with structural flow obstructions that cause reduced traffic flow at certain road locations and times—for example, the expected traffic flow conditions information may be based at least in part on fitting or otherwise adapting partial actual traffic flow information about a vehicle's actual travel path to a historical travel profile for a road that includes representative traffic flow information for various combinations of road locations and time periods.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving information about prior road traffic flow conditions at multiple prior times for an indicated portion of a road having a plurality of locations, the indicated portion of the road having one or more traffic flow obstructions at one or more of the plurality of locations that reduce traffic flow at those one or more locations;
automatically generating, by one or more programmed computing systems, a historical travel profile of the indicated portion of the road based at least in part on the received information about the prior road traffic flow conditions, the generated historical travel profile indicating differing representative traffic flow conditions for a plurality of distinct combinations of the plurality of locations and of multiple time periods;
obtaining information about an actual travel path of a vehicle that previously passed by the plurality of locations of the indicated portion of the road, the obtained information indicating actual traffic flow conditions of the vehicle at a subset of two or more of the plurality of locations of the indicated portion of the road and not indicating actual traffic flow conditions of the vehicle at other locations of the plurality of locations, wherein the other locations include locations between the two or more locations of the subset that the vehicle passed by without a device associated with the vehicle generating a corresponding data sample;
automatically calculating, by at least one of the programmed computing systems, expected traffic flow conditions of the vehicle as it previously passed the other by fitting the actual travel path of the vehicle to the representative traffic flow conditions indicated by the generated historical travel profile; and
providing one or more indications of the automatically calculated expected traffic flow conditions of the vehicle.

2. The method of claim 1 wherein the indicated portion of the road includes a series of multiple defined road links, wherein the received information about the prior road traffic flow conditions includes a plurality of readings from multiple road traffic sensors that each has a location associated with one of the road links, and wherein each of the readings reports an average speed of traffic on the associated road link for one of the road traffic sensors at one of the prior times.

3. The method of claim 2 wherein the obtained information about the actual travel path of the vehicle includes a plurality of data samples that each reports an actual traffic speed of the vehicle at an indicated time and at an indicated associated road location, the data samples being periodically generated by the device associated with the vehicle, and wherein the indicated associated road locations for the plurality of data samples include the two or more locations of the subset.

4. The method of claim 1 wherein the received information about the prior road traffic flow conditions at the multiple prior times includes a plurality of prior traffic flow values that are each associated with one of the prior times and one of the plurality of locations, and wherein the automatic generating of the historical travel profile of the indicated portion of the road includes:
selecting the multiple time periods for use in aggregating the received information about the prior road traffic conditions, the multiple time periods each being based at least in part on time-of-day information;
determining multiple traffic flow aggregation classifications for which representative traffic flow conditions information will be distinctly represented in the generated historical travel profile, each of the traffic flow aggregation classifications corresponding to one of the plurality of distinct combinations and including at least one of the plurality of locations and one of the time periods; and
for each of the traffic flow aggregation classifications, generating representative traffic flow conditions information that represents prior traffic that occurred at the at least one location for the traffic flow aggregation classification during the one time period for the traffic flow aggregation classification, the generating of the representative traffic flow conditions information being based at least in part on aggregating multiple of the prior traffic flow values that are associated with those at least one locations and with one or more prior times to which that one time period corresponds, on determining a typical traffic flow conditions value based on the aggregated prior traffic flow values, and on using the determined typical traffic flow conditions value as the generated representative traffic flow conditions information for the traffic flow aggregation classification.

5. The method of claim 4 wherein the prior traffic flow values each include a traffic speed of one or more vehicles, and wherein the determined typical traffic flow conditions values represent average traffic speeds of multiple vehicles.

6. The method of claim 4 wherein the obtained information indicating the actual traffic flow conditions of the vehicle at the two or more locations includes multiple actual traffic flow conditions values for the vehicle that are each associated with one of the two or more locations and with an indicated time, and wherein the fitting of the actual travel path of the vehicle to the representative traffic flow conditions indicated by the generated historical travel profile includes, for each of at least some of the actual traffic flow conditions values for the vehicle,
determining one of the traffic flow aggregation classifications that includes the associated location for the actual traffic flow conditions value and that includes a time period to which the associated indicated time for the actual traffic flow conditions value corresponds, and retrieving the determined typical traffic flow conditions value for the determined one traffic flow aggregation classification; and
determining a numerical difference between the actual traffic flow conditions value and the retrieved determined typical traffic flow conditions value.

7. The method of claim 6 wherein the fitting of the actual travel path of the vehicle to the representative traffic flow conditions indicated by the generated historical travel profile further includes, for each of one or more of the other locations,
determining one of the multiple time periods to which the other location corresponds for the actual travel path of the vehicle;
identifying one of the traffic flow aggregation classifications that includes the other location and that includes the determined one time period, and retrieving the determined typical traffic flow conditions value for the identified one traffic flow aggregation classification;
adjusting the retrieved determined typical traffic flow conditions value for the identified one traffic flow aggregation classification based at least in part on one or more of the determined numerical differences for the actual traffic flow conditions values; and
selecting the adjusted typical traffic flow conditions value as the expected traffic flow conditions of the vehicle for the other location.

8. The method of claim 4 wherein the fitting of the actual travel path of the vehicle to the representative traffic flow conditions indicated by the generated historical travel profile further includes, for each of one or more of the other locations,
determining one of the multiple time periods to which the other location corresponds for the actual travel path of the vehicle;
identifying one of the traffic flow aggregation classifications that includes the other location and that includes the determined one time period, and retrieving the determined typical tra

Assignees

• Scofield Christopher Laurence
• Cahn Robert C
• Hersch Jesse
• Stoppler Wayne
• Yakich Valerie Raybold
• Barker Alec
• Inrix Inc

Inventors

• Scofield Christopher Laurence
• Cahn Robert C
• Hersch Jesse
• Stoppler Wayne
• Yakich Valerie Raybold
• Huang Te-Ming
• Barker Alec

Classifications

• G08G1/0104 Primary

  Measuring and analyzing of parameters relative to traffic conditions · CPC title

• G08G1/01 Primary

  Detecting movement of traffic to be counted or controlled (G08G1/07 - G08G1/14 take precedence) · CPC title