System and methods for automatic generation of remote assistance sessions based on anomaly data collected from human-driven vehicle

1. A computer-implemented method for using navigation anomaly data to improve remote assistance service, the method comprising:

receiving, by a computing system with one or more processors from a computing device associated with a human-driven vehicle, travel data for the human-driven vehicle;

identifying, by the computing system, a navigation anomaly associated with the human-driven vehicle based on the travel data;

generating, by the computing system and based on the identified navigation anomaly, an anomaly entry for storage in an anomaly database, the anomaly entry comprising geofence data describing a geographic area associated with the navigation anomaly;

determining, by the computing system based on location data received from an autonomous vehicle and the geofence data, that the autonomous vehicle is entering the geographic area associated with the navigation anomaly;

determining that a confidence value associated with the anomaly entry meets a threshold condition, the confidence value describing a confidence that an anomaly exists at the geographic area; and

initiating, by the computing system, a remote assistance session with the autonomous vehicle.

2. The computer-implemented method of claim 1 , wherein the travel data describes at least one of a speed, location, direction, heading, acceleration, or route of the human-driven vehicle.

3. The computer-implemented method of claim 1 , wherein the travel data includes stop data that describes a location and a timing when the human-driven vehicle comes to a stop.

4. The computer-implemented method of claim 1 , wherein initiating a remote assistance session with the autonomous vehicle further comprises:

accessing, by the computing system, the anomaly entry to determine a particular remote assistance operator previously associated with the navigation anomaly; and

assigning, by the computing system, the particular remote assistance operator to the remote assistance session.

5. The computer-implemented method of claim 1 , wherein determining a navigation anomaly comprises:

determining, by the computing system and based on the travel data for the human-driven vehicle, a current average speed of the human-driven vehicle;

accessing, by the computing system, past average speed data for a geographic location associated with the human-driven vehicle to determine a past average speed;

determining, by the computing system, whether a difference between the current average speed of the human-driven vehicle and the past average speed exceeds a threshold speed value; and

in accordance with a determination that the difference between the current average speed of the human-driven vehicle and the past average speed exceeds the threshold speed value, determining, by the computing system, that the navigation anomaly exists.

6. The computer-implemented method of claim 1 , wherein determining a navigation anomaly comprises:

determining, by the computing system and based on the travel data for the human-driven vehicle, one or more stop points for the human-driven vehicle;

accessing, by the computing system, past stopping data for a geographic location associated with the human-driven vehicle; and

comparing, by the computing system, the one or more stop points for the human-driven vehicle to the past stopping data for the geographic location.

7. The computer-implemented method of claim 1 , wherein determining a navigation anomaly comprises:

determining, by the computing system and based on travel data for the human-driven vehicle, a current route for the human-driven vehicle;

accessing, by the computing system, map data for a geographic location associated with the human-driven vehicle to determine an expected route for the human-driven vehicle; and

comparing, by the computing system, the current route for the human-driven vehicle to the expected route for the human-driven vehicle.

8. The computer-implemented method of claim 1 , wherein generating an anomaly entry comprises:

in response to identifying the navigation anomaly associated with the human-driven vehicle based on the travel data, determining, by the computing system, whether the anomaly entry corresponding to the navigation anomaly exists in the anomaly database.

9. The computer-implemented method of claim 8 , wherein generating an anomaly entry for storage in an anomaly database comprises:

in response to determining that the anomaly entry exists in the anomaly database, updating, by the computing system, the confidence value associated with the navigation anomaly to increase the confidence that the anomaly exists at the geographic area anomaly.

10. The computer-implemented method of claim 1 , wherein generating an anomaly entry comprises:

determining, by the computing system, an anomaly type associated with the navigation anomaly; and

generating a geofence with specific geographic boundaries to use as geofence data.

11. The computer-implemented method of claim 10 , wherein the geofence is generated based on the anomaly type associated with the navigation anomaly and the geographic area associated with the navigation anomaly.

12. The computer-implemented method of claim 1 , wherein the computing device associated with the human-driven vehicle is a smartphone.

13. A computing system for using traffic anomalies to improve remote assistance, the system comprising:

one or more processors and a non-transitory computer-readable memory;

wherein the non-transitory computer-readable memory stores instructions that, when executed by the processor, cause the computing system to perform operations, the operations comprising:

receiving, from a computing device associated with a human-driven vehicle, travel data for the human-driven vehicle;

identifying a navigation anomaly associated with the human-driven vehicle based on the travel data;

generating, based on the navigation anomaly, an anomaly entry for storage in an anomaly database, the anomaly entry comprising geofence data describing a geographic area associated with the navigation anomaly;

determining, based on location data received from an autonomous vehicle and the geofence data, that that autonomous vehicle is entering the geographic area associated with the navigation anomaly;

determining that a confidence value associated with the anomaly entry meets a threshold condition, the confidence value describing a confidence that an anomaly exists at the geographic area; and

initiating a remote assistance session with the autonomous vehicle.

14. The computing system of claim 13 , wherein generating an anomaly entry for storage in an anomaly database further comprises:

determining an anomaly type associated with the identified navigation anomaly.

15. The computing system of claim 14 , wherein determining that an autonomous vehicle is entering the geographic area associated with the navigation anomaly further comprises:

determining, based on the anomaly type associated with the identified navigation anomaly, whether a geographic location associated with the identified navigation anomaly is passable; and

in response to determining that the geographic location associated with the identified navigation anomaly is not passable, generating an alternative route for the autonomous vehicle.

16. The computing system of claim 15 , wherein determining that the autonomous vehicle is entering the geographic area associated with the navigation anomaly further comprises:

receiving current location data for the autonomous vehicle;

comparing the current location data to the geofence data associated with one or more anomaly entries in the anomaly database; and

in response to determining that the current location data is within a location indicated by the geofence data associated with a specific anomaly entry in the anomaly database, analyzing travel data associated with the autonomous vehicle to confirm an existence of the navigation anomaly.

17. The computing system of claim 15 , the operations further comprising:

in response to confirming, based on the travel data associated with the autonomous vehicle, the existence of the navigation anomaly, increasing the confidence value associated with the navigation anomaly, the confidence value being associated with the in the anomaly database.

18. The computing system of claim 15 the operations further comprising:

in response to being unable to confirm, based on the travel data associated with the autonomous vehicle, the existence of the navigation anomaly, decreasing the confidence value associated with the navigation anomaly in the anomaly database.

19. The computing system of claim 15 , the operations further comprising:

in response to being unable to confirm, based on the travel data associated with the autonomous vehicle, the existence of the navigation anomaly, removing the anomaly entry associated with the navigation anomaly from the anomaly database.

20. A non-transitory computer-readable medium storing instruction that, when executed by one or more computing devices, cause the one or more computing devices to perform operations, the operations comprising:

receiving, from a computing device associated with a human-driven vehicle, travel data for the human-driven vehicle;

identifying a navigation anomaly associated with the human-driven vehicle based on the travel data;

generating, based on the identified navigation anomaly, an anomaly entry for storage in an anomaly database, the anomaly entry including geofence data describing a geographic area associated with the navigation anomaly;

determining, based on location data, that an autonomous vehicle is entering the geographic area associated with the navigation anomaly;

determining that a confidence value associated with the anomaly entry meets a threshold condition, the confidence value describing a confidence that an anomaly exists at the geographic area; and

initiating a remote assistance session with the autonomous vehicle.

21. The computer-implemented method of claim 20 , wherein generating an anomaly entry for storage in an anomaly database comprises:

in response to identifying the navigation anomaly associated with the human-driven vehicle based on the travel data, determining, by the computing system, whether the anomaly entry corresponding to the navigation anomaly exists in the anomaly database; and

updating, by the computing system, the confidence value associated with the navigation anomaly to increase the confidence that the anomaly exists at the geographic area anomaly.