System and Method for Real-Time Travel Path Prediction and Automatic Incident Alerts

• US 20100070171A1
• Filed: 09/14/2007
• Published: 03/18/2010
• Est. Priority Date: 09/14/2006
• Status: Active Grant

• Current Assignee: University of South Florida (State University System of Florida)
• Original Assignee: University of South Florida (State University System of Florida)
• Inventors: Winters, Philip L., Barbeau, Sean J., Labrador, Miguel, Georggi, Nevine, Perez, Rafael
• Granted Patent: US 8,548,734 B2
• Time in Patent Office: Days
• US Class Current: 701/207
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles
• CPC Class Codes: G01C 21/3617 using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement

Abstract

A path prediction method that uses a commuter'"'"'s travel patterns to predict their route and destination, and transmit road advisories via a GPS-enabled device. Once the user'"'"'s location data is transmitted via a GPS-enabled device it is then catalogued and stored in a GIS database. The user'"'"'s current travel path is then compared to their path history and statistics and a destination is determined based on related spatial and time properties. A warning is then automatically delivered to the user if there is an accident along their predicted path, without requiring any request or input form the user.

Claims

1. A method of predicting a path of travel, comprising:

establishing a travel profile for a user, wherein the travel profile comprises coordinates related to a plurality of trips taken by the user;

receiving real-time data comprising a plurality of coordinates related to the movement of the user; and

generating a predicted path by comparing the real-time data to the travel profile.

2. The method of claim 1, further comprising:

establishing an obstacle profile comprising coordinates related to at least one real-time obstacle;

comparing the predicted path to the obstacle profile; and

communicating the existing of an obstacle in the obstacle profile whose coordinates correspond to the predicted path.

3. The method of claim 2 wherein at least one real-time obstacle is selected from the group consisting of delay points, delay polylines and delay polygons.

4. The method of claim 1 wherein the travel profile comprises trip data selected from the group consisting of trip start coordinates, trip end coordinates, trip way-point coordinates, travel time, travel start time, travel end time, day of week of travel, travel distance, travel speed, travel purpose, intermediate stops, frequency of travel to a specific location, frequency of motorized travel and frequency of non-motorized travel.

5. The method of claim 1, further comprising:

generating a trip-polyline for each trip in the travel profile; and

constructing a real-time polyline comprising the plurality of coordinates in the real-time data;

wherein the predicted path is generated by comparing the real-time polyline to at least one trip-polyline in the travel profile.

6. The method of claim 5 wherein the predicted path is a trip stored in the travel profile, responsive to a real-time polyline whose coordinates correspond with at least one trip polyline stored in the travel profile.

7. The method of claim 5 wherein the predicted path is the best matching buffer, responsive to finding a plurality of trip-polylines in the travel profile that correspond with the real-time polyline.

8. The method of claim 5 further comprising determining the number of coordinates in the real-time polyline that do not correspond with a trip-polyline in the travel profile, responsive to finding no trip-polylines in the travel profile that correspond with the real-time polyline.

9. The method of claim 8, further comprising:

constructing a modified real-time polyline by removing the oldest coordinate from the real-time polyline, responsive to finding a plurality of coordinates in the real-time polyline that do not correspond with a trip polyline in the travel profile; and

comparing the modified real-time polyline to at least one trip-polyline stored in the travel profile.

10. The method of claim 9 wherein the predicted path is a trip stored in the travel profile, responsive to a modified real-time polyline whose coordinates correspond to at least one trip-polyline stored in the travel profile.

11. The method of claim 9 wherein the predicted path is the best matching buffer, responsive to finding a plurality of trip-polylines in the travel profile that correspond with the modified real-time polyline.

12. A method of predicting a path of travel, comprising:

establishing a travel profile for a user, wherein the travel profile comprises coordinates associate with a plurality of trips taken by the user;

receiving real-time data related comprising coordinates related to the position of the user; and

generating a predicted path by comparing the real-time data to the travel profile.

13. The method of claim 12 wherein the plurality of trips comprises trip data selected from the group consisting of trip start coordinates, trip end coordinates, trip way-point coordinates, travel time, travel start time, travel end time, day of week of travel, travel distance, travel speed, travel purpose, intermediate stops, frequency of travel to a specific location, frequency of motorized travel and frequency of non-motorized travel.

14. The method of claim 12, further comprising:

establishing an obstacle profile comprising coordinates related to at least one real-time obstacle;

comparing the predicted path to the obstacle profile; and

communicating the existing of an obstacle in the obstacle profile whose coordinates correspond to the predicted path.

15. The method of claim 14 wherein at least one real-time obstacle is selected from the group consisting of delay points, delay polylines and delay polygons.

16. The method of claim 12, further comprising:

establishing a buffer associated with at least one trip in the travel profile; and

storing the buffer in the travel profile.

17. The method of claim 16 wherein the buffer is established by generating a trip-polyline for each trip in the trip profile, wherein the trip-polyline comprises the coordinates from a trip;

and constructing a polygon by buffering the trip-polyline by a predetermined radius.

18. The method of claim 16, further comprising constructing a real-time polyline comprising the plurality of coordinates in the real-time data.

19. The method of claim 18 wherein the real-time polyline is constructed from critical points in the real-time data.

20. The method of claim 18 wherein predicted path is generated by comparing the real-time polyline to at least one buffer stored in the travel profile.

21. The method of claim 18 wherein the predicted path is a trip stored in the travel profile, responsive to a real-time polyline whose coordinates are contained within at least one buffer stored in the travel profile.

22. The method of claim 18 wherein the predicted path is the best matching buffer, responsive to finding a plurality of buffers in the travel profile that contain the real-time polyline.

23. The method of claim 18 further comprising determining the number of coordinates in the real-time polyline that are not contained within a buffer in the travel profile, responsive to finding no buffers in the travel profile that contain the real-time polyline.

24. The method of claim 23, further comprising:

constructing a modified real-time polyline by removing the oldest coordinate from the real-time polyline that is contained within a buffer in the travel profile, responsive to finding a plurality of coordinates in the real-time polyline that are not contained within a buffer in the travel profile; and

comparing the modified real-time polyline to at least one buffer stored in the travel profile.

25. The method of claim 24 wherein the predicted path is a trip stored in the travel, responsive to a modified real-time polyline whose coordinates are contained within at least one buffer stored in the travel profile.

26. The method of claim 24 wherein the predicted path is the best matching buffer, responsive to finding a plurality of buffers in the travel profile that encompass the modified real-time polyline.