Automated dynamic vehicle blind spot determination

• US 8,489,284 B2
• Filed: 08/21/2008
• Issued: 07/16/2013
• Est. Priority Date: 08/21/2008
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Emam, Ossama, Kanevsky, Dimitri, Rish, Irina
• Primary Examiner(s): Jayne, Darnell
• Assistant Examiner(s): HAWN, PATRICK D
• Application Number:
  US12/196,042
• Publication Number:
  US 20100049393A1
• Time in Patent Office: 1,790 Days
• Field of Search: 701/45, 701/49, 340/438, 340/435, 340/439
• US Class Current: 701/45
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G08G 1/161 Decentralised systems, e.g. inter-vehicle communication

Abstract

A driver'"'"'s orientation within a vehicle is monitored. A change in the driver'"'"'s orientation is detected. A change to a blind spot of the vehicle is calculated based upon the detected change in the driver'"'"'s orientation. This abstract is not to be considered limiting, since other embodiments may deviate from the features described in this abstract.

Claims

1. A method, comprising:

monitoring, via a computing device, a driver'"'"'s orientation within a first vehicle;

detecting a change in the driver'"'"'s orientation;

calculating, in response to detecting the change in the driver'"'"'s orientation, a change to a rear blind spot dimensional area of the first vehicle, where the rear blind spot dimensional area comprises coordinates and dimensions of an area behind a peripheral view area of the driver and outside of rear viewable areas of viewable mirrors of the vehicle;

applying the calculated change to the rear blind spot dimensional area to a statistical model of dangerous vehicle situations, where the statistical model to which the calculated change to the rear blind spot dimensional area is applied comprises a probabilistic function comprising at least one of a Gaussian distribution and a uniform distribution of at least one of the dangerous blind spot coordinates, dangerous information about the first vehicle, and dangerous characteristics of a vehicular environment surrounding the first vehicle; and

predicting a dangerous situation associated with the first vehicle based upon a result of the calculated change to the rear blind spot dimensional area applied to the statistical model of the dangerous vehicle situations.

2. The method of claim 1, where detecting the change in the driver'"'"'s orientation comprises detecting a change in at least one of an eye position of the driver, a head position of the driver, a body position of the driver, and an activity of the driver.

3. The method of claim 1, where calculating, in response to detecting the change in the driver'"'"'s orientation, the change to the rear blind spot dimensional area comprises calculating a change to at least one of a blind spot shape and blind spot dimensions.

4. The method of claim 1, further comprising:

determining at least one characteristic associated with the first vehicle, the at least one characteristic comprising at least one of a size of the first vehicle, a mirror adjustment associated with the first vehicle, a speed of the first vehicle, a driver'"'"'s seat height, a driver'"'"'s seat position, and a steering angle of the first vehicle; and

where calculating, in response to detecting the change in the driver'"'"'s orientation, the change to the rear blind spot dimensional area comprises calculating the change to the rear blind spot dimensional area based upon the determined at least one characteristic associated with the first vehicle.

5. The method of claim 1, further comprising communicating information associated with at least one of the calculated change to the rear blind spot dimensional area and the predicted dangerous situation to at least one of the first vehicle and a second vehicle.

6. The method of claim 1, where:

the statistical model of dangerous vehicle situations further comprises dangerous driver orientation characteristics; and

applying the calculated change to the rear blind spot dimensional area to the statistical model of dangerous vehicle situations further comprises applying the calculated change to the rear blind spot dimensional area to the dangerous driver orientation characteristics within the statistical model.

7. The method of claim 1, where:

the at least one of the Gaussian distribution and the uniform distribution of the dangerous information about the first vehicle comprises mathematical relationships associated with at least one of a dangerous vehicle speed, a dangerous vehicle orientation, and a dangerous steering angle relative to speed; and

the at least one of the Gaussian distribution and the uniform distribution of the dangerous characteristics of a vehicular environment surrounding the first vehicle comprises mathematical relationships associated with at least one of a dangerous weather condition and dangerous conditions associated with other surrounding vehicles.

8. The method of claim 1, further comprising updating the statistical model of dangerous vehicle situations based upon data associated with at least one of an actual collision and a near collision.

9. The method of claim 8, where updating the statistical model of dangerous vehicle situations based upon the data associated with at least one of the actual collision and the near collision comprises updating the statistical model of dangerous vehicle situations with at least one of a new dangerous driver characteristic, new dangerous blind spot coordinates, new dangerous information about the first vehicle, and a new dangerous characteristic of the environment surrounding the first vehicle.

10. A system comprising:

a memory adapted to store a statistical model of dangerous vehicle situations; and

a processor programmed to;

monitor a driver'"'"'s orientation within a first vehicle;

detect a change in the driver'"'"'s orientation;

calculate, in response to detecting the change in the driver'"'"'s position, a change to a rear blind spot dimensional area of the first vehicle, where the rear blind spot dimensional area comprises coordinates and dimensions of an area behind a peripheral view area of the driver and outside of rear viewable areas of viewable mirrors of the vehicle;

apply the calculated change to the rear blind spot dimensional area to the statistical model of dangerous vehicle situations, where the statistical model to which the calculated change to the rear blind spot dimensional area is applied comprises a probabilistic function comprising at least one of a Gaussian distribution and a uniform distribution of at least one of the dangerous blind spot coordinates, dangerous information about the first vehicle, and dangerous characteristics of a vehicular environment surrounding the first vehicle; and

predict a dangerous situation associated with the first vehicle based upon a result of the calculated change to the rear blind spot dimensional area applied to the statistical model of dangerous vehicle situations.

11. The system of claim 10, where, in being programmed to detect a change in the driver'"'"'s orientation, the processor is programmed to detect a change in at least one of an eye position of the driver, a head position of the driver, a body position of the driver, and an activity of the driver.

12. The system of claim 10, where, in being programmed to calculate, in response to detecting the change in the driver'"'"'s orientation, the change to the rear blind spot dimensional area, the processor is programmed to calculate a change to at least one of a blind spot shape and blind spot dimensions.

13. The system of claim 10, where the processor is further programmed to:

determine at least one characteristic associated with the first vehicle, the at least one characteristic comprising at least one of a size of the first vehicle, a mirror adjustment associated with the first vehicle, a speed of the first vehicle, a driver'"'"'s seat height, a driver'"'"'s seat position, and a steering angle of the first vehicle; and

where, in being programmed to calculate, in response to detecting the change in the driver'"'"'s orientation, the change to the rear blind spot dimensional area, the processor is programmed to calculate the change to the rear blind spot dimensional area based upon the determined at least one characteristic associated with the first vehicle.

14. The system of claim 10, where the processor is further programmed to communicate information associated with at least one of the calculated change to the rear blind spot dimensional area and the predicted dangerous situation to at least one of the first vehicle and a second vehicle.

15. The system of claim 10, where:

the at least one of the Gaussian distribution and the uniform distribution of the dangerous information about the first vehicle comprises mathematical relationships associated with at least one of a dangerous vehicle speed, a dangerous vehicle orientation, and a dangerous steering angle relative to speed; and

the at least one of the Gaussian distribution and the uniform distribution of the dangerous characteristics of a vehicular environment surrounding the first vehicle comprises mathematical relationships associated with at least one of a dangerous weather conditions and dangerous conditions associated with other surrounding vehicles.

16. The system of claim 10, where the processor is further programmed to update the statistical model of dangerous vehicle situations based upon data associated with at least one of an actual collision and a near collision.

17. The system of claim 16, where, in being programmed to update the statistical model of dangerous vehicle situations based upon the data associated with at least one of an actual collision and a near collision, the processor is programmed to update the statistical model of dangerous vehicle situations with at least one of a new dangerous driver characteristic, new dangerous blind spot coordinates, new dangerous information about the first vehicle, and a new dangerous characteristic of the environment surrounding the first vehicle.

18. A system, comprising:

a memory adapted to store a statistical model of dangerous vehicle situations that comprises a probabilistic function comprising at least one of a Gaussian distribution and a uniform distribution of at least one of dangerous blind spot coordinates, dangerous information about a first vehicle, and dangerous characteristics of a vehicular environment surrounding the first vehicle; and

a processor programmed to;

monitor a driver'"'"'s orientation within the first vehicle;

detect a change in the driver'"'"'s orientation comprising at least one of a change of an eye position of the driver, a change of a head position of the driver, a change of a body position of the driver, and a change of an activity of the driver;

determine at least one characteristic associated with the first vehicle, the at least one characteristic comprising at least one of a size of the first vehicle, a mirror adjustment associated with the first vehicle, a speed of the first vehicle, a driver'"'"'s seat height, a driver'"'"'s seat position, and a steering angle of the first vehicle;

calculate a change to a rear blind spot dimensional area comprising at least one of a blind spot shape and blind spot dimensions of the first vehicle in response to the detected change in the driver'"'"'s orientation and the determined at least one characteristic associated with the first vehicle, where the rear blind spot dimensional area comprises coordinates and dimensions of an area behind a peripheral view area of the driver and outside of rear viewable areas of viewable mirrors of the vehicle;

read the statistical model of dangerous vehicle situations that comprises the probabilistic function comprising at least one of the Gaussian distribution and the uniform distribution of the at least one of the dangerous blind spot coordinates, The dangerous information about the first vehicle, and the dangerous characteristics of the vehicular environment surrounding the first vehicle from the memory;

apply at least one of the detected change in the driver'"'"'s orientation and the calculated change to the rear blind spot dimensional area to the statistical model of the dangerous vehicle situations that comprises the probabilistic function comprising at least one of the Gaussian distribution and the uniform distribution of the at least one of the dangerous blind spot coordinates, the dangerous information about the first vehicle, and the dangerous characteristics of the vehicular environment surrounding the first vehicle;

predict a dangerous situation associated with the first vehicle based upon a result of the at least one of the detected change in the driver'"'"'s orientation and the calculated change to the rear blind spot dimensional area applied to the statistical model of the dangerous vehicle situations that comprises the probabilistic function comprising at least one of the Gaussian distribution and the uniform distribution of the at least one of the dangerous blind spot coordinates, the dangerous information about the first vehicle, and the dangerous characteristics of the vehicular environment surrounding the first vehicle;

communicate information associated with at least one of the calculated change to the rear blind spot dimensional area and the predicted dangerous situation to at least one of the first vehicle and a second vehicle;

update the statistical model of dangerous vehicle situations based upon data associated with the predicted dangerous situation; and

store the updated statistical model of dangerous vehicle situations to the memory.