Sensor for safe detection of intrusions in a 3D volume
In various embodiments, systems and methods for safely operating machinery such as industrial robots signal intrusions into and/or above computationally defined safeguarded volumes in a workspace during sensor monitoring of the workspace. Various related actions may be taken in response thereto, including restricting operation of the machinery and/or issuing safety or occlusion signals.
1. A method of safely operating machinery in a three-dimensional workspace, the method comprising:
providing a sensor associated with a grid of pixels for recording images of the workspace within a field of view of the sensor, each pixel (i) having a pixel field of view extending therefrom and (ii) being configured to generate a depth value indicative of an estimated distance from the pixel to an object within the pixel field of view thereof;
computationally defining within the field of view of the sensor a three-dimensional safeguarded volume having an outer boundary by, at least in part, storing for each pixel (i) an entry point corresponding to a first distance from the pixel at which the pixel field of view enters the safeguarded volume, and (ii) an exit point corresponding to a second distance from the pixel at which the pixel field of view exits the safeguarded volume;
monitoring the workspace with the sensor; and
signaling an intrusion into the safeguarded volume when, for at least one of the pixels, a reported depth value registered by a processor is greater than the entry point of the pixel and less than the exit point of the pixel.
2. The method of claim 1 , further comprising issuing a safety signal when the intrusion is signaled.
3. The method of claim 2 , further comprising restricting activity of the machinery when the intrusion is signaled.
4. The method of claim 3 , wherein restricting activity of the machinery comprises stopping the machinery or modifying an operation speed of the machinery.
5. The method of claim 1 , further comprising:
identifying the at least one of the pixels for which the reported depth value is greater than the entry point of the pixel and less than the exit point of the pixel; and
based thereon, computationally determining a distance between the intrusion and the machinery.
6. The method of claim 5 , further comprising issuing a safety signal when the distance between the intrusion and the machinery is less than a predetermined threshold.
7. The method of claim 6 , further comprising restricting activity of the machinery when the distance between the intrusion and the machinery is less than the predetermined threshold.
8. The method of claim 1 , further comprising issuing an occlusion signal when, for at least one of the pixels, the reported depth value is less than the entry point of the pixel.
9. The method of claim 8 , further comprising reporting the reported depth value for the at least one of the pixels.
10. The method of claim 8 , further comprising placing the machinery in a safe state when the occlusion signal is issued.
11. The method of claim 10 , wherein placing the machinery in the safe state comprises stopping the machinery, modifying an operation speed of the machinery, or placing the machinery in a standby mode.
12. The method of claim 1 , wherein the machinery comprises at least one robot.
13. The method of claim 1 , wherein the safeguarded volume is only a portion of the sensor field of view.
14. The method of claim 1 , wherein the sensor comprises a 3D time-of-flight camera.
15. The method of claim 1 , wherein the entry point and exit point for each pixel are stored in a lookup table.
16. A system for safely operating machinery in a three-dimensional workspace, the system comprising:
a sensor associated with a grid of pixels for recording images of the workspace within a field of view of the sensor, each pixel (i) having a pixel field of view extending therefrom and (ii) being configured to generate a depth value indicative of an estimated distance from the pixel to an object within the pixel field of view thereof; and
a processor for:
computationally defining within the field of view of the sensor a three-dimensional safeguarded volume having an outer boundary by, at least in part, storing for each pixel (i) an entry point corresponding to a first distance from the pixel at which the pixel field of view enters the safeguarded volume, and (ii) an exit point corresponding to a second distance from the pixel at which the pixel field of view exits the safeguarded volume; and
during monitoring of the workspace with the sensor, signaling an intrusion into the safeguarded volume when, for at least one of the pixels, a reported depth value registered by the processor is greater than the entry point of the pixel and less than the exit point of the pixel.
17. The system of claim 16 , wherein the processor is configured to issue a safety signal when the intrusion is signaled.
18. The system of claim 17 , wherein the processor is configured to restrict activity of the machinery when the intrusion is signaled.
19. The system of claim 18 , wherein restricting activity of the machinery comprises stopping the machinery or modifying an operation speed of the machinery.
20. The system of claim 16 , wherein the processor is configured to:
identify the at least one of the pixels for which the reported depth value is greater than the entry point of the pixel and less than the exit point of the pixel; and
based thereon, computationally determine a distance between the intrusion and the machinery.
21. The system of claim 20 , wherein the processor is configured to issue a safety signal when the distance between the intrusion and the machinery is less than a predetermined threshold.
22. The system of claim 21 , wherein the processor is configured to restrict activity of the machinery when the distance between the intrusion and the machinery is less than the predetermined threshold.
23. The system of claim 16 , wherein the processor is configured to issue an occlusion signal when, for at least one of the pixels, the reported depth value is less than the entry point of the pixel.
24. The system of claim 23 , wherein the processor is configured to report the reported depth value for the at least one of the pixels.
25. The system of claim 23 , wherein the processor is configured to place the machinery in a safe state when the occlusion signal is issued.
26. The system of claim 25 , wherein placing the machinery in the safe state comprises stopping the machinery, modifying an operation speed of the machinery, or placing the machinery in a standby mode.
27. The system of claim 16 , wherein the machinery comprises at least one robot.
28. The system of claim 16 , wherein the safeguarded volume is only a portion of the sensor field of view.
29. The system of claim 16 , wherein the sensor comprises a 3D time-of-flight camera.
30. The system of claim 16 , further comprising a computer memory, wherein the entry point and exit point for each pixel are stored in a lookup table within the computer memory.
31. A method of safely operating machinery in a three-dimensional workspace, the method comprising:
providing a sensor associated with a grid of pixels for recording images of the workspace within a field of view of the sensor, each pixel (i) having a pixel field of view extending therefrom and (ii) being configured to generate a depth value indicative of an estimated distance from the pixel to an object within the pixel field of view thereof;
computationally defining within the field of view of the sensor a three-dimensional safeguarded volume having an outer boundary by, at least in part, storing for each pixel (i) an entry point corresponding to a first distance from the pixel at which the pixel field of view enters the safeguarded volume, and (ii) an exit point corresponding to a second distance from the pixel at which the pixel field of view exits the safeguarded volume;
computationally defining within the field of view of the sensor one or more entry regions each having an outer boundary adjacent to the outer boundary of the safeguarded volume;
monitoring the workspace with the sensor; and
generating an alert signal when an intrusion by an obstruction is detected in an entry region.
32. The method of claim 31 , further comprising, when the intrusion by the obstruction is detected in the entry region, incrementing a counter if the obstruction is detected in the safeguarded volume and decrementing the counter if the obstruction is not detected in the safeguarded volume.
33. A system for safely operating machinery in a three-dimensional workspace, the system comprising:
a sensor associated with a grid of pixels for recording images of the workspace within a field of view of the sensor, each pixel (i) having a pixel field of view extending therefrom and (ii) being configured to generate a depth value indicative of an estimated distance from the pixel to an object within the pixel field of view thereof; and
a processor for:
computationally defining within the field of view of the sensor a three-dimensional safeguarded volume having an outer boundary by, at least in part, storing for each pixel (i) an entry point corresponding to a first distance from the pixel at which the pixel field of view enters the safeguarded volume, and (ii) an exit point corresponding to a second distance from the pixel at which the pixel field of view exits the safeguarded volume;
computationally defining within the field of view of the sensor one or more entry regions each having an outer boundary adjacent to the outer boundary of the safeguarded volume; and
during monitoring of the workspace with the sensor, generating an alert signal when an intrusion by an obstruction is detected in an entry region.
34. The system of claim 33 , wherein the processor is configured to, when the intrusion by the obstruction is detected in the entry region, increment a counter if the obstruction is detected in the safeguarded volume and decrement the counter if the obstruction is not detected in the safeguarded volume.