Data selection based on uncertainty quantification

Patent metadata

Field	Value
Publication number	US-11931909-B2
Application number	US-202117331466-A
Country	US
Kind code	B2
Filing date	May 26, 2021
Priority date	May 26, 2021
Publication date	Mar 19, 2024
Grant date	Mar 19, 2024

Abstract

Apparatuses, systems, and techniques generate poses of an object based on data of the object observed from a first viewpoint and a second viewpoint. The poses can be evaluated to determine a portion of the data usable by an estimator to generate a pose of the object.

First claim

What is claimed is:

1. A computer system comprising one or more processors and computer-readable memory storing instructions executable by the one or more processors to cause the computer system to at least:
perform a first comparison of first results of a first estimator and a second estimator, the first results obtained by inputting into the first estimator and second estimator first data associated with observing an object;
perform a second comparison of second results of the first estimator and the second estimator, the second results obtained by inputting into the first estimator and the second estimator second data associated with observing the object; and
based at least in part on the first comparison and the second comparison, select the first data associated with observing the object or the second data associated with observing the object to be obtained by the first estimator or the second estimator.

2. The computer system according to claim 1 , wherein the first data is generated by a sensor disposed to generate the first data from a first viewpoint and the second data is generated by the sensor disposed to generate the second data from a second viewpoint.

3. The computer system according to claim 1 , wherein the first data is generated by a first sensor disposed to generate the first data from a first viewpoint and the second data is generated by a second sensor disposed to generate the second data from a second viewpoint.

4. The computer system according to claim 1 , wherein the first estimator is a first neural network and the second estimator is a second neural network.

5. The computer system according to claim 4 , wherein the first neural network and the second neural network are equivalent neural networks, the first neural network trained using a first data set and the second neural network trained using a second data set, the first data set being different than the second data set.

6. The computer system according to claim 4 , wherein the first neural network and the second neural network are different neural networks, the first neural network and the second neural network trained using a common data set.

7. The computer system according to claim 1 , wherein performing the first comparison generates a first value representing a first uncertainty quantification and performing the second comparison generates a second value representing a second uncertainty quantification.

8. The computer system according to claim 1 , wherein the first results comprise a first bounding box and a second bounding box and the second results comprise a third bounding box and a fourth bounding box, the first and third bounding boxes generated by the first estimator and the second and fourth bounding boxes generated by the second estimator.

9. The computer system according to claim 1 , wherein the instructions executable by the one or more processors are further to cause the computer system to at least:
cause the first estimator or the second estimator to generate a grasp pose corresponding to the object; and
based on the grasp pose, control a robot to grasp the object using a robotic manipulator of the robot.

10. The computer system according to claim 1 , wherein the instructions executable by the one or more processors are further to cause the computer system to at least:
cause the first estimator or the second estimator to generate a pose corresponding to the object; and
based on the pose, control a computer-implemented device.

11. A device comprising:
one or more processors and memory storing executable instructions that, as a result of being executed by the one or more processors, cause the device to:
generate a first set of data based on an object observed from a first viewpoint;
generate a second set of data based on the object observed from a second viewpoint;
determine a first value based on the first set of data and a second value based on the second set of data; and
based on the first and second values, selecting the first set of data or the second set of data to be processed.

12. The device according to claim 11 , wherein the first viewpoint is different from the second viewpoint.

13. The device according to claim 11 , wherein the data associated with the object observed from the first viewpoint is generated by a sensor device in the data associated with the object observed from the second viewpoint is generated by the sensor device, the sensor device comprising an image capturing device or a radar device.

14. The device according to claim 11 , wherein generating the first set of data based on the object observed from the first viewpoint comprises:
processing the data of the object observed from the first viewpoint with a first neural network to generate a first portion of data in the first set of data; and
processing the data of the object observed from the first viewpoint with a second neural network to generate a second portion of data in the first set of data.

15. The device according to claim 11 , wherein generating the second set of data based on the object observed from the second viewpoint comprises:
processing the data of the object observed from the second viewpoint with a first neural network to generate a first portion of data in the second set of data; and
processing the data of the object observed from the second viewpoint with a second neural network to generate a second portion of data in the second set of data.

16. The device according to claim 11 , wherein determining the first value comprises calculating an average disagreement between discrete data portions associated with the first set of data, and wherein determining the second value comprises calculating an average disagreement between discrete data portions associated with the second set of data.

17. The device according to claim 11 , wherein the object observed from the first viewpoint is observed by a sensor associated with the device and the object observed from the second viewpoint is observed by the sensor associated with the device.

18. A computer-implemented method comprising:
generating a plurality of evaluations by at least, for each viewpoint of a plurality of viewpoints, evaluating outputs of estimators applied to data associated with an object detected from the viewpoint; and
determining to process, based at least in part on the plurality of evaluations, the data associated with the object detected from a viewpoint of a plurality of viewpoints.

19. The computer-implemented method according to claim 18 , wherein individual estimators of the estimators are implemented by a neural network.

20. The computer-implemented method according to claim 19 , wherein individual neural networks of the neural networks are implemented by an equivalent neural network, and each neural network of the neural networks is trained with a distinct data set.

21. The computer-implemented method according to claim 19 , wherein individual neural networks of the neural networks are different neural networks, and each neural network of the neural networks is trained with a common data set.

22. The computer-implemented method according to claim 18 , wherein the plurality of evaluations comprise evaluations generated based on the outputs of the estimators comprising at least object poses generated by the estimators based on the data associated with the object.

23. The computer-implemented method according to claim 22 , wherein the object poses comprise bounding cuboids associated with

Assignees

• Nvidia Corp

Inventors

• Tremblay Jonathan
• Tozeto Ramos Fabio
• Zhu Yuke
• Anandkumar Anima
• Shi Guanya

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• B25J9/1697 Primary

  Vision controlled systems · CPC title

• B25J9/161 Primary

  Hardware, e.g. neural networks, fuzzy logic, interfaces, processor · CPC title

• B25J9/1612

  characterised by the hand, wrist, grip control · CPC title