Vision-based robot control system

• US 10,377,042 B2
• Filed: 06/17/2016
• Issued: 08/13/2019
• Est. Priority Date: 06/17/2016
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Anderson, Glen J.
• Primary Examiner(s): Jen, Ian
• Application Number:
  US15/185,241
• Publication Number:
  US 20170361466A1
• Time in Patent Office: 1,152 Days
• CPC Class Codes: B25J 9/1697 Vision controlled systems

Abstract

Various systems and methods for providing a vision-based robot control system are provided herein. A vision-based robot control system comprises a camera system interface to receive image data from a camera system; a trigger detection unit to determine a triggering action from the image data; and a transceiver to initiate a robot operation associated with the triggering action.

Claims

1. A vision-based robot control system, the system comprising:

a camera system interface to receive image data from a camera system;

a trigger detection unit to determine a triggering action from the image data; and

a transceiver to initiate a robot operation associated with the triggering action.

2. The system of claim 1, wherein to receive the image data, the camera system interface is to receive an image of a user performing a gesture;

and

wherein to determine the triggering action, the trigger detection unit is to determine the triggering action corresponding to the gesture.

3. The system of claim 2, wherein the gesture comprises pointing to a location in an environment.

4. The system of claim 2, wherein the gesture comprises tapping a foot on a location in an environment.

5. The system of claim 4, wherein the triggering action is the gesture and the robot operation comprises performing extra cleaning at the location in the environment.

6. The system of claim 1, wherein the image data includes a gesture performed by a user, and wherein the trigger detection unit is to receive a voice command issued by the user and determine the triggering action using the gesture and the voice command.

7. The system of claim 6, wherein the gesture is used to specify a location in the environment, and wherein the voice command is used to specify an action to be taken by the robot.

8. The system of claim 1, wherein the image data includes a non-visible marking made by a user, the non-visible marking acting as the triggering action.

9. The system of claim 8, wherein the non-visible marking comprises an infrared-visible ink marking.

10. The system of claim 8, wherein the non-visible marking is a symbol, and to initiate the robot operation, an operation database interface is used to access a lookup table and search for the symbol to identify a corresponding robot operation.

11. The system of claim 1, wherein the trigger detection unit is to obtain a geolocation associated with the triggering action;

and wherein the transceiver is to initiate the robot operation to be performed at the geolocation.

12. The system of claim 11, wherein the geolocation is obtained from a device operated by a user performing the triggering action.

13. The system of claim 11, wherein the geolocation is obtained from a gesture performed by the user, the gesture captured in the image data.

14. The system of claim 1, wherein to initiate the robot operation, the transceiver is to transmit a command sequence to a robot over a wireless network.

15. The system of claim 1, wherein the robot operation comprises a cleaning task.

16. A method of providing a vision-based robot control system, the method comprising:

receiving, at a processor-based robot control system, image data from a camera system;

determining a triggering action from the image data; and

initiating a robot operation associated with the triggering action.

17. The method of claim 16, wherein receiving the image data comprises receiving an image of a user performing a gesture;

and

wherein determining the triggering action comprises determining the triggering action corresponding to the gesture.

18. The method of claim 17, wherein the gesture comprises pointing to a location in an environment.

19. The method of claim 17, wherein the gesture comprises tapping a foot on a location in an environment.

20. The method of claim 19, wherein the triggering action is the gesture and the robot operation comprises performing extra cleaning at the location in the environment.

21. At least one machine-readable medium including instructions, which when executed by a machine, cause the machine to

receive, at a processor-based robot control system, image data from a camera system;

determine a triggering action from the image data; and

initiate a robot operation associated with the triggering action.

22. The at least one machine-readable medium of claim 21, wherein the instructions to receive the image data comprise instructions to receive an image of a user performing a gesture;

and

wherein the instructions to determine the triggering action comprise instructions to determine the triggering action corresponding to the gesture.

23. The at least one machine-readable medium of claim 22, wherein the gesture comprises pointing to a location in an environment.

24. The at least one machine-readable medium of claim 22, wherein the gesture comprises tapping a foot on a location in an environment.

25. The at least one machine-readable medium of claim 24, wherein the triggering action is the gesture and the robot operation comprises performing extra cleaning at the location in the environment.