Identification of proxy calibration targets for a fleet of vehicles

1. A method comprising:

collecting, using a sensor coupled to a vehicle, data about one or more objects within an environment of the vehicle, wherein the sensor has been calibrated using a ground-truth calibration target;

identifying, based on the collected data, at least one candidate object, from among the one or more objects, to be used as a proxy calibration target for other sensors coupled to vehicles within a fleet of vehicles; and

providing, by the vehicle, data about the candidate object for use by one or more vehicles within the fleet of vehicles.

2. The method of claim 1 , wherein providing, by the vehicle, data about the candidate object for use by one or more vehicles within the fleet of vehicles comprises transmitting, by the vehicle, the data about the candidate object to a proxy calibration target server for use by the fleet of vehicles.

3. The method of claim 1 , wherein providing, by the vehicle, data about the candidate object for use by one or more vehicles within the fleet of vehicles comprises transmitting, by the vehicle, the data about the candidate object to at least one vehicle within the fleet of vehicles.

4. The method of claim 1 , wherein the sensor is calibrated using the ground-truth calibration target within a threshold time period from collecting data about the one or more objects within the environment of the vehicle.

5. The method of claim 4 , further comprising:

determining a time difference between a time at which the sensor was calibrated using the ground-truth calibration target and a current time;

comparing the time difference to a threshold; and

determining, based on the comparison, that the sensor is usable to identify candidate objects to be used as proxy calibration targets.

6. The method of claim 1 , wherein the sensor comprises a light detection and ranging (LIDAR) sensor, a radar sensor, or a camera.

7. The method of claim 6 , wherein the vehicle is configured to operate in an autonomous mode, and wherein the fleet of vehicles comprises vehicles configured to operate in an autonomous mode.

8. The method of claim 1 , wherein the data about the candidate object comprises a color of the candidate object.

9. The method of claim 1 , wherein the data about the candidate object comprises a reflectivity of the candidate object.

10. The method of claim 1 , wherein the data about the candidate object comprises data specifying a geographic area within which the candidate object is observable.

11. The method of claim 1 , wherein the data about the candidate object comprises a time stamp that indicates a time at which the candidate object was characterized.

12. The method of claim 1 , wherein the data about the candidate object comprises a three-dimensional model of the candidate object.

13. The method of claim 1 , wherein the candidate object comprises a wall of a building, a billboard, a traffic signal, a road sign, a metallic pole, a road surface, a calibration target, or a validation target.

14. The method of claim 1 , wherein the candidate object has a Lambertian reflectivity or a nearly Lambertian reflectivity.

15. The method of claim 1 , further comprising:

receiving data about the one or more objects from another sensor coupled to another vehicle within the fleet of vehicles; and

comparing the received data to the collected data, wherein the at least one candidate object is identified based on the comparison.

16. A method comprising:

receiving, by a first sensor coupled to a first vehicle within a fleet of vehicles, data about a proxy calibration target, wherein the proxy calibration target has been:

characterized using a second sensor coupled to a second vehicle within the fleet of vehicles, wherein the second sensor has been calibrated using a ground-truth calibration target; and

identified, from among one or more objects, by the second sensor, as a candidate target for proxy calibration; and

calibrating the first sensor using the data about the proxy calibration target.

17. The method of claim 16 ,

wherein the data about the proxy calibration target comprises a boundary of a geographic area within which the proxy calibration target is observable,

wherein the method further comprises altering a navigation route for the first vehicle, and

wherein the altered navigation route passes through the boundary.

18. The method of claim 16 , wherein the data about the proxy calibration target is transmitted by the second vehicle to the first vehicle.

19. The method of claim 16 ,

wherein the data about the proxy calibration target is uploaded, by the second vehicle, to a proxy calibration target server for use by the fleet of vehicles, and

wherein receiving the data about the proxy calibration target comprises downloading, by the first vehicle, the data about the proxy calibration target from the proxy calibration target server.

20. The method of claim 16 , further comprising determining, by the first sensor, that a proxy calibration is to be performed based on an amount of time since a previous calibration of the first sensor.

21. A method comprising:

receiving, by a proxy calibration target server, data about a candidate object within an environment,

wherein the data about the candidate object is usable by a fleet of vehicles to perform proxy calibrations,

wherein the data about the candidate object has been determined by a first sensor coupled to a first vehicle within the fleet of vehicles,

wherein the first sensor has been calibrated using a ground-truth calibration target, and

wherein the candidate object has been identified, by the first sensor, from among one or more objects for use as a proxy calibration target; and

providing, by the proxy calibration target server, the data about the candidate object to one or more vehicles within the fleet of vehicles.

22. The method of claim 21 ,

wherein the data about the candidate object comprises a time stamp that indicates a time at which the candidate object was characterized by the first sensor, and

wherein the method further comprises:

determining, by the proxy calibration target server, a time difference between a current time and the time at which the candidate object was characterized by the first sensor;

comparing the time difference to a threshold; and

modifying the data about the candidate object in the proxy calibration target server or removing the data about the candidate object from the proxy calibration target server based on the comparison.

23. The method of claim 21 ,

wherein the data about the candidate object comprises a geographic location tag that indicates a geographic location of the candidate object, and

wherein the method further comprises:

monitoring, by the proxy calibration target server, weather conditions at the geographic location of the candidate object; and

modifying the data about the candidate object in the proxy calibration target server or removing the data about the candidate object from the proxy calibration target server based on weather conditions.

24. The method of claim 21 , wherein the data about the candidate object comprises one or more tags that indicate which types of sensors can be calibrated using the candidate object.