Systems and methods for remote status detection of autonomous vehicles

1. A computing system, comprising:

one or more processors; and

one or more non-transitory computer-readable media that store instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:

accessing a third-party communication associated with an autonomous vehicle;

determining a predetermined identifier of the autonomous vehicle;

inputting imagery data from the third-party communication to a machine-learned model trained to analyze the imagery data to identify a condition of an external surface of the autonomous vehicle and to generate as an output a status associated with the condition of the external surface of the autonomous vehicle based on the imagery data, wherein the machine-learned model is located remotely from the autonomous vehicle;

receiving an indication of the status associated with the condition of the external surface of the autonomous vehicle from the machine-learned model; and

transmitting one or more control messages to the autonomous vehicle based at least in part on the predetermined identifier and the status associated with the condition of the external surface of the autonomous vehicle.

2. The computing system of claim 1 , wherein:

the third-party communication includes imagery depicting at least a portion of the autonomous vehicle, the imagery having been captured at a client computing device by a user of the client computing device; and

determining the predetermined identifier includes detecting the predetermined identifier based at least in part on an analysis of the imagery.

3. The computing system of claim 2 , wherein:

determining the status associated with the autonomous vehicle is based at least part on the analysis of the imagery.

4. The computing system of claim 1 , wherein:

the status associated with the autonomous vehicle includes a condition of the autonomous vehicle.

5. The computing system of claim 1 , wherein accessing the third-party communication comprises:

receiving, from a remote client device, the third-party communication.

6. The computing system of claim 5 , wherein the third-party communication includes at least one of a short messaging service (SMS) message, an e-mail message, or a web-based message.

7. The computing system of claim 6 , further comprising:

transmitting one or more reply messages to the remote client device based on the third-party communication.

8. The computing system of claim 1 , wherein accessing the third-party communication comprises:

accessing one or more third-party computing systems that provide third-party content.

9. The computing system of claim 8 , wherein the operations further comprise:

analyzing an image from the third-party content to detect the predetermined identifier.

10. The computing system of claim 1 , wherein:

accessing the third-party communication includes receiving the third-party communication via an application provided by a service entity associated with the autonomous vehicle.

11. The computing system of claim 1 , wherein:

the one or more control messages include instructions for the autonomous vehicle to execute a controlled stop in a safe state.

12. The computing system of claim 1 , wherein:

the one or more control messages include instructions for the autonomous vehicle to proceed toward a predetermined location.

13. The computing system of claim 1 , wherein:

the one or more control messages include instructions for the autonomous vehicle to transmit sensor data from the autonomous vehicle to the computing system.

14. The computing system of claim 1 , wherein:

the predetermined identifier comprises a code provided on an external surface of the autonomous vehicle.

15. The computing system of claim 1 , wherein the one or more control messages comprise instructions for the autonomous vehicle to initiate travel according to a backup motion plan.

16. One or more tangible, non-transitory computer-readable media storing computer-readable instructions that when executed by one or more processors cause the one or more processors to perform operations, the operations comprising:

accessing a third-party communication associated with an autonomous vehicle;

determining a predetermined identifier of the autonomous vehicle;

inputting imagery data from the third-party communication to a machine-learned model trained to analyze the imagery data to identify a condition of an external surface of the autonomous vehicle and to generate as an output a status associated with the condition of the external surface of the autonomous vehicle based on the imagery data, wherein the machine-learned model is located remotely from the autonomous vehicle;

receiving an indication of the status associated with the condition of the external surface of the autonomous vehicle from the machine-learned model; and

transmitting one or more control messages to the autonomous vehicle based at least in part on the predetermined identifier and the status associated with the condition of the external surface of the autonomous vehicle.

17. A computer-implemented method, comprising:

accessing a third-party communication associated with an autonomous vehicle;

determining a predetermined identifier of the autonomous vehicle;

inputting imagery data from the third-party communication to a machine-learned model trained to analyze the imagery data to identify a condition of an external surface of the autonomous vehicle and to generate as an output a status associated with the condition of the external surface of the autonomous vehicle based on the imagery data, wherein the machine-learned model is located remotely from the autonomous vehicle;

receiving an indication of the status associated with the condition of the external surface of the autonomous vehicle from the machine-learned model; and

transmitting one or more control messages to the autonomous vehicle based at least in part on the predetermined identifier and the status associated with the condition of the external surface of the autonomous vehicle.

18. The one or more tangible, non-transitory computer-readable media of claim 16 , wherein:

the third-party communication includes imagery depicting at least a portion of the autonomous vehicle, the imagery having been captured at a client computing device by a user of the client computing device; and

determining the predetermined identifier includes detecting the predetermined identifier based at least in part on an analysis of the imagery.

19. The computer-implemented method of claim 17 , wherein:

the third-party communication includes imagery depicting at least a portion of the autonomous vehicle, the imagery having been captured at a client computing device by a user of the client computing device; and

determining the predetermined identifier includes detecting the predetermined identifier based at least in part on an analysis of the imagery.