System and method for detecting severe road events

1. A computer-implemented method comprising:

collecting sensor data from at least one sensor on an autonomous vehicle, wherein the sensor data includes a plurality of measurements from the at least one sensor;

identifying, from the sensor data, at least one measurement from the plurality of measurements that is outside a threshold measurement for the at least one sensor and is indicative of an impact incident;

determining, based on an algorithm, whether the autonomous vehicle requires a repair to the autonomous vehicle as a result of the impact incident, wherein the algorithm is configured to receive the sensor data and output a respective classification of severity of the impact incident, wherein the autonomous vehicle is included in a fleet;

sending the sensor data to a remote computing system; and

in response to the sending of the sensor data that is indicative of the impact incident, receiving, from the remote computing system, routing instructions instructing the autonomous vehicle to navigate to a particular service station for maintenance in a particular order with respect to other autonomous vehicles, wherein the particular order is based on the severity of the impact incident, and

wherein the collection of sensor data is received from a plurality of autonomous vehicles and is labeled with classifications of at least a severity of a respective impact event and any repair that was needed for a respective autonomous vehicle in response to the respective impact.

2. The computer-implemented method of claim 1 , wherein the impact incident was driving over a pothole in a road, the method further comprising:

collecting additional sensor data from the at least one sensor on the autonomous vehicle, wherein the additional sensor data is collected after the impact incident when the autonomous vehicle is driving toward a location when the impact incident occurred, the additional sensor data indicating a second impact event from driving over the pothole in the road;

determining that the additional sensor data indicates a deviation from the sensor data previously collected in relation to the impact incident, and that the deviation is greater than a threshold deviation; and

reporting the additional sensor data to the remote computing system after determining that the additional sensor data indicates the deviation is greater than the threshold deviation.

3. The computer-implemented method of claim 1 , wherein the threshold measurement is based off a suspension sensor with a threshold vertical displacement of at least 1 inch from a ground.

4. The computer-implemented method of claim 1 , wherein the threshold measurement is further based upon a condition of a lane that the autonomous vehicle is traversing.

5. The computer-implemented method of claim 1 , further comprising:

analyzing, after identifying the at least one measurement from the plurality of measurements that is outside a threshold measurement for the at least one sensor and is indicative of an impact incident, data from at least one second sensor to determine that the impact incident resulted in a change in a baseline reading from the at least one second sensor, wherein the sending of the sensor data to the remote computing system is dependent on an outcome of the analyzing the data from the at least one second sensor.

6. The computer-implemented method of claim 1 , further comprising:

initiating, after identifying the at least one measurement from the plurality of measurements that is outside a threshold measurement for the at least one sensor and is indicative of an impact incident, specific actions effective to identify issues of a component, wherein the plurality of measurements are measurements of the component.

7. A computing system comprising:

at least one storage including computer-readable instructions stored thereon; and

at least one processor configured to execute the computer-readable instructions which cause the computing system to:

collect sensor data from at least one sensor on an autonomous vehicle, wherein the sensor data includes a plurality of measurements from the at least one sensor;

identify, from the sensor data, at least one measurement from the plurality of measurements that is outside a threshold measurement for the at least one sensor and is indicative of an impact incident;

determine, based on an algorithm, whether the autonomous vehicle requires a repair to the autonomous vehicle as a result of the impact incident, wherein the algorithm is configured to receive the sensor data and output a respective classification of severity of the impact incident, wherein the autonomous vehicle is included in a fleet;

send the sensor data to a remote computing system; and

in response to the sending of the sensor data that is indicative of the impact incident, receive, from the remote computing system, routing instructions instructing the autonomous vehicle to navigate to a particular service station for maintenance in a particular order with respect to other autonomous vehicles, wherein the particular order is based on the severity of the impact incident, and

wherein the collection of sensor data is received from a plurality of autonomous vehicles and is labeled with classifications of at least a severity of a respective impact event and any repair that was needed for a respective autonomous vehicle in response to the respective impact.

8. The computing system of claim 7 , wherein the impact incident was driving over a pothole in a road, wherein the computer-readable instructions further cause the remote computing system to:

collect additional sensor data from the at least one sensor on the autonomous vehicle, wherein the additional sensor data is collected after the impact incident when the autonomous vehicle is driving toward a location when the impact incident occurred, the additional sensor data indicating a second impact event from driving over the pothole in the road;

determine that the additional sensor data indicates a deviation from the sensor data previously collected in relation to the impact incident, and that the deviation is greater than a threshold deviation; and

report the additional sensor data to the remote computing system after determining that the additional sensor data indicates the deviation is greater than the threshold deviation.

9. The computing system of claim 7 , wherein the threshold measurement is changed based on the sensor data.

10. The computing system of claim 7 , wherein the threshold measurement is further based upon a condition of a lane that the autonomous vehicle is traversing.

11. The computing system of claim 7 , wherein the computer-readable instructions further cause the remote computing system to:

analyze, after identifying the at least one measurement from the plurality of measurements that is outside a threshold measurement for the at least one sensor and is indicative of an impact incident, data from at least one second sensor to determine that the impact incident resulted in a change in a baseline reading from the at least one second sensor, wherein the sending of the sensor data to the remote computing system is dependent on an outcome of the analyzing the data from the at least one second sensor.

12. The computing system of claim 7 , wherein the computer-readable instructions further cause the remote computing system to:

initiate, after identifying the at least one measurement from the plurality of measurements that is outside a threshold measurement for the at least one sensor and is indicative of an impact incident, specific actions effective to identify issues of a component, wherein the plurality of measurements are measurements of the component.

13. A non-transitory computer-readable storage medium comprising instructions therein, which when executed by one or more processors, cause the processors to perform operations comprising:

collecting sensor data from at least one sensor on an autonomous vehicle, wherein the sensor data includes a plurality of measurements from the at least one sensor;

identifying, from the sensor data, at least one measurement from the plurality of measurements that is outside a threshold measurement for the at least one sensor and is indicative of an impact incident;

determining, based on an algorithm, whether the autonomous vehicle requires a repair to the autonomous vehicle as a result of the impact incident, wherein the algorithm is configured to receive the sensor data and output a respective classification of severity of the impact incident, wherein the autonomous vehicle is included in a fleet;

sending the sensor data to a remote computing system; and

in response to the sending of the sensor data that is indicative of the impact incident, receiving, from the remote computing system, routing instructions instructing the autonomous vehicle to navigate to a particular service station for maintenance in a particular order with respect to other autonomous vehicles, wherein the particular order is based on the severity of the impact incident, and

wherein the collection of sensor data is received from a plurality of autonomous vehicles and is labeled with classifications of at least a severity of a respective impact event and any repair that was needed for a respective autonomous vehicle in response to the respective impact.

14. The non-transitory computer-readable storage medium of claim 13 , wherein the impact incident was driving over a pothole in a road, wherein the operations further comprising:

collecting additional sensor data from the at least one sensor on the autonomous vehicle, wherein the additional sensor data is collected after the impact incident when the autonomous vehicle is driving toward a location when the impact incident occurred, the additional sensor data indicating a second impact event from driving over the pothole in the road;

determining that the additional sensor data indicates a deviation from the sensor data previously collected in relation to the impact incident, and that the deviation is greater than a threshold deviation; and

reporting the additional sensor data to the remote computing system after determining that the additional sensor data indicates the deviation is greater than the threshold deviation.

15. The non-transitory computer-readable storage medium of claim 13 , wherein the threshold measurement is changed based on the sensor data.

16. The non-transitory computer-readable storage medium of claim 13 , wherein the threshold measurement is further based upon a condition of a lane that the autonomous vehicle is traversing.

17. The non-transitory computer-readable storage medium of claim 13 , wherein the operations further comprising:

analyzing, after identifying the at least one measurement from the plurality of measurements that is outside a threshold measurement for the at least one sensor and is indicative of an impact incident, data from at least one second sensor to determine that the impact incident resulted in a change in a baseline reading from the at least one second sensor, wherein the sending of the sensor data to the remote computing system is dependent on an outcome of the analyzing the data from the at least one second sensor.

18. The computer-implemented method of claim 1 , further comprising:

receiving, from the remote computing system, a determination that the repair to the autonomous vehicle is required, wherein the determination is based on a severity determination of the impact incident.

19. The computer-implemented method of claim 1 , wherein the sensor data is calibrated based on a condition of a lane that the autonomous vehicle is traversing or has traversed, the condition comprising an amount of irregularity or unevenness of the lane.

20. The computer-implemented method of claim 1 , wherein the sensor data is used to create the algorithm, and wherein the fleet of autonomous vehicles can make determinations regarding a respective severity of future impact events.