Physical context management for a motor vehicle

• US 7,610,130 B1
• Filed: 07/20/2006
• Issued: 10/27/2009
• Est. Priority Date: 07/20/2005
• Status: Active Grant

• Current Assignee: National Technology & Engineering Solutions Of Sandia LLC (Honeywell International Inc.)
• Original Assignee: Sandia Corporation (Martin Marietta Corporation)
• Inventors: Dixon, Kevin R., Forsythe, James C., Lippitt, legal representative, Lippitt, Carl E.
• Primary Examiner(s): Zanelli; Michael J.
• Application Number:
  US11/489,833
• Time in Patent Office: 1,195 Days
• Field of Search: None
• US Class Current: 701/36
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: B60W 40/08 related to drivers or passengers

Abstract

Computer software for and a method of enhancing safety for an operator of a motor vehicle comprising employing a plurality of sensors of vehicle and operator conditions, matching collective output from the sensors against a plurality of known dangerous conditions, and preventing certain activity of the operator if a known dangerous condition is detected.

Claims

1. A method of enhancing safety for an operator of a motor vehicle, the method comprising the steps of:

employing a plurality of sensors of vehicle and operator conditions;

matching collective output from the sensors against a plurality of known dangerous conditions; and

preventing certain activity of the operator if a known dangerous condition is detected; and

wherein the matching step comprises matching against a plurality of conditions known a priori but as determined from a plurality of test subjects experiencing simulations of those conditions and from the sensor data received during recording of those simulations.

2. The method of claim 1 wherein the matching step comprises employing a nonlinear dynamical system.

3. The method of claim 2 wherein in the matching step an optimal solution of a learning algorithm of the nonlinear dynamical system has been calculated.

4. The method of claim 3 wherein in the matching step false negatives are substantially reduced in the calculation of an optimal solution via a method selected from the group consisting of gradient-descent methods and genetic algorithm methods.

5. The method of claim 2 wherein the matching step comprises matching against a plurality of known conditions as determined automatically from collected sensor data of those conditions and from concomitant human-scored difficulty estimates.

6. The method of claim 5 wherein the matching step comprises matching against a plurality of known conditions as determined via unsupervised learning from collected sensor data of those conditions and from concomitant human-scored difficulty estimates.

7. The method of claim 6 wherein the matching step comprises matching against a plurality of known conditions as determined via unsupervised learning employing linear regression of a 2*N dimensional vector of sensor input from N sensors.

8. The method of claim 5 additionally comprising allowing the operator to make difficulty estimates concerning current conditions, which estimates are then incorporated into the matching step.

9. The method of claim 1 wherein the preventing step comprises preventing one or more activities from the list consisting of employing a telephone, listening to audio programs, listening to high-volume audio programs, and employing vehicle interior lighting.

10. A physical storage device having machine executable code stored therein, which when executed by a computer enhances the safety for an operator of a motor vehicle, the device comprising code for:

receiving data from a plurality of sensors of vehicle and operator conditions;

matching collective output from the sensors against a plurality of known dangerous conditions; and

preventing certain activity of the operator if a known dangerous condition is detected; and

wherein the matching code comprises code matching against a plurality of conditions known a priori but as determined from a plurality of test subjects experiencing simulations of those conditions and from the sensor data received during recording of those simulations.

11. The storage device of claim 10 wherein the matching code comprises code implementing a nonlinear dynamical system.

12. The storage device of claim 11 wherein the matching code derives from an optimal solution of a learning algorithm of the nonlinear dynamical system.

13. The storage device of claim 12 wherein the matching code comprises code in which false negatives are substantially reduced via the calculation of an optimal solution via a method selected from the group consisting of gradient-descent methods and genetic algorithm methods.

14. The storage device of claim 11 wherein the matching code comprises code matching against a plurality of known conditions as determined automatically from collected sensor data of those conditions and from concomitant human-scored difficulty estimates.

15. The storage device of claim 14 wherein the matching code comprises code matching against a plurality of known conditions as determined via unsupervised learning from collected sensor data of those conditions and from concomitant human-scored difficulty estimates.

16. The storage device of claim 15 wherein the matching code comprises code matching against a plurality of known conditions as determined via unsupervised learning employing linear regression of a 2*N dimensional vector of sensor input from N sensors.

17. The storage device of claim 14 additionally comprising code allowing the operator to make difficulty estimates concerning current conditions, which estimates are then incorporated into operations of the matching code.

18. The storage device of claim 10 wherein the preventing code comprises code preventing one or more activities from the list consisting of employing a telephone, listening to audio programs, listening to high-volume audio programs, and employing vehicle interior lighting.

19. A method of enhancing safety for an operator of a motor vehicle, the method comprising the steps of:

employing a plurality of sensors of vehicle and operator conditions;

matching collective output from the sensors against a plurality of known dangerous conditions; and

preventing certain activity of the operator if a known dangerous condition is detected; and

wherein the matching step comprises matching against a plurality of known conditions as determined automatically from collected sensor data of those conditions and from concomitant human-scored difficulty estimates.

20. The method of claim 19 wherein the matching step comprises matching against a plurality of known conditions as determined via unsupervised learning from collected sensor data of those conditions and from concomitant human-scored difficulty estimates.

21. The method of claim 20 wherein the matching step comprises matching against a plurality of known conditions as determined via unsupervised learning employing linear regression of a 2*N dimensional vector of sensor input from N sensors.

22. The method of claim 19 additionally comprising allowing the operator to make difficulty estimates concerning current conditions, which estimates are then incorporated into the matching step.

23. A physical storage device having machine executable code stored therein, which when executed by a computer enhances the safety for an operator of a motor vehicle, the device comprising code for:

receiving data from a plurality of sensors of vehicle and operator conditions;

matching collective output from the sensors against a plurality of known dangerous conditions; and

preventing certain activity of the operator if a known dangerous condition is detected; and

wherein the matching code comprises code matching against a plurality of known conditions as determined automatically from collected sensor data of those conditions and from concomitant human-scored difficulty estimates.

24. The storage device of claim 23 wherein the matching code comprises code matching against a plurality of known conditions as determined via unsupervised learning from collected sensor data of those conditions and from concomitant human-scored difficulty estimates.

25. The storage device of claim 24 wherein the matching code comprises code matching against a plurality of known conditions as determined via unsupervised learning employing linear regression of a 2*N dimensional vector of sensor input from N sensors.

26. The storage device of claim 23 additionally comprising code allowing the operator to make difficulty estimates concerning current conditions, which estimates are then incorporated into operations of the matching code.