Methods and apparatus to facilitate autonomous navigation of robotic devices

Patent metadata

Field	Value
Publication number	US-11249492-B2
Application number	US-201916365361-A
Country	US
Kind code	B2
Filing date	Mar 26, 2019
Priority date	Mar 26, 2019
Publication date	Feb 15, 2022
Grant date	Feb 15, 2022

Abstract

Methods and apparatus to facilitate autonomous navigation of robotic devices. An example autonomous robot includes a region model analyzer to: analyze a first image of an environment based on a first neural network model, the first image captured by an image sensor of the robot when the robot is in a first region of the environment; and analyze a second image of the environment based on a second neural network model, the second image captured by the image sensor when the robot is in a second region of the environment, the second neural network associated with the second region. The example robot further includes a movement controller to: autonomously control movement of the robot within the first region toward the second region based on the analysis of the first image; and autonomously control movement of the robot within the second region based on the analysis of the second image.

First claim

What is claimed is:

1. An autonomous robot, comprising:
at least one memory;
instructions in the robot, and
processor circuitry to execute the instructions a region model analyzer to:
analyze a first image of an environment based on a first neural network model, the first image captured by an image sensor of the robot when the robot is in a first region of the environment, the first neural network model used exclusively when the robot is in the first region;
analyze a second image of the environment based on a second neural network model, the second image captured by the image sensor when the robot is in a second region of the environment, the second neural network model used exclusively when the robot is in the second region;
autonomously control movement of the robot within the first region toward the second region based on the analysis of the first image; and
autonomously control movement of the robot within the second region based on the analysis of the second image.

2. The robot of claim 1 , wherein the first region overlaps the second region, the first and second regions defining different portions of a travel path for the robot to navigate through the environment.

3. The robot of claim 2 , wherein the processor circuitry is to:
in response to an obstacle along the travel path, request a new travel path from a remote server, the new travel path defined by different regions within the environment; and
autonomously control movement of the robot along the new travel path based on different neural network models respectively associated with the different regions.

4. The autonomously controlled robot of claim 3 , wherein the processor circuitry is to receive the different neural network models before detection of the obstacle.

5. The robot of claim 2 , wherein the travel path extends through a series of multiple different regions of the environment, each successive one of the multiple different regions in the series to overlap an immediately preceding one of the multiple different regions in the series, the multiple different regions including the first region, the second region, and other regions, each of the multiple different regions associated with a corresponding one of multiple different neural networks, the processor circuitry to control movement of the robot within each successive one of the multiple different regions in the series based on the corresponding one of the different neural networks.

6. The robot of claim 1 , wherein the processor circuitry is to autonomously control movement of the robot by controlling movement of the robot from a current point within the first region toward a second point within the first region based on the analysis of the first image, the second point circumscribed by the second region.

7. The robot of claim 1 , wherein a center point of the first region is located within the second region.

8. The robot of claim 7 , wherein the processor circuitry is to autonomously control movement of the robot toward the second region by controlling movement of the robot toward the center point of the first region.

9. The robot of claim 8 , wherein the processor circuitry is to begin controlling movement of the robot within the second region based on the second neural network model in response to the robot being within a threshold distance of the center point of the first region.

10. The robot of claim 1 , wherein the processor circuitry is to:
determine a distance between a current location of the robot and a center point of the first region;
determine an orientation of the robot relative to the center point; and
autonomously control movement of the robot based on the distance and the orientation.

11. The robot of claim 1 , wherein the processor circuitry is to, in response to the robot entering the second region, access a third neural network model from a remote server while the robot is moving through the second region, the third neural network model associated with a third region within the environment.

12. The robot of claim 11 , wherein the processor circuitry is to remove the first neural network model from memory after the robot enters the second region.

13. The robot of claim 1 , wherein the robot is to navigate through the environment without a map of the environment.

14. The robot of claim 1 , wherein the environment is an indoor environment.

15. The robot of claim 14 , wherein the image sensor is directed upward such that the first and second images include a ceiling of the indoor environment.

16. A non-transitory computer readable medium comprising instructions that, when executed, cause a robot to at least:
capture, with an image sensor, a first image of an environment from within a first region of the environment;
autonomously move within the first region toward a second region within the environment based on the first image and a first neural network model used exclusively when the robot is in associated with the first region;
capture, with the image sensor, a second image corresponding to the second region; and
autonomously move within the second region based on the second image and a second neural network model used exclusively when the robot is in the second region.

17. The non-transitory computer readable medium of claim 16 , wherein the first region overlaps the second region, the first and second regions defining different portions of a travel path for the robot to navigate through the environment.

18. The non-transitory computer readable medium of claim 17 , wherein the instructions further cause the robot to:
respond to an obstacle along the travel path by requesting a new travel path from a remote server, the new travel path defined by different regions within the environment; and
autonomously move along the new travel path based on different neural network models associated with respective ones of the different regions.

19. The non-transitory computer readable medium of claim 18 , wherein the instructions further cause the robot to download the different neural network models before detection of the obstacle.

20. The non-transitory computer readable medium of claim 16 , wherein a center point of the first region is located within the second region.

21. The non-transitory computer readable medium of claim 20 , wherein the instructions further cause the robot to autonomously move toward the second region by autonomously moving toward the center point of the first region.

22. The non-transitory computer readable medium of claim 16 , wherein the instructions further cause the robot to:
determine a distance between a current location of the robot and a center point of the first region;
determine an orientation of the robot relative to the center point; and
autonomously move based on the distance and the orientation.

23. A method to autonomously control movement of a robot, the method comprising:
capturing, with an image sensor, a first image of an environment from within a first region of the environment;
autonomously controlling movement of the robot within the first region toward a second region within the environment based on the first image and a first neural network model, the first neural network model used exclusively when the robot is in the first region;
capturing, with the image sensor, a second image corresponding to the second region; and
autonomously controlling movement of the robot within the second region based on the second image and a second neural network model, t

Assignees

• Intel Corp

Inventors

• Zamora Esquivel Julio Cesar
• Aldana Lopez Rodrigo
• Campos Macias Leobardo
• Cruz Vargas Jesus Adan
• De La Guardia Gonzalez Rafael
• Gomez Gutierrez David
• Macias Garcia Edgar

Classifications

• G06V10/82 Primary

  using neural networks · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06V20/10

  Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59) · CPC title

• G05D1/0282

  generated in a local control room · CPC title

• G05D1/0011

  associated with a remote control arrangement · CPC title