SENSING AND PREDICTING FLOW VARIANCE IN A TRAFFIC SYSTEM FOR TRAFFIC ROUTING AND SENSING

• US 20090002195A1
• Filed: 06/29/2007
• Published: 01/01/2009
• Est. Priority Date: 06/29/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Horvitz, Eric J., Srinivasan, Sridhar
• Granted Patent: US 7,948,400 B2
• Time in Patent Office: Days
• US Class Current: 340/934
• CPC Class Codes: G08G 1/0104 Measuring and analyzing of parameters relative to traffic conditions

Abstract

Methods for decision making about sensor location/configuration for traffic sensing and routing are described. Construction of predictive models via machine learning that infer variance of road speeds, in general or for specific contexts (e.g., rush hours for a traffic system) occurs. The predictive models for road reliability are built from libraries of data about sensed variances and road segments. The datasets include information for road segments monitored by fixed sensors/moving probes, road segment properties, geometric relationships among road segments, and proximal resources. Road segments are labeled by the sensed variance seen in traffic speeds over similar contexts. A model is created that can apply estimates of the variance of the traffic speed for a segment, including non-sensed segments via generalization to non-sensed road segments. Methods are described for employing the predictive models of variance, along with demand and propagation models, to make decisions about configuration of sensors.

Claims

1. A computer-implemented system for valuation of relative utility of data associated with an arterial flow system, comprising:

a flow system representation that describes probable flow for the flow system; and

a valuation component that generates a utility value associated with at least one section of a plurality of sections of the flow system based at least in part upon the flow system representation, the utility value is a function of the utility of sensor data associated with the section in detecting congestion for the flow system.

2. The system of claim 1, further comprising:

a context analyzer component that analyzes contextual data for the flow system, the utility value is based at least in part upon the contextual data.

3. The system of claim 1, further comprising:

a section component that specifies the plurality of sections based upon at least one of geographical regions and sensor positions for the flow system; and

a data store component that maintains the plurality of sections.

4. The system of claim 1, placement of a plurality of sensors that collect the sensor data is based at least in part upon the utility value.

5. The system of claim 1, further comprising:

a sensor interface component that obtains the sensor data as collected by a plurality of sensors;

a context analyzer component that analyzes contextual data associated with the plurality of sensors, the utility value is based at least in part upon the contextual data; and

a filter component that filters the sensor data based at least in part upon the utility value prior to provision of the sensor data to a route planning system.

6. The system of claim 5, further comprising:

a user context component that adjusts the utility value based at least in part upon a user profile that includes at least one of user preferences and frequent user routes.

7. The system of claim 5, the sensor data is filtered based at least in part upon a comparison of the utility value to a predetermined threshold.

8. The system of claim 1, further comprising:

a bottleneck identification component that identifies a location of a probable bottleneck;

a bottleneck indicator component that identifies a bottleneck indicator section indicative of a bottleneck; and

a route generating component that generates an alternate route based upon the probable bottleneck and the bottleneck indicator section.

9. The system of claim 1, further comprising

a sensor analysis component that analyzes distribution of the sensor data in comparison to the utility value;

and

an output component that provides the sensor analysis information to an operator.

10. A method for determining utility of information for an arterial flow system, comprising:

receiving a request to generate valuations for the flow system;

obtaining a set of segments that define the flow system; and

determining utility values of one or more segments of the set of segments, the utility values are a function of utility of sensor data associated with the one or more segments for monitoring the flow system.

11. The method of claim 10, further comprising:

generating a prioritized list of the set of segments based at least in part upon the utility values.

12. The method of claim 10, further comprising:

receiving the sensor data collected by a plurality of sensors;

identifying correspondence between the sensor data and the set of segments; and

filtering the sensor data based at least in part upon the relative utility values of the set of segments corresponding to the sensor data.

13. The method of claim 12, further comprising:

analyzing context associated with the sensor data; and

adjusting the utility values corresponding to the sensor data as a function of the context.

14. The method of claim 10, further comprising:

receiving the sensor data for the flow system;

analyzing the distribution of sensor data corresponding to the set of segments with regard to the utility values of the one or more segments;

identifying a subset of the set of segments based upon the analysis of the sensor data and the utility values; and

providing the identified subset of segments to an operator.

15. The method of claim 10, further comprising:

identifying a probable bottleneck in the flow system;

identifying one or more bottleneck indicative segments corresponding to sensor data indicative of the bottleneck;

generating a route that includes one or more alternate routes, selection of the one or more alternate routes is based at least in part upon the one or more bottleneck indicative segments; and

providing the route to a user.

16. A system for model composition, comprising:

a reception component that obtains data from an auxiliary source; and

a data valuation component that constructs at least one predictive model of traffic variance from obtained data.

17. The system of claim 16, further comprising a sensor placement component that determines location of at least one sensor based at least in part off the predictive model.

18. The system of claim 16, further comprising a library that provides data to the data valuation component.

19. The system of claim 16, wherein the data valuation component utilizes machine learning to construct at least one predictive model of traffic variance.

20. The system of claim 16, further comprising a path component that generates a route for a vehicle based at least in part off the predictive model of traffic variance.