Method, apparatus, and computer program product for determining sensor orientation

Patent metadata

Field	Value
Publication number	US-11805390-B2
Application number	US-201816210252-A
Country	US
Kind code	B2
Filing date	Dec 5, 2018
Priority date	Dec 5, 2018
Publication date	Oct 31, 2023
Grant date	Oct 31, 2023

Abstract

A method, apparatus, and computer program product are provided to determine sensor orientation. In the context of a method, the orientation of a sensor is predicted based on a predetermined dataset. The method also includes receiving information regarding a location of the sensor and information from which a gravity direction of the sensor is derivable. The method further includes determining a relative orientation of the sensor in relation to a frame of reference and the gravity direction of the sensor. The method still further includes comparing the orientation of the sensor that was predicted and the relative orientation of the sensor to determine a prediction accuracy. The method finally includes updating the predetermined dataset based on the prediction accuracy of the sensor orientation.

First claim

That which is claimed:

1. The method for determining sensor orientation, the method comprising:
utilizing a neural network to establish a predetermined dataset using at least one of a known set of orientations or a loss function, wherein the predetermined dataset provides information pertaining to i) an orientation of a sensor or ii) a type of sensor;
predicting an orientation of the sensor based on the predetermined dataset;
receiving, from the sensor, information regarding a location of the sensor and information from which a gravity direction of the sensor is derivable;
determining, via a processor, a relative orientation of the sensor in relation to a frame of reference and the gravity direction of the sensor;
normalizing data from the sensor relative to the location and the orientation of the sensor to produce normalized data that is combinable with other sensor readings regardless of position or orientation;
comparing the orientation of the sensor that was predicted and the relative orientation of the sensor to determine a prediction accuracy; and
updating the predetermined dataset based on the prediction accuracy of the sensor orientation.

2. The method according to claim 1 further comprising receiving, from at least one additional sensor, information regarding a location of the at least one additional sensor and information from which a gravity direction of the at least one additional sensor is derivable.

3. The method according to claim 2 , wherein the sensor and the at least one additional sensor have a plurality of sensor types.

4. The method according to claim 1 further comprising storing, via a storage device, at least one of the predicted orientations of the sensor, the relative orientation of the sensor, or the prediction accuracy.

5. The method according to claim 1 , wherein the sensor is carried by a vehicle.

6. The method according to claim 1 further comprising establishing the frame of reference for sensing by the sensor.

7. An apparatus for determining sensor orientation, the apparatus comprising at least one processor and at least one non-transitory memory including computer program code instructions, the computer program code instructions configured to, when executed, cause the apparatus to:
utilize a neural network to establish a predetermined dataset using at least one of a known set of orientations or a loss function, wherein the predetermined dataset provides information pertaining to i) an orientation of a sensor or ii) a type of sensor;
predict an orientation of the sensor based on the predetermined dataset;
receive information regarding a location of the sensor and information from which a gravity direction of the sensor is derivable;
determine a relative orientation of the sensor in relation to a frame of reference and the gravity direction of the sensor;
normalize data from the sensor relative to the location and the orientation of the sensor to produce normalized data that is combinable with other sensor readings regardless of position or orientation;
compare the orientation of the sensor that was predicted and the relative orientation of the sensor to determine a prediction accuracy; and
update the predetermined dataset based on the prediction accuracy of the sensor orientation.

8. The apparatus according to claim 7 , wherein the computer program code instructions are further configured to, when executed, cause the apparatus to receive, from at least one additional sensor, information regarding a location of the at least one additional sensor and information from which a gravity direction of the at least one additional sensor is derivable.

9. The apparatus according to claim 8 , wherein the sensor and the at least one additional sensor have a plurality of sensor types.

10. The apparatus according to claim 7 , wherein the computer program code instructions are further configured to, when executed, cause the apparatus to store, via a storage device, at least one of the predicted orientations of the sensor, the relative orientation of the sensor, or the prediction accuracy.

11. The apparatus according to claim 7 , wherein the sensor carried by a vehicle.

12. The apparatus according to claim 7 , wherein the computer program code instructions are further configured to, when executed, cause the apparatus to establish the frame of reference for sensing by the sensor.

13. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code portions stored therein, the computer-executable program code portions comprising program code instructions configured to:
utilize a neural network to establish a predetermined dataset using at least one of a known set of orientations or a loss function, wherein the predetermined dataset provides information pertaining to i) an orientation of a sensor or ii) a type of sensor;
predict an orientation of the sensor based on the predetermined dataset;
receive, from the sensor, information regarding a location of the sensor and information from which a gravity direction of the sensor is derivable;
determine a relative orientation of the sensor in relation to a frame of reference and the gravity direction of the sensor;
normalize data from the sensor relative to the location and the orientation of the sensor to produce normalized data that is combinable with other sensor readings regardless of position or orientation;
compare the orientation of the sensor that was predicted and the relative orientation of the sensor to determine a prediction accuracy; and
update the predetermined dataset based on the prediction accuracy of the sensor orientation.

14. The computer program product according to claim 13 , wherein the program code instructions are further configured to receive information regarding a location of at least one additional sensor and information from which a gravity direction of the at least one additional sensor is derivable.

15. The computer program product according to claim 14 , wherein the sensor and the at least one additional sensor have a plurality of sensor types.

16. The computer program product according to claim 13 , wherein the program code instructions are further configured to store at least one of the predicted orientations of the sensor, the relative orientation of the sensor, or the prediction accuracy.

17. The computer program product according to claim 13 , wherein the sensor is carried by a vehicle.

18. The computer program product according to claim 13 , wherein the program code instructions further are configured to establish the frame of reference for sensing by the sensor.

Assignees

• Here Global Bv

Inventors

• Viswanathan Anirudh

Classifications

• G01C25/00

  Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass (testing, calibrating or compensating compasses G01C17/38) · CPC title

• G01C21/165

  combined with non-inertial navigation instruments · CPC title

• G05D1/0088

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/0455

  Auto-encoder networks; Encoder-decoder networks · CPC title