Drone for recognizing and testing monitoring system sensors
Methods, systems, and apparatus, including computer programs encoded on a storage device, for using a drone to test monitoring system sensors. In one aspect, the drone perform operations that include navigating from a first location of a property towards a second location of the property, detecting a sensor that is installed at the property, interrupting, by the drone, navigation through the property from the first location of the property towards the second location of the property to initiate a test of the detected sensor and (ii) determining a sensor test type for the detected sensor, administering a sensor test to the detected sensor, wherein the sensor test is based on the determined sensor test type, evaluating results of the administered test, storing data describing the results of the administered test, and continuing navigation through the property towards the second location of the property or towards another location of the property.
1. A system comprising:
one or more computing devices; and
one or more storage devices, wherein the storage devices include instructions that, when executed by the one or more computing devices, cause to the one or more computing devices to perform operations comprising:
determining, using a trained model that was trained to detect one or more sensors depicted in images, that an image captured by a drone depicts a sensor located at a property;
in response to determining that the image depicts the sensor, providing, to the drone, a first instruction that, when received by the drone, causes the drone to (i) interrupt navigation of the drone at the property and (ii) perform a test on the sensor that was depicted in the image captured by the drone;
obtaining, from the drone, test data indicating whether the sensor is properly functioning; and
in response to obtaining the test data, providing, to the drone, a second instruction that, when received by the drone, causes the drone to resume navigation of the drone within the property.
2. The system of claim 1 , wherein:
the drone comprises a camera; and
the image captured by the drone is captured by the camera.
3. The system of claim 1 , wherein the operations further comprise:
determining, using a second trained model, a sensor type of the sensor included in the image;
determining a test type for testing the sensor using the sensor type; and
wherein the first instruction, when received by the drone, causes the drone to perform a test of the test type when performing the test on the sensor.
4. The system of claim 1 , wherein the operations further comprise:
determining, using the trained model, that a second image captured by a drone does not depict one or more sensors located at the property; and
in response to determining that the second image does not depict the one or more sensors, providing, to the drone, a third instruction that, when received by the drone, causes the drone to continue navigation of the drone within the property without performing a test.
5. The system of claim 1 , wherein the operations further comprise:
providing, to a monitoring system that receives sensor data from the sensor, an instruction to disregard sensor data collected by the sensor for a predetermined amount of time that overlaps with a time when the drone performs the test on the sensor.
6. The system of claim 1 , wherein:
the drone comprises a sensor testing unit;
the sensor comprises a smoke detector; and
the first instruction causes the drone to perform the test on the sensor by using the sensor testing unit to emit an airborne material configured to trigger the smoke detector to generate sensor data that is indicative of presence of smoke.
7. The system of claim 6 , wherein:
the drone comprises a communication unit; and
the first instruction causes the drone to:
perform a test on the smoke detector,
use the communication unit to detect that the smoke detector did not generate data indicating presence of smoke within a predetermined amount of time of performing the test on the smoke detector, and
determine that the smoke detector is not properly functioning in response to detecting that the smoke detector did not generate data indicating presence of smoke within the predetermined amount of time.
8. A method performed by one or more computing devices, the method comprising:
determining, using a trained model that was trained to detect one or more sensors depicted in images, that an image captured by a drone depicts a sensor located at a property;
in response to determining that the image depicts the sensor, providing, to the drone, a first instruction that, when received by the drone, causes the drone to (i) interrupt navigation of the drone at the property and (ii) perform a test on the sensor that was depicted in the image captured by the drone;
obtaining, from the drone, test data indicating whether the sensor is properly functioning; and
in response to obtaining the test data, providing, to the drone, a second instruction that, when received by the drone, causes the drone to resume navigation of the drone within the property.
9. The method of claim 8 , wherein:
the drone comprises a camera; and
the image captured by the drone is captured by the camera.
10. The method of claim 8 , further comprising:
determining, using a second trained model, a sensor type of the sensor included in the image;
determining a test type for testing the sensor using the sensor type; and
wherein the first instruction, when received by the drone, causes the drone to perform a test of the test type when performing the test on the sensor.
11. The method of claim 8 , further comprising:
determining, using the trained model, that a second image captured by a drone does not depict one or more sensors located at the property; and
based on determining that the second image does not depict the one or more sensors, providing, to the drone, a third instruction that, when received by the drone, causes the drone to continue navigation of the drone within the property without performing a test.
12. The method of claim 8 , further comprising:
providing, to a monitoring system that receives sensor data from the sensor, an instruction to disregard sensor data collected by the sensor for a predetermined amount of time that overlaps with a time when the drone performs the test on the sensor.
13. The method of claim 8 , wherein:
the drone comprises a sensor testing unit;
the sensor comprises a smoke detector; and
the first instruction causes the drone to perform the test on the sensor by using the sensor testing unit to emit an airborne material configured to trigger the smoke detector to generate sensor data that is indicative of presence of smoke.
14. The method of claim 13 , wherein:
the drone comprises a communication unit; and
the first instruction causes the drone to:
perform a test on the smoke detector,
use the communication unit to detect that the smoke detector did not generate data indicating presence of smoke within a predetermined amount of time of performing the test on the smoke detector, and
determine that the smoke detector is not properly functioning based on detecting that the smoke detector did not generate data indicating presence of smoke within the predetermined amount of time.
15. At least one non-transitory computer-readable storage device storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
determining, using a trained model, that an image captured by a drone includes a sensor located in a property;
based on determining that the image includes the sensor, providing, to the drone, a first instruction that, when received by the drone, causes the drone to (i) interrupt navigation of the drone within the property and (ii) perform a test on the sensor;
obtaining, from the drone, test data indicating whether the sensor is properly functioning; and
based on obtaining the test data, providing, to the drone, a second instruction that, when received by the drone, causes the drone to resume navigation of the drone within the property.
16. The non-transitory computer-readable storage device of claim 15 , wherein:
the drone comprises a camera; and
the image captured by the drone is captured by the camera.
17. The non-transitory computer-readable storage device of claim 15 , wherein the operations further comprise:
determining, using a second trained model, a sensor type of the sensor included in the image;
determining a test type for testing the sensor based on the sensor type; and
wherein the first instruction, when received by the drone, causes the drone to perform a test of the test type when performing the test on the sensor.
18. The non-transitory computer-readable storage device of claim 15 , wherein the operations further comprise:
determining, using the trained model, that a second image captured by a drone does not depict one or more sensors located at the property; and
based on determining that the second image does not depict the one or more sensors, providing, to the drone, a third instruction that, when received by the drone, causes the drone to continue navigation of the drone within the property without performing a test.
19. The non-transitory computer-readable storage device of claim 15 , wherein the operations further comprise:
providing, to a monitoring system that receives sensor data from the sensor, an instruction to disregard sensor data collected by the sensor for a predetermined amount of time that overlaps with a time when the drone performs the test on the sensor.
20. The non-transitory computer-readable storage device of claim 15 , wherein:
the drone comprises a sensor testing unit;
the sensor comprises a smoke detector; and
the first instruction causes the drone to perform the test on the sensor by using the sensor testing unit to emit an airborne material configured to trigger the smoke detector to generate sensor data that is indicative of presence of smoke.