Vehicle behavior learning apparatuses, methods, and programs

• US 20080243312A1
• Filed: 03/13/2008
• Published: 10/02/2008
• Est. Priority Date: 03/30/2007
• Status: Active Grant

• Current Assignee: Aisin AW Company Limited (Aisin Corp.)
• Original Assignee: Aisin AW Company Limited (Aisin Corp.)
• Inventors: Nakamura, Masaki, Aisaka, Osamu, Ishikawa, Tomoaki, Kanba, Motoki, Nakao, Koichi
• Granted Patent: US 8,155,826 B2
• Time in Patent Office: Days
• US Class Current: 701/1
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network

Abstract

Vehicle behavior learning apparatuses, methods, and programs store pieces of feature information including position information and attribute information of a plurality of target features. The apparatuses, methods, and programs obtain vehicle position information that shows a current position of a vehicle, obtaining image information of surroundings of the vehicle, and obtain one of the stored pieces of feature information corresponding to the surroundings of the vehicle based on the vehicle position information. The apparatuses, methods, and programs perform an image recognition for recognizing a target feature contained in the image information that corresponds to the obtained piece of feature information, detect a behavior of the vehicle that is performed within a predetermined range from a position of the recognized target feature, and store, based on the vehicle position information, the detected behavior in correspondence with information of a position in which the detected behavior was detected. The apparatuses, methods, and programs extract, based the detected behavior being stored a plurality of times at the same position, the detected behavior as a learned behavior, output learned behavior information including attribute information of the detected behavior and the position information of the detected behavior, each of which are kept in correspondence with the piece of feature information of the recognized target feature.

Claims

1. A vehicle behavior learning apparatus comprising:

a memory that stores pieces of feature information including position information and attribute information of a plurality of target features; and

a controller that;

obtains vehicle position information that shows a current position of a vehicle;

obtains image information of surroundings of the vehicle;

obtains one of the stored pieces of feature information corresponding to the surroundings of the vehicle based on the vehicle position information;

performs an image recognition for recognizing a target feature contained in the image information that corresponds to the obtained piece of feature information;

detects a behavior of the vehicle that is performed within a predetermined range from a position of the recognized target feature;

based on the vehicle position information, stores the detected behavior in correspondence with information of a position in which the detected behavior was detected;

based the detected behavior being stored a plurality of times at the same position, extracts the detected behavior as a learned behavior; and

outputs learned behavior information, the learned behavior information including attribute information of the detected behavior and the position information of the detected behavior, each of which are kept in correspondence with the piece of feature information of the recognized target feature.

2. The vehicle behavior learning apparatus according to claim 1, wherein:

the detected behavior includes at least one of;

receiving of an operation performed by a driver, the operation received by an element of the vehicle; and

an operation of the vehicle.

3. The vehicle behavior learning apparatus according to claim 1, wherein

the controller is connected to a plurality of vehicles in such a manner that communication is possible between the controller and the vehicles;

and

when the detected behavior is an operation of the vehicle caused by an external factor affecting the vehicle from outside, the controller extracts, as the learned behavior, the detected behavior, the detected behavior being stored a plurality of times among memories of the plurality of vehicles at the same position.

4. The vehicle behavior learning apparatus according to claim 1, wherein the controller:

predicts a future occurrence of the detected behavior that is kept in correspondence with the recognized target feature based on the learned behavior information.

5. The vehicle behavior learning apparatus according to claim 4, wherein the controller:

outputs the predicted future occurrence to a navigation calculating unit that performs a calculation process in order to output guidance information for the vehicle.

6. The vehicle behavior learning apparatus according to claim 4, wherein:

the detected behavior is an operation performed by the driver; and

the controller outputs the predicted future occurrence to a controlling device included in the vehicle to reproduce the operation performed by the driver.

7. The vehicle behavior learning apparatus according to claim 4, wherein the controller:

outputs the predicted future occurrence to a controlling device that optimizes operations of the vehicle.

8. The vehicle behavior learning apparatus according to claim 1, wherein:

the recognized target feature is a road marker that is provided on a surface of a road.

9. The vehicle behavior learning apparatus according to claim 1, wherein the feature information includes at least one of:

initial feature information that is stored in advance; and

learned feature information that has been learned and stored based on image recognition.

10. The vehicle behavior learning apparatus according to claim 1, wherein information of the position in which the detected behavior was detected includes at least one of:

coordinate information indicating a position of the detected behavior; and

distance information indicating a distance between a position of the recognized target feature and the position of the detected behavior.

11. The vehicle behavior learning apparatus according to claim 1, wherein the position of the detected behavior that is output as the learned behavior information includes at least one of:

coordinate information indicating a position of the learned behavior; and

distance information indicating a distance between a position of the recognized target feature and the position of the learned behavior.

12. A navigation apparatus comprising:

the vehicle behavior learning apparatus according to claim 1;

a map memory that stores map information; and

a controller that provides guidance information based on at least one of the output learned behavior information and the map information.

13. A vehicle behavior learning method comprising:

storing pieces of feature information including position information and attribute information of a plurality of target features;

obtaining vehicle position information that shows a current position of a vehicle;

obtaining image information of surroundings of the vehicle;

obtaining one of the stored pieces of feature information corresponding to the surroundings of the vehicle based on the vehicle position information;

performing an image recognition for recognizing a target feature contained in the image information that corresponds to the obtained piece of feature information;

detecting a behavior of the vehicle that is performed within a predetermined range from a position of the recognized target feature;

storing, based on the vehicle position information, the detected behavior in correspondence with information of a position in which the detected behavior was detected;

extracting, based the detected behavior being stored a plurality of times at the same position, the detected behavior as a learned behavior; and

outputting learned behavior information, the learned behavior information including attribute information of the detected behavior and the position information of the detected behavior, each of which are kept in correspondence with the piece of feature information of the recognized target feature.

14. The vehicle behavior learning method according to claim 13, wherein:

the detected behavior includes at least one of;

receiving of an operation performed by a driver, the operation received by an element of the vehicle; and

an operation of the vehicle.

15. The vehicle behavior learning method according to claim 13, further comprising:

predicting a future occurrence of the detected behavior that is kept in correspondence with the recognized target feature based on the learned behavior information.

16. The vehicle behavior learning method according to claim 15, further comprising:

outputting guidance information for the vehicle based on the prediction.

17. The vehicle behavior learning method according to claim 15, further comprising:

controlling the vehicle to reproduce the detected behavior based on the prediction.

18. The vehicle behavior learning method according to claim 15, further comprising:

optimizing operations of the vehicle based on the prediction.

19. The vehicle behavior learning method according to claim 13, wherein:

the recognized target feature is a road marker that is provided on a surface of a road.

20. A computer-readable storage medium storing a computer-executable program usable to learn vehicle behavior, the program comprising:

instructions for storing pieces of feature information including position information and attribute information of a plurality of target features;

instructions for obtaining vehicle position information that shows a current position of a vehicle;

instructions for obtaining image information of surroundings of the vehicle;

instructions for obtaining one of the stored pieces of feature information corresponding to the surroundings of the vehicle based on the vehicle position information;

instructions for performing an image recognition for recognizing a target feature contained in the image information that corresponds to the obtained piece of feature information;

instructions for detecting a behavior of the vehicle that is performed within a predetermined range from a position of the recognized target feature;

instructions for storing, based on the vehicle position information, the detected behavior in correspondence with information of a position in which the detected behavior was detected; and

instructions for extracting, based the detected behavior being stored a plurality of times at the same position, the detected behavior as a learned behavior; and

instructions for outputting learned behavior information, the learned behavior information including attribute information of the detected behavior and the position information of the detected behavior, each of which are kept in correspondence with the piece of feature information of the recognized target feature.