Method and system for risk prediction for a support actuation system

• US 8,880,282 B2
• Filed: 10/04/2010
• Issued: 11/04/2014
• Est. Priority Date: 10/04/2010
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Motor Engineering & Manufacturing North America Incorporated (Toyota Motor Corporation)
• Inventors: Gunaratne, Pujitha
• Primary Examiner(s): Holwerda, Stephen
• Application Number:
  US12/897,596
• Publication Number:
  US 20120083942A1
• Time in Patent Office: 1,492 Days
• Field of Search: 340/436, 340/438, 340/575, 340/576, 340/439, 382/115, 382/118, 701/33.4, 701/45, 701/48, 701/29.1, 705/4, 180/272, 180/287
• US Class Current: 701/33.4
• CPC Class Codes: B60W 2050/0029 Mathematical model of the driver
• CPC Class Codes: B60W 2050/005 Sampling
• CPC Class Codes: B60W 2050/0051 combined with averaging
• CPC Class Codes: B60W 2540/30 Driving style
• CPC Class Codes: B60W 2555/20 Ambient conditions, e.g. wind or rain
• CPC Class Codes: B60W 40/02 related to ambient conditions
• CPC Class Codes: B60W 40/09 Driving style or behaviour

Abstract

A method and system for risk prediction for a support actuation system. The system includes a support actuation system for an automobile having a support actuation module and/or a risk prediction system. The risk prediction system includes a sensor, a processor, and/or a memory. The sensor detects images corresponding to identity data, environment data, event data, and/or behavior data, which are stored in the memory. The memory also stores a database including identities of users, environment risk values, event risk values, and/or behavior risk values. Using the identity data, the environment data, the event data, and/or the behavior data, the processor determines the environment risk value, the event risk value, the behavior risk value, and/or the total risk value for a user. When the total risk value is above a predetermined risk threshold, the support actuation module performs support actuation.

Claims

1. A method for risk prediction for a support actuation system having a processor connected to a sensor and to a database, the method comprising:

detecting, using the sensor, identity data of a first user of an automobile;

detecting, using the sensor, behavior data of the first user;

detecting, using the sensor, environment data;

detecting, using the sensor, event data;

registering, in the database, the behavior data of the first user in response to the processor determining that the behavior data does not have corresponding behavior data in the database for the first user and does not have corresponding behavior data in the database for other users registered in the database;

generating, using the processor, a state trajectory for the behavior data and a total risk value based on the state trajectory in response to the processor determining that corresponding behavior data is in the database for other users registered in the database but not for the first user; and

generating, using the processor, a total risk value based on the identity data, the behavior data, the environment data, the event data, and corresponding behavior data in response to the processor determining that corresponding behavior data is in the database for the first user.

2. The method of claim 1 further comprising performing, using a support actuation module, support actuation in response to the processor determining that the total risk value is greater than a predetermined risk threshold.

3. The method of claim 1 further comprising:

determining, using the processor, an environment risk value associated with the environment data; and

determining, using the processor, an event risk value associated with the event data.

4. The method of claim 3 further comprising analyzing the identity data, using the processor, to locate the first user in the database with an identity corresponding to the identity data.

5. The method of claim 4 further comprising analyzing the behavior data, using the processor, to locate a behavior in the database associated with the first user that corresponds to the behavior data, in response to the processor determining that the first user is located.

6. The method of claim 5 wherein the step of generating the total risk value in response to the processor determining that corresponding behavior data is in the database for the first user includes:

determining, using the processor, a behavior risk value associated with the behavior in the database for the first user that corresponds to the behavior data in response to the processor determining that the behavior in the database associated with the first user that corresponds to the behavior data is located, wherein the generating, using the processor, the total risk value is further based on the behavior risk value, the environment risk value, and the event risk value.

7. The method of claim 5 wherein the step of generating the state trajectory for the behavior data in response to the processor determining that corresponding behavior data is in the database for other users registered in the database but not for the first user includes:

determining, using the processor, a second user with a behavior in the database associated with the second user that corresponds to the behavior data in response to the processor determining that the behavior in the database associated with the first user that corresponds to the behavior data is unable to be located;

analyzing, using the processor, behavior risk values for common behaviors between the first user and the second user to determine an offset; and

applying, using the processor, the offset to a behavior risk value for the behavior in the database associated with the second user that corresponds to the behavior data to determine an offset behavior risk value,

wherein the generating, using the processor, the state trajectory is further based on the offset behavior risk value, the environment risk value, and the event risk value.

8. The method of claim 1 wherein the step of generating the state trajectory for the behavior data in response to the processor determining that corresponding behavior data is in the database for other users registered in the database but not for the first user includes:

analyzing the behavior data, using the processor, to locate behavior in the database associated with any user that corresponds to the behavior data in response to the processor determining that the first user is unable to be located;

determining, using the processor, an environment risk value associated with the environment data; and

determining, using the processor, an event risk value associated with the event data;

determining, using the processor, an average behavior risk value for the behavior in the database associated with any user in the database that corresponds to the behavior data; and

wherein the generating, using the processor, the state trajectory is further based on the average behavior risk value, the environment risk value, and the event risk value.

9. The method of claim 8 further comprising:

storing, using the processor, an entry for a new user in the database with an identity corresponding to the identity data; and

storing, using the processor, an entry for a behavior in the database associated with the new user and corresponding to the behavior data, and having a behavior risk value of the average behavior risk value.

10. A method for risk prediction for a support actuation system in an automobile comprising:

detecting, using a sensor, identity data of a first user of the automobile;

detecting, using the sensor, behavior data of the first user;

detecting, using the sensor, environment data;

detecting, using the sensor, event data;

generating, using a processor, an environment risk value based on the environment data;

generating, using the processor, an event risk value based on the event data;

determining, using the processor, whether the behavior data has corresponding behavior data in a database;

registering, in the database, the behavior data of the first user in response to the processor determining that the behavior data does not have corresponding behavior data in the database for the first user and does not have corresponding behavior data in the database for other users registered in the database;

generating, using the processor, a state trajectory for the behavior data and a total risk value based on the state trajectory in response to the processor determining that corresponding behavior data is in the database for other users registered in the database but not for the first user; and

generating, using the processor, a total risk value based on the identity data, the behavior data, the environment risk value, the event risk value, and corresponding behavior data in response to the processor determining that corresponding behavior data is in the database for the first user.

11. The method of claim 10 further comprising analyzing the identity data, using the processor, to locate the first user in the database with an identity corresponding to the identity data.

12. The method of claim 11 further comprising analyzing the behavior data, using the processor, to locate a behavior in the database associated with the first user that corresponds to the behavior data in response to the processor determining that the first user is located.

13. The method of claim 12 wherein the step of generating the total risk value in response to the processor determining that corresponding behavior data is in the database for the first user includes:

determining, using the processor, a behavior risk value associated with the behavior in the database for the first user that corresponds to the behavior data in response to the processor determining that the behavior in the database associated with the first user that corresponds to the behavior data is located,

wherein the generating, using the processor, the total risk value is further based on the behavior risk value, the environment risk value, and the event risk value.

14. The method of claim 10 wherein the step of generating the state trajectory for the behavior data in response to the processor determining that corresponding behavior data is in the database for other users registered in the database but not for the first user includes:

determining, using the processor, a second user with a behavior in the database associated with the second user that corresponds to the behavior data in response to the processor determining that the behavior in the database associated with the first user that corresponds to the behavior data is unable to be located;

analyzing, using the processor, behavior risk values for common behaviors between the first user and the second user to determine an offset; and

applying, using the processor, the offset to a behavior risk value for the behavior in the database associated with the second user that corresponds to the behavior data to determine an offset behavior risk value,

wherein the generating, using the processor, the state trajectory is further based on the offset behavior risk value, the environment risk value, and the event risk value.

15. The method of claim 11 wherein the step of generating the state trajectory for the behavior data in response to the processor determining that corresponding behavior data is in the database for other users registered in the database but not for the first user includes:

analyzing the behavior data, using the processor, to locate behavior in the database associated with any user that corresponds to the behavior data in response to the processor determining that the first user is unable to be located;

determining, using the processor, an average behavior risk value for the behavior in the database associated with any user in the database that corresponds to the behavior data;

generating, using the processor, the state trajectory by further using the average behavior risk value, the environment risk value, and the event risk value;

storing, using the processor, an entry for a new user in the database with an identity corresponding to the identity data; and

storing, using the processor, an entry for a behavior in the database associated with the new user and corresponding to the behavior data, and having a behavior risk value of the average behavior risk value.

16. An automobile comprising:

a sensor detecting identity data of a first user of the automobile, behavior data of the first user of the automobile, environment data, and event data;

a memory storing a database, the identity data, the behavior data, the environment data, and the event data;

a processor connected to the sensor and the memory, and configured to;

register, in the database, the behavior data of the first user in response to the processor determining that the behavior data does not have corresponding behavior data in the database for the first user and does not have corresponding behavior data in the database for other users registered in the database;

generate a state trajectory for the behavior data and a total risk value based on the state trajectory in response to the processor determining that corresponding behavior data is in the database for other users registered in the database but not for the first user; and

generate a total risk value based on the identity data, the behavior data the environment data, and the event data, and corresponding behavior data in response to the processor determining that corresponding behavior data is in the database for the first user.

17. The automobile of claim 16 wherein the processor is further configured to analyze the behavior data to locate a behavior in the database associated with the first user that corresponds to the behavior data in response to the processor determining that the first user is located.

18. The automobile of claim 17 wherein the processor is further configured to:

determine a behavior risk value associated with the behavior in the database for the first user that corresponds to the behavior data in response to the processor determining that the behavior in the database associated with the first user that corresponds to the behavior data is located, and generate the total risk value by further using the behavior risk value, the environment risk value, and the event risk value.

19. The automobile of claim 16 wherein the processor is further configured to:

determine a second user with a behavior in the database associated with the second user that corresponds to the behavior data in response to the processor determining that a behavior in the database associated with the first user that corresponds to the behavior data is unable to be located,

analyze behavior risk values for common behaviors between the first user and the second user to determine an offset,

apply the offset to a behavior risk value for the behavior in the database associated with the second user that corresponds to the behavior data to determine an offset behavior risk value, and

generate the state trajectory by further using the offset behavior risk value, the environment risk value, and the event risk value.

20. The automobile of claim 16 wherein the processor is further configured to:

analyze the behavior data to locate behavior in the database associated with any user that corresponds to the behavior data in response to the processor determining that the first user is unable to be located,

determine an average behavior risk value for the behavior in the database associated with any user in the database that corresponds to the behavior data,

generate the state trajectory by further using the average behavior risk value, the environment risk value, and the event risk value,

store an entry for a new user in the database with an identity corresponding to the identity data, and

store an entry for a behavior in the database associated with the new user and corresponding to the behavior data, and having a behavior risk value of the average behavior risk value.