BLOCKED SENSOR DETECTION AND NOTIFICATION

• US 20160187127A1
• Filed: 12/30/2014
• Published: 06/30/2016
• Est. Priority Date: 12/30/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: DIXON, Michael, PUROHIT, Aveek Ravishekhar
• Granted Patent: US 10,429,177 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01B 21/00 Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
• CPC Class Codes: G08B 29/04 Monitoring of the detection circuits
• CPC Class Codes: G08B 29/046 prevention of tampering with detection circuits
• CPC Class Codes: G08B 29/16 Security signalling or alarm systems, e.g. redundant systems

Abstract

Systems and techniques are provided for blocked sensor detection and notification. A signal may be received from a sensor. The sensor may be determined to be producing anomalous output based on checking the signal from the sensor against a signal from a second sensor on the same sensor device as the sensor, checking the signal from the sensor against signals from sensors on additional sensor devices, and checking the signal from the sensor against a slow temporal model for the sensor. In response to the determination that the sensor is producing anomalous output, a notification may be generated indicating the sensor is producing anomalous output, and a confidence level in the sensor may be degraded.

Claims

1. A computer-implemented method performed by a data processing apparatus, the method comprising:

receiving a signal from a sensor;

determining that the sensor is producing anomalous output based on at least one of;

checking the signal from the sensor against a signal from a second sensor on the same sensor device as the sensor,

checking the signal from the sensor against one or more signals from one or more sensors on one or more additional sensor devices, and

checking the signal from the sensor against a slow temporal model for the sensor;

and in response to the determination that the sensor is producing anomalous output, at least one of;

generating a notification indicating the sensor is producing anomalous output, and

degrading a confidence level in the sensor.

2. The computer-implemented method of claim 1, wherein checking the signal from the sensor against a signal from a second sensor on the same sensor device as the sensor further comprises:

receiving the signal from the second sensor on the same sensor device as the sensor;

determining that the signal from the sensor is inconsistent with the signal from the second sensor; and

generating an indication that the sensor is producing anomalous output.

3. The computer-implemented method of claim 1, wherein checking the signal from the sensor against one or more signals from one or more sensors on one or more additional sensor devices further comprises:

receiving the one or more signals from the one or more sensors on the one or more additional sensor devices;

determining that the signal from the sensor is inconsistent with at least one of the one or more signals from the one or more sensors;

determining that the one or more signals from the one or more sensors are consistent with each other; and

generating an indication that the sensor is producing anomalous output.

4. The computer-implemented method of claim 1, wherein checking the signal from the sensor against a slow temporal model tier the sensor further comprises:

receiving the slow temporal model for the sensor;

determining that the signal from the sensor is inconsistent with a signal that the slow temporal model indicates is expected from the sensor in the situation in which the signal from the sensor was generated; and

generating an indication that the sensor is producing anomalous output.

5. The computer-implemented method of claim 4, wherein the slow temporal model for the sensor comprises signals from the sensor over a period of time.

6. The computer-implemented method of claim 4, wherein the slow temporal model is one of a statistical, probabilistic, or machine learning based model for the signals from the sensor.

7. The computer-implemented method of claim 4, further comprising determining that the signal from the sensor is inconsistent with a signal that the slow temporal model indicates is expected over a threshold period of time before generating the indication that the sensor is producing anomalous output.

8. The computer-implemented method of claim 4, further comprising determining that there are no extenuating circumstances causing the signal from the sensor to be inconsistent with the signal that the slow temporal model indicates is expected, before generating the indication that the sensor is producing anomalous output.

9. The computer-implemented method of claim 8, wherein an extenuating circumstance comprises a security system comprising the sensor being set to an away mode or a vacation mode.

10. The computer-implemented method of claim 3, wherein the sensor is a motion sensor, and wherein determining that the signal from the sensor is inconsistent with at least one of the one or more signals from the one or more sensors further comprises:

determining that the signal from the motion sensor indicates no motion is detected in an environment monitored by the motion sensor; and

determining that the at least one of the one or more signals indicates e presence of a moving person within the environment.

11. The computer-implemented method of claim 10, wherein the environment is a room in a structure.

12. The computer-implemented method of claim 1, wherein the sensor is one of motion sensor, a passive infrared sensor, a low power motion sensor, a light sensor, a camera, a microphone, and an entryway sensor.

13. The computer-implemented method of claim 1, wherein the notification is a blocked sensor notification indicating that the sensor is obstructed.

14. The computer-implemented method of claim 1, wherein the notification is sent to one or more of:

a computing device associated with a user of a smart home environment, a display within the smart home environment, and a speaker system within the smart home environment.

24. The computer-implemented system of claim 14, wherein the sensor is a motion sensor, and wherein the hub computing device is adapted to determine that the signal from the sensor is inconsistent with at least one of the one or more signals from the one or more sensors further comprises by determining that the signal from the motion sensor indicates no motion is detected in an environment monitored by the motion sensor and determining that the at least one of the one or more signals indicates the presence of a moving person within the environment.

29. The system of claim 8, wherein the instructions further cause the one or more computers to perform operations comprising:

receiving the signal from the second sensor on the same sensor device as the sensor;

determining that the signal from the sensor is inconsistent with the signal from the second sensor; and

generating an indication that the sensor is producing anomalous output.

15. A computer-implemented system for blocked sensor detection and notification comprising:

a sensor of a smart home environment, the sensor adapted to monitor an aspect of an environment and generate a signal;

a storage comprising one or more slow temporal models, at least one of the slow temporal models associated with the sensor; and

a hub computing device adapted to receive the signal from the sensor, determine that the sensor is producing anomalous output based on at least one of checking the signal from the sensor against a signal from a second sensor on the same sensor device as the sensor, checking the signal from the sensor against one or more signals from one or more sensors on one or more additional sensor devices, and checking the signal from the sensor against the slow temporal model associated with the sensor, generate a notification indicating the sensor is producing anomalous output, and degrade a confidence level in the sensor.

16. The computer-implemented system of claim 15, wherein the hub computing device is further adapted to check the signal from the sensor against a signal from a second sensor on the same sensor device as the sensor by receiving the signal from the second sensor on the same sensor device as the sensor, determining that the signal from the sensor is inconsistent with the signal from the second sensor, and generating an indication that the sensor is producing anomalous output.

17. The computer-implemented system of claim 15, wherein the hub computing device is further adapted to check the signal from the sensor against one or more signals from one or more sensors on one or more additional sensor devices by receiving the one or more signals from the one or more sensors on the one or more additional sensor devices, determining that the signal from the sensor is inconsistent with at least one of the one or more signals from the one or more sensors, determining that the one or more signals from the one or more sensors are consistent with each other, and generating an indication that the sensor is producing anomalous output.

18. The computer-implemented system of claim 15, wherein the hub computing device is further adapted to check the signal from the sensor against a slow temporal model for the sensor further comprises by receiving the slow temporal model for the sensor, determining that the signal from the sensor is inconsistent with a signal that the slow temporal model indicates is expected from the sensor in the situation in which the signal from the sensor was generated, and generating an indication that the sensor is producing anomalous output.

19. The computer-implemented system of claim 15, wherein the slow temporal model for the sensor comprises signals from the sensor over a period of time.

20. The computer-implemented system of claim 15, wherein the slow temporal model is one of a statistical, probabilistic, or machine learning based model for the signals from the sensor.

21. The computer-implemented system of claim 15, wherein the hub computing device is further adapted to determine that the signal from the sensor is inconsistent with a signal that the slow temporal model indicates is expected over a threshold period of time before generating the indication that the sensor is producing anomalous output.

22. The computer-implemented system of claim 15, wherein the hub computing device is further adapted to determine that there are no extenuating circumstances causing the signal from the sensor to be inconsistent with the signal that the slow temporal model indicates is expected, before generating the indication that the sensor is producing anomalous output.

23. The computer-implemented system of claim 22, wherein an extenuating circumstance comprises a security system comprising the sensor being set to an away mode or a vacation mode.

25. The computer-implemented system of claim 15, wherein the sensor is one of motion sensor, a passive infrared sensor, a low power motion sensor, alight sensor, a camera, a microphone, and an entryway sensor.

26. The computer-implemented system of claim 15, wherein the notification is a blocked sensor notification indicating that the sensor is obstructed.

27. The computer-implemented system of claim 15, wherein the hub computing device is further adapted to send the notification to one or more of:

a computing device associated with a user of a smart home environment, a display within the smart home environment, and a speaker system within the smart home environment.

28. A system comprising:

one or more computers and one or more storage devices storing instructions which are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving a signal from a sensor;

determining that the sensor is producing anomalous output based on at least one of

checking the signal from the sensor against a signal from a second sensor on the same sensor device as the sensor,

checking the signal from the sensor against one or more signals from one or more sensors on one or more additional sensor devices, and

checking the signal from the sensor against a slow temporal model for the sensor;

and in response to the determination that the sensor is producing anomalous output, at least one of;

generating a notification indicating the sensor is producing anomalous output,and degrading a confidence level in the sensor.

30. The system of claim 28, wherein the instructions further cause be one or more computers to perform operations comprising:

receiving the one or more signals from the one or more sensors on the one or more additional sensor devices;

determining that the signal from the sensor is inconsistent with at east one of the one or more signals from the one or more sensors;

determining that the one or more signals from the one or more sensors are consistent with each other; and

generating an indication that the sensor is producing anomalous output.

31. The system of claim 28, wherein the instructions further cause the one or more computers to perform operations comprising:

receiving the slow temporal model for the sensor;

determining that the signal from the sensor is inconsistent with a signal that the slow temporal model indicates is expected from the sensor in the situation in which the signal from the sensor was generated; and

generating an indication that the sensor is producing anomalous output.