Using predictive traffic modeling

• US 6,256,577 B1
• Filed: 09/17/1999
• Issued: 07/03/2001
• Est. Priority Date: 09/17/1999
• Status: Expired due to Term

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Graunke, Gary L.
• Primary Examiner(s): Camby, Richard M.
• Application Number:
  US09/398,603
• Time in Patent Office: 655 Days
• Field of Search: 701/117, 701/118, 701/119, 701/122, 701/202, 340/905, 340/984, 340/988, 340/990, 340/993, 340/995
• US Class Current: 701/117
• CPC Class Codes: G01C 21/3694 Output thereof on a road map
• CPC Class Codes: G08G 1/096811 where the route is computed offboard
• CPC Class Codes: G08G 1/096861 where the immediate route instructions are output to the driver, e.g. arrow signs for next turn

Abstract

A system may receive requests for traffic routing information from a plurality of vehicles and may provide a suggested route, not only based on actual current conditions and historical information, but based on the application of a predictive model. The predictive model may use information about current traffic conditions and historical information to predict the actual conditions that will occur in the course of traversing a desired route to an intended destination. In this way, the system may adapt for the dynamic nature of traffic conditions.

Claims

1. A method for developing a predictive model of traffic flows comprising:

developing a database of the count of the number of vehicles and their times for traversing a given segment at a plurality of different times;

using said database to determine an amount of time to traverse said segment at a future time; and

using a matching algorithm to find a segment and time interval that matches a characteristics of a future time interval.

2. The method of claim 1 including comparing the information determined from said database to actual time information to reduce the amount of information to develop the database.

3. The method of claim 1 including finding a segment specific historical record for the time of day that most closely matches a given situation.

4. The method of claim 3 including selecting a number of preceding and succeeding street segments and time intervals and using information about the times for these intervals to predict a future time for a given interval.

5. The method of claim 1 further including developing counts for a particular segment at a future time and using information about current vehicle positions and predicted routes to determine an amount of time to traverse said segment at a future time.

6. The method of claim 1 including estimating the travel time to reach a particular location based on the time taken to reach a similar location during the time interval identified by the matching algorithm.

7. An article comprising a medium for storing instructions that cause a processor-based system to:

develop a database of the count of the number of vehicles and their times for traversing a given segment at a plurality of different times;

use said database to determine an amount of time to traverse said segment at a future time; and

use a matching algorithm to find a segment and a time interval that matches the characteristics of a future time interval.

8. The article of claim 7 further storing instructions that enable the processor-based system to compare the information determined from the database to actual time information to reduce the amount of information to develop the database.

9. The article of claim 7 further storing instructions that enable the processor-based system to find a segment specific historical record for the time of day that most closely matches a given situation.

10. The article of claim 9 further storing instructions that enable the processor-based system to select a number preceding and succeeding street segments and time intervals and use information about the times for those intervals to predict a future time for a given interval.

11. The article of claim 7 further storing instructions that enable the processor-based system to develop a count for a particular segment at a future time and use information about current vehicle position and predicted routes to determine an amount of time to traverse such segments at a future time.

12. The article of claim 7 further storing instructions that enable the processor-based system to estimate the travel time to reach a particular location based on the time taken to reach a similar location during the time interval identified by the matching algorithm.