Risk situations for vehicle occupants based on data provided by vehicle sensors and contextual information

• US 10,274,338 B2
• Filed: 12/11/2016
• Issued: 04/30/2019
• Est. Priority Date: 12/11/2016
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated (Kyndryl Holdings, Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Boss, Gregory J., Cuervo, Ivonne R., Hasbun Pacheco, Maria E., Macias Garcia, Andrea, Navarro Piedra, Blanca R., Zamora Duran, Edgar A.
• Primary Examiner(s): Butler, Rodney A
• Application Number:
  US15/375,136
• Publication Number:
  US 20180162307A1
• Time in Patent Office: 870 Days
• CPC Class Codes: B60R 2021/01013 Means for detecting collision, impending collision or roll-over
• CPC Class Codes: B60R 2021/01286 Electronic control units
• CPC Class Codes: B60R 21/013 including means for detecting collisions, impending collisions or roll-over
• CPC Class Codes: G01C 21/3691 Retrieval, searching and output of information related to real-time traffic, weather, or environmental conditions arrangements for giving variable traffic instructions G08G1/09
• CPC Class Codes: G01C 21/3697 Output of additional, non-guidance related information, e.g. low fuel level G01C21/3679 takes precedence
• CPC Class Codes: G05B 23/00 Testing or monitoring of control systems or parts thereof monitoring of programme-control systems G05B19/048, G05B19/406
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G07C 5/08 Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
• CPC Class Codes: G07C 5/0816 Indicating performance data, e.g. occurrence of a malfunction
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0141 for traffic information dissemination
• CPC Class Codes: G08G 1/16 Anti-collision systems road vehicle drive control systems for predicting or avoiding probable or impending collision otherwise than by control of a particular sub-unit B60W30/08
• CPC Class Codes: G08G 1/164 Centralised systems, e.g. external to vehicles
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

A method for improving risk situations for vehicle occupants in a vehicle which includes: configuring a set of circumstances; defining a set of values for each circumstance where each value has a rate; collecting context information for the circumstances, values and rates; collecting real-time sensor measurements pertaining to a vehicle, a driver and vehicle occupants; retrieving risk patterns from a risk pattern database; matching the sensor measurements to the risk patterns to find a matching risk pattern having a risk similarity value; contextualizing the matching risk pattern by increasing the risk similarity value to result in a personalized risk value; comparing the personalized risk value to a threshold; and executing a context modifying action to lower the personalized risk value below a predefined threshold when the personalized risk value exceeds the predefined threshold.

Claims

1. A computer-implemented method for improving risk situations for vehicle occupants in a vehicle comprising the steps of;

configuring a set of circumstances where each circumstances is a condition of a time, a place or a manner that accompanies or influences an event or a person;

defining a set of values for each circumstance where each value has a rate;

collecting context information for the circumstances, values and rates;

collecting by vehicle sensors, real-time sensor measurements pertaining to a vehicle, a driver and vehicle occupants;

retrieving risk patterns from a risk pattern database;

matching the sensor measurements to the risk patterns to find a matching risk pattern having a risk similarity value;

contextualizing the matching risk pattern by increasing the risk similarity value to result in a personalized risk value;

comparing the personalized risk value to a threshold; and

autonomously executing by the vehicle a context modifying action to lower the personalized risk value when the personalized risk value exceeds a predefined threshold wherein the context modifying action is a personalized action performed by the vehicle to take over and autonomously execute the personalized action with respect to the vehicle occupants or the vehicle that decreases the personalized risk value below the predefined threshold.

2. The computer-implemented method of claim 1 where when the personalized risk value does not exceed the predefined threshold, repeating the process starting from configuring a set of circumstances.

3. The computer-implemented method of claim 1 wherein when matching the sensor measurements to the risk patterns does not find a matching risk pattern, repeating the process starting from configuring a set of circumstances.

4. The computer-implemented method of claim 1 wherein collecting context information includes collecting one or more of identifying the driver, loading a profile of the driver, obtaining a mood of the driver, time of day weather information, GPS location and vehicle route information.

5. The computer-implemented method of claim 1 wherein collecting by vehicle sensors including continuously collecting by vehicle sensors the real-time sensor measurements.

6. The computer-implemented method of claim 1 further comprising a training process comprising:

predefining a default context information for the circumstances, values and rates;

predefining a default set of patterns for sensor readouts that represent default risk patterns;

adjusting the rates using the collected context information for the circumstances, values and rates and the collected real-time sensor measurements.

7. The computer-implemented method of claim 1 wherein the context modifying action comprises a context modifier changing environmental variables to reduce the risk below the predefined threshold risk.

8. A vehicle system for improving risk situations for vehicle occupants in a vehicle comprising;

a computer readable storage medium that stores instructions; and

a processor that executes the instructions to perform the following functions;

configure a set of circumstances where each circumstances is a condition of a time, a place or a manner that accompanies or influences an event or a person;

define a set of values for each circumstance where each value has a rate;

collect context information for the circumstances, values and rates;

collect by vehicle sensors, real-time sensor measurements pertaining to a vehicle, a driver and vehicle occupants;

retrieve risk patterns from a risk pattern database;

match the sensor measurements to the risk patterns to find a matching risk pattern having a risk similarity value;

contextualize the matching risk pattern by increasing the risk similarity value to result in a personalized risk value;

compare the personalized risk value to a threshold; and

autonomously execute by the vehicle a context modifying action to lower the personalized risk value when the personalized risk value exceeds a predefined threshold wherein the context modifying action is a personalized action performed by the vehicle to take over and autonomously execute the personalized action with respect to the vehicle occupants or the vehicle that decreases the personalized risk value below the predefined threshold.

9. The system of claim 8 where when the personalized risk value does not exceed the predefined threshold, repeat starting from configure a set of circumstances.

10. The system of claim 8 wherein when match the sensor measurements to the risk patterns does not find a matching risk pattern, repeat starting from configure a set of circumstances.

11. The system of claim 8 wherein collect context information includes collect one or more of identifying the driver, loading a profile of the driver, obtaining a mood of the driver, time of day weather information, GPS location and vehicle route information.

12. The system of claim 8 wherein collect by vehicle sensors including continuously collect by vehicle sensors the real-time sensor measurements.

13. The system of claim 8 further wherein the processor that executes the instructions to perform the following additional functions comprising a training process comprising:

predefine a default context information for the circumstances, values and rates;

predefine a default set of patterns for sensor readouts that represent default risk patterns;

adjust the rates using the collected context information for the circumstances, values and rates and the collected real-time sensor measurements.

14. The system of claim 8 wherein the context modifying action comprises a context modifier changing environmental variables to reduce the risk below the predefined threshold risk.

15. A computer program product for improving risk situations for vehicle occupants in a vehicle, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising;

configuring a set of circumstances where each circumstances is a condition of a time, a place or a manner that accompanies or influences an event or a person;

defining a set of values for each circumstance where each value has a rate;

collecting context information for the circumstances, values and rates;

collecting by vehicle sensors, real-time sensor measurements pertaining to a vehicle, a driver and vehicle occupants;

retrieving risk patterns from a risk pattern database;

matching the sensor measurements to the risk patterns to find a matching risk pattern having a risk similarity value;

contextualizing the matching risk pattern by increasing the risk similarity value to result in a personalized risk value;

comparing the personalized risk value to a threshold; and

autonomously executing by the vehicle a context modifying action to lower the personalized risk value when the personalized risk value exceeds a predefined threshold wherein the context modifying action is a personalized action performed by the vehicle to take over and autonomously execute the personalized action with respect to the vehicle occupants or the vehicle that decreases the personalized risk value below the predefined threshold.

16. The computer program product of claim 15 where when the personalized risk value does not exceed the predefined threshold, repeating the process starting from configuring a set of circumstances.

17. The computer program product of claim 15 wherein when matching the sensor measurements to the risk patterns does not find a matching risk pattern, repeating the process starting from configuring a set of circumstances.

18. The computer program product of claim 15 wherein collecting context information includes collecting one or more of identifying the driver, loading a profile of the driver, obtaining a mood of the driver, time of day weather information, GPS location and vehicle route information.

19. The computer program product of claim 15 further comprising a training process comprising:

predefining a default context information for the circumstances, values and rates;

predefining a default set of patterns for sensor readouts that represent default risk patterns;

adjusting the rates using the collected context information for the circumstances, values and rates and the collected real-time sensor measurements.

20. The computer program product of claim 15 wherein the context modifying action comprises a context modifier changing environmental variables to reduce the risk below the predefined threshold risk.