Method and apparatus for characterizing platform motion

Patent metadata

Field	Value
Publication number	US-10663298-B2
Application number	US-201715632361-A
Country	US
Kind code	B2
Filing date	Jun 25, 2017
Priority date	Jun 25, 2017
Publication date	May 26, 2020
Grant date	May 26, 2020

Abstract

An apparatus and method are disclosed for characterizing motion of a platform. Motion sensor data from a portable device having a sensor assembly may be obtained. The portable device may be within the platform and tethered or untethered, and the mobility of the portable device may be constrained or unconstrained within the platform. Following a determination the platform is moving, motion dynamics of the portable device that are independent from motion dynamics of the platform may be identified and motion sensor data corresponding to motion of the platform and motion sensor data corresponding to the identified independent motion of the portable device may be separated from the obtained motion sensor data. Accordingly, motion sensor data corresponding to motion of the platform that is independent of motion of the portable device may be output. This may be used to derive operator analytics for assessing performance.

First claim

What is claimed is:

1. A method for characterizing motion of a platform, the method comprising:
obtaining motion sensor data from a portable device having a sensor assembly, wherein the portable device is within the platform and may be tethered or untethered and wherein mobility of the portable device may be constrained or unconstrained within the platform;
determining the platform is moving based at least in part on processing the obtained motion sensor data;
identifying motion dynamics of the portable device that are independent from motion dynamics of the platform and the lack thereof when it is determined the platform is moving;
when independent motion dynamics of the portable device are identified, separating motion sensor data corresponding to motion of the platform and motion sensor data corresponding to the identified independent motion of the portable device from the obtained motion sensor data; and
outputting motion sensor data corresponding to motion of the platform that is independent of motion of the portable device.

2. The method of claim 1 , further comprising processing the motion sensor data corresponding to motion of the platform that is independent of motion of the portable device to derive operator analytics for an operator of the platform.

3. The method of claim 2 , further comprising providing a navigation solution for the platform by using the motion sensor data corresponding to motion of the platform that is independent of motion of the portable device, wherein the operator analytics are based at least in part on the navigation solution.

4. The method of claim 2 , wherein the operator analytics are based on at least one of acceleration change, heading change, and speed.

5. The method of claim 4 , wherein the operator analytics include adjusting for detection of events comprising at least one of large acceleration, large deceleration, sharp turns, a vehicle swerve, a vehicle sideways slide and vehicle interaction with rumble strips.

6. The method of anyone of claim 4 or 5 , further comprising scoring operator performance by comparing the operator analytics to local conditions determined to exist during operation of the platform.

7. The method of claim 1 , wherein processing the motion sensor data comprises applying a signal analysis technique.

8. The method of claim 7 , wherein the signal analysis technique comprises at least one of: (i) a statistical analysis; (ii) a frequency-domain analysis; and (iii) a time-domain analysis.

9. The method of claim 1 , wherein processing the motion sensor data comprises applying a machine learning technique.

10. The method of claim 9 , further comprising inputting features extracted from the processed motion sensor data to at least one stored classification model to determine whether the platform is moving.

11. The method of claim 10 , wherein the at least one stored classification model comprises extracted features developed during a training phase.

12. The method of claim 1 , further comprising providing a source of absolute navigational information, wherein determining the platform is moving is based at least in part on absolute navigational information.

13. The method of claim 1 , further comprising obtaining image sensor data from the portable device, wherein determining the platform is moving comprises processing the image sensor data.

14. The method of claim 13 , wherein processing the image sensor data comprises comparing similarity between successive samples.

15. The method of claim 1 , wherein identifying motion dynamics of the portable device that are independent from motion dynamics of the platform comprises processing the motion sensor data from the portable device.

16. The method of claim 15 , wherein processing the motion sensor data comprises at least one of:
(i) calculating radius of rotation;
(ii) assessing change in orientation of the portable device;
(iii) determining heading misalignment between the portable device and the platform; and
(iv) fusing extracted features from different sensor types.

17. The method of claim 15 , further comprising obtaining motion sensor data from at least one auxiliary portable device, wherein processing the motion sensor data comprises comparing motion sensor data from the portable device with motion sensor data from the auxiliary portable device.

18. The method of claim 1 , further comprising providing a source of absolute navigational information, wherein identifying motion dynamics of the portable device that are independent from motion dynamics of the platform is based at least in part on absolute navigational information.

19. The method of claim 15 , further comprising obtaining supplemental sensor data from the portable device, wherein identifying motion dynamics of the portable device that are independent from motion dynamics of the platform comprises processing the supplemental sensor data.

20. The method of claim 1 , further comprising obtaining image sensor data from the portable device, wherein identifying motion dynamics of the portable device that are independent from motion dynamics of the platform comprises processing the image sensor data.

21. The method of claim 20 , wherein the image sensor data comprises a sequence of images and processing the image sensor data comprises calculating a frame related parameter.

22. The method of claim 21 , wherein the frame related parameter is derived from at least one of:
(i) a comparison of pixels between sequential images;
(ii) a comparison of histograms of sequential images; and
(iii) a comparison of frame entropy of sequential images.

23. The method of claim 20 , wherein the image sensor data comprises a sequence of images and processing the image sensor data comprises performing an optical flow analysis.

24. The method of claim 20 , wherein the image sensor data comprises a sequence of images and processing the image sensor data comprises correlating regions between sequential images using at least one of: (i) edge change rate detection; (ii) statistical analysis; (iii) frequency domain analysis; and (iv) multi-resolution analysis.

25. The method of claim 20 , further comprising obtaining image sensor data from at least one auxiliary device, wherein processing the image sensor data comprises comparing image sensor data from the portable device with image sensor data from the auxiliary device.

26. The method of claim 20 , further comprising obtaining supplemental sensor data from the portable device, wherein identifying motion dynamics of the portable device that are independent from motion dynamics of the platform comprises processing the supplemental sensor data.

27. The method of claim 1 , further comprising obtaining ranging sensor data from the portable device, wherein identifying motion dynamics of the portable device that are independent from motion dynamics of the platform comprises processing the ranging sensor data.

28. The method of claim 1 , wherein separating motion sensor data corresponding to motion of the platform and motion sensor data corresponding to the identified independent motion of the portable device from the obtained motion sensor data comprises processing the motion sensor data from the portable device.

29. The method of claim 28 , wherein processing the motion sensor data comprises at least one of:
(i) performing a wavelet analysis;
(

Assignees

• Invensense Inc

Inventors

• Ali Abdelrahman
• Elhoushi Mostafa
• Georgy Jacques
• Goodall Christopher

Classifications

• G06N20/00

  Machine learning · CPC title

• G06T2207/30252

  Vehicle exterior; Vicinity of vehicle · CPC title

• G06T2207/20056

  Discrete and fast Fourier transform, [DFT, FFT] · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title

• G06T2207/30268

  Vehicle interior · CPC title