Determining gate state and remedial measures using gate sensor attachment
An edge device receives sensor data from a sensor affixed to a moveable gate. The edge device determines the positional state of the moveable gate based on the sensor data by inputting the received data into a machine learning model or by comparing the sensor data to values associated with a positional state through a calibration process. The edge device stores a log that associates the positional state and sensor data. The edge device determines the health state of the moveable gate using a machine learning model that is trained to predict, based on input of a new log, the health state of the gate. Responsive to determining that the health state of the gate is unhealthy, the edge device triggers a remedial action.
1. A method comprising:
receiving, at an edge device within a threshold proximity of a parking facility, sensor data from a sensor affixed to a moveable gate forming a barrier to vehicles with respect to the parking facility;
determining, by the edge device, based on the sensor data, a positional state of the moveable gate;
storing, by the edge device, a log that associates the positional state and the sensor data;
determining, from one or more logs comprising the log, a health state of the moveable gate, wherein the health state indicates a health of the moveable gate;
determining whether the health state is unhealthy; and
responsive to determining that the health state is unhealthy, triggering a remedial action.
2. The method of claim 1 , wherein the sensor data is received responsive to movement of the moveable gate.
3. The method of claim 1 , further comprising calibrating the edge device to translate given sensor data to a candidate positional state of a plurality of candidate positional states.
4. The method of claim 3 , wherein the sensor is an accelerometer, and wherein calibrating the edge device comprises:
storing, to the edge device, a first accelerometer value corresponding to a positional state of closed; and
storing, to the edge device, a second accelerometer value corresponding to a positional state of open.
5. The method of claim 4 , wherein a tolerance is defined relative to the first accelerometer value within which the positional state of closed is determined, and outside of which a positional state of unknown is determined.
6. The method of claim 4 , wherein the accelerometer is a three-axis accelerometer, and wherein calibrating the edge device further comprises:
storing, to the edge device, a threshold force value along an axis perpendicular to the moveable gate and parallel to a plane of a ground of the parking facility;
storing, to the edge device, an indication that force values below the threshold force value correspond to a positional state of wobble; and
storing, to the edge device, an indication that force values above the threshold force value correspond to a positional state of crashed through.
7. The method of claim 4 , further comprising:
determining the positional state using camera data; and
pairing the determined positional state with an accelerometer value received while the camera data indicated that the moveable gate was in the determined positional state.
8. The method of claim 4 , further comprising:
determining the positional state using magnet data; and
pairing the determined positional state with an accelerometer value received while the magnet data indicated that the moveable gate was in the determined positional state.
9. The method of claim 1 , wherein determining the health state comprises:
inputting the one or more logs into a supervised machine learning model; and
receiving, as output from the supervised machine learning model, the health state.
10. The method of claim 9 , wherein the supervised machine learning model was trained using existing logs including sensor data, positional state, and time data, annotated with gate attributes, and labelled with health state, wherein health state is determined by comparing an accelerometer value of the moveable gate within a time window to a threshold.
11. The method of claim 9 , wherein the supervised machine learning model is trained to output health state for a particular gate type.
12. The method of claim 1 , wherein determining the health state comprises:
inputting normalized sensor into a classifier; and
receiving, as output from the classifier, the health state.
13. The method of claim 1 , wherein determining the positional state comprises:
inputting the one or more logs into a supervised machine learning model; and
receiving, as output from the supervised machine learning model, the positional state.
14. The method of claim 13 , wherein the supervised machine learning model was trained using historical sensor data from the moveable gate, labelled with positional state, wherein positional state is determined by a calibration process.
15. The method of claim 1 , wherein the remedial action comprises an alert prompt to a technician for immediate redress responsive to determining that the health state of the moveable gate is crashed through.
16. A non-transitory computer-readable medium comprising memory with instructions encoded thereon, the instructions, when executed by one or more processors, causing the one or more processors to perform operations, the instructions comprising instructions to:
receive, at an edge device within a threshold proximity of a parking facility, sensor data from a sensor affixed to a moveable gate forming a barrier to vehicles with respect to the parking facility;
determine, by the edge device, based on the sensor data, a positional state of the moveable gate;
store, by the edge device, a log that associates the positional state and the sensor data;
determine, from one or more logs comprising the log, a health state of the moveable gate, wherein the health state indicates a health of the moveable gate;
determine whether the health state is unhealthy; and
responsive to determining that the health state is unhealthy, trigger a remedial action.
17. The non-transitory computer-readable medium of claim 16 , wherein the sensor data is received responsive to movement of the moveable gate.
18. The non-transitory computer-readable medium of claim 16 , wherein the instructions further comprise instructions to calibrate the edge device to translate given sensor data to a candidate positional state of a plurality of candidate positional states.
19. The non-transitory computer-readable medium of claim 16 , wherein the sensor is an accelerometer, and wherein the instructions for calibrating the edge device comprise instructions to:
store, to the edge device, a first accelerometer value corresponding to a positional state of closed; and
store, to the edge device, a second accelerometer value corresponding to a positional state of open.
20. A system comprising:
memory with instructions encoded thereon; and
one or more processors that, when executing the instructions, are caused to perform operations comprising:
receiving, at an edge device within a threshold proximity of a parking facility, sensor data from a sensor affixed to a moveable gate forming a barrier to vehicles with respect to the parking facility;
determining, by the edge device, based on the sensor data, a positional state of the moveable gate;
storing, by the edge device, a log that associates the positional state and the sensor data;
determining, from one or more logs comprising the log, a health state of the moveable gate, wherein the health state indicates a health of the moveable gate;
determining whether the health state is unhealthy; and
responsive to determining that the health state is unhealthy, triggering a remedial action.