Systems and methods for mapping an environment

Patent metadata

Field	Value
Publication number	US-9996944-B2
Application number	US-201615268203-A
Country	US
Kind code	B2
Filing date	Sep 16, 2016
Priority date	Jul 6, 2016
Publication date	Jun 12, 2018
Grant date	Jun 12, 2018

Abstract

A method for mapping an environment by an electronic device is described. The method includes obtaining a set of sensor measurements. The method also includes determining a set of voxel occupancy probability distributions respectively corresponding to a set of voxels based on the set of sensor measurements. Each of the voxel occupancy probability distributions represents a probability of occupancy of a voxel over a range of occupation densities. The range includes partial occupation densities.

First claim

What is claimed is:

1. A method for mapping an environment by an electronic device, the method comprising:
obtaining a set of sensor measurements comprising at least one of depth measurements or image data;
determining a set of voxel occupancy probability distributions respectively corresponding to a set of voxels based on the set of sensor measurements, wherein each of the voxel occupancy probability distributions represents a probability of occupancy of a voxel over a range of occupation densities, wherein the range comprises partial occupation densities; and
updating the set of voxel occupancy probability distributions based on an affine function.

2. The method of claim 1 , further comprising, determining a set of confidence values respectively corresponding to the set of voxels.

3. The method of claim 2 , wherein each of the set of confidence values is a variance respectively based on each of the set of voxel occupancy probability distributions.

4. The method of claim 1 , wherein determining and updating each of the set of voxel occupancy probability distributions is based on an inverse cause model.

5. The method of claim 1 , wherein determining and updating each of the set of voxel occupancy probability distributions is based on Bayes' rule.

6. The method of claim 1 , wherein determining and updating each of the set of voxel occupancy probability distributions is based on a fusion of measurements from different times.

7. The method of claim 1 , wherein determining and updating each of the set of voxel occupancy probability distributions is based on a fusion of measurements from different sensors.

8. The method of claim 1 , wherein updating each of the set of voxel occupancy probability distributions comprises multiplying a previous probability distribution with the affine function.

9. The method of claim 1 , wherein determining the set of voxel occupancy probability distributions is based on an inverse cause model, wherein the inverse cause model models a probability that a voxel is a cause of one or more of the set of sensor measurements.

10. The method of claim 1 , wherein the range of occupation densities is a continuous range between completely empty and completely occupied.

11. An electronic device for mapping an environment, comprising:
a processor configured to:
obtain a set of sensor measurements comprising at least one of depth measurements or image data;
determine a set of voxel occupancy probability distributions respectively corresponding to a set of voxels based on the set of sensor measurements, wherein each of the voxel occupancy probability distributions represents a probability of occupancy of a voxel over a range of occupation densities, wherein the range comprises partial occupation densities; and
update the set of voxel occupancy probability distributions based on an affine function.

12. The electronic device of claim 11 , wherein the processor is configured to determine a set of confidence values respectively corresponding to the set of voxels.

13. The electronic device of claim 12 , wherein each of the set of confidence values is a variance respectively based on each of the set of voxel occupancy probability distributions.

14. The electronic device of claim 11 , wherein the processor is configured to determine and update each of the set of voxel occupancy probability distributions based on an inverse cause model.

15. The electronic device of claim 11 , wherein the processor is configured to determine and update each of the set of voxel occupancy probability distributions based on Bayes' rule.

16. The electronic device of claim 11 , wherein the processor is configured to determine and update each of the set of voxel occupancy probability distributions based on a fusion of measurements from different times.

17. The electronic device of claim 11 , wherein the processor is configured to determine and update each of the set of voxel occupancy probability distributions based on a fusion of measurements from different sensors.

18. The electronic device of claim 11 , wherein the processor is configured to update each of the set of voxel occupancy probability distributions by multiplying a previous probability distribution with the affine function.

19. The electronic device of claim 11 , wherein the processor is configured to determine the set of voxel occupancy probability distributions based on an inverse cause model, wherein the inverse cause model models a probability that a voxel is a cause of one or more of the set of sensor measurements.

20. The electronic device of claim 11 , wherein the range of occupation densities is a continuous range between completely empty and completely occupied.

21. A computer-program product for mapping an environment, comprising a non-transitory tangible computer-readable medium having instructions thereon, the instructions comprising:
code for causing an electronic device to obtain a set of sensor measurements comprising at least one of depth measurements or image data;
code for causing the electronic device to determine a set of voxel occupancy probability distributions respectively corresponding to a set of voxels based on the set of sensor measurements, wherein each of the voxel occupancy probability distributions represents a probability of occupancy of a voxel over a range of occupation densities, wherein the range comprises partial occupation densities; and
code for causing the electronic device to update the set of voxel occupancy probability distributions based on an affine function.

22. The computer-program product of claim 21 , further comprising code for causing the electronic device to determine a set of confidence values respectively corresponding to the set of voxels.

23. The computer-program product of claim 21 , wherein the code for causing the electronic device to determine the set of voxel occupancy probability distributions is based on an inverse cause model, wherein the inverse cause model models a probability that a voxel is a cause of one or more of the set of sensor measurements.

24. An apparatus for mapping an environment, comprising:
means for obtaining a set of sensor measurements comprising at least one of depth measurements or image data;
means for determining a set of voxel occupancy probability distributions respectively corresponding to a set of voxels based on the set of sensor measurements, wherein each of the voxel occupancy probability distributions represents a probability of occupancy of a voxel over a range of occupation densities, wherein the range comprises partial occupation densities; and
means for updating the set of voxel occupancy probability distributions based on an affine function.

25. The apparatus of claim 24 , further comprising means for determining a set of confidence values respectively corresponding to the set of voxels.

26. The apparatus of claim 24 , wherein the means for determining the set of voxel occupancy probability distributions is based on an inverse cause model, wherein the inverse cause model models a probability that a voxel is a cause of one or more of the set of sensor measurements.

Assignees

• Qualcomm Inc

Inventors

• Aghamohammadi Aliakbar
• Somasundaram Kiran

Classifications

• G06T7/70 Primary

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

• G06T7/50 Primary

  Depth or shape recovery · CPC title

• G06F18/251

  of input or preprocessed data · CPC title

• G01C11/04

  Interpretation of pictures · CPC title

• G01C15/002

  Active optical surveying means (optical plumbing G01C15/105) · CPC title