Validating vehicle sensor calibration

1. A computer-implemented method comprising:

obtaining first sensor data captured by a first sensor of a vehicle during a given period of operation of the vehicle;

obtaining second sensor data captured by a second sensor of the vehicle during the given period of operation of the vehicle;

accessing a combined map comprising (i) a first map layer corresponding to a first type of the first sensor and (ii) a second map layer corresponding to a second type of the second sensor, wherein the first and second map layers are aligned such that there is a known transformation between a first coordinate frame of the first map layer and a second coordinate frame of the second map layer;

based on the first sensor data, localizing the first sensor within the first coordinate frame of the first map layer of the combined map;

based on the second sensor data, localizing the second sensor within the second coordinate frame of the second map layer of the combined map;

based on the known transformation between the first coordinate frame and the second coordinate frame, determining respective poses for the first sensor and the second sensor in a common coordinate frame;

determining (i) a translation and (ii) a rotation between the respective poses for the first and second sensors in the common coordinate frame;

determining a calibration between the first sensor and the second sensor based on the determined (i) translation and (ii) rotation between the respective poses for the first sensor and the second sensor in the common coordinate frame; and

based on the determined calibration, carrying out an action that facilitates recalibration of the first and second sensors, wherein the action comprises at least one of (i) causing issuance of a notification to recalibrate the first or second sensors, (ii) causing the vehicle to pull over, or (iii) updating a previously determined calibration between the first and second sensors.

2. The computer-implemented method of claim 1 , wherein the vehicle is stationary during the given period of operation.

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

comparing (i) the determined translation to a previously determined translation between the respective poses for the first and second sensors in the common coordinate frame and (ii) the determined rotation to a previously determined rotation between the respective poses for the first and second sensors in the common coordinate frame.

4. The computer-implemented method of claim 3 , further comprising:

determining a difference between one or both of (i) the determined translation and the previously determined translation between the respective poses for the first and second sensors or (ii) the determined rotation and the previously determined rotation between the respective poses for the first and second sensors; and

based on the difference, determining a change to the previously determined calibration between the first sensor and the second sensor.

5. The computer-implemented method of claim 4 , further comprising:

based on the difference between one or both of (i) the determined translation and the previously determined translation between the respective poses for the first and second sensors or (ii) the determined rotation and the previously determined rotation between the respective poses for the first and second sensors, updating the previously determined calibration between the first sensor and the second sensor to incorporate the difference.

6. The computer-implemented method of claim 4 , further comprising:

determining that the difference exceeds a threshold difference between one or both of (i) the determined translation and the previously determined translation between the respective poses for the first and second sensors or (ii) the determined rotation and the previously determined rotation between the respective poses for the first and second sensors; and

based on determining that the difference exceeds the threshold difference, causing issuance of the notification to recalibrate the first or second sensors.

7. The computer-implemented method of claim 1 , wherein the first sensor is a LiDAR unit and the first map layer is a LiDAR-based map layer, and wherein the second sensor is a camera and the second map layer is an image-based map layer.

8. The computer-implemented method of claim 1 , wherein the common coordinate frame is one of the first coordinate frame of the first map layer or the second coordinate frame of the second map layer.

9. The computer-implemented method of claim 1 , wherein the known transformation between the first coordinate frame and the second coordinate frame is determined during creation of the combined map.

10. The computer-implemented method of claim 1 , wherein determining (i) the translation and (ii) the rotation between the respective poses for the first and second sensors in the common coordinate frame comprises determining a series of respective (i) translations and (ii) rotations between a series of respective poses for the first and second sensors in the common coordinate frame; and

wherein determining the calibration between the first sensor and the second sensor based on the determined (i) translation and (ii) rotation between the respective poses for the first sensor and the second sensor in the common coordinate frame comprises determining the calibration between the first sensor and the second sensor based on the determined series of respective (i) translations and (ii) rotations.

11. A non-transitory computer-readable medium comprising program instructions stored thereon that are executable to cause a computing system to:

obtain first sensor data captured by a first sensor of a vehicle during a given period of operation of the vehicle;

obtain second sensor data captured by a second sensor of the vehicle during the given period of operation of the vehicle;

access a combined map comprising (i) a first map layer corresponding to a first type of the first sensor and (ii) a second map layer corresponding to a second type of the second sensor, wherein the first and second map layers are aligned such that there is a known transformation between a first coordinate frame of the first map layer and a second coordinate frame of the second map layer;

based on the first sensor data, localize the first sensor within the first coordinate frame of the first map layer of the combined map;

based on the second sensor data, localize the second sensor within the second coordinate frame of the second map layer of the combined map;

based on the known transformation between the first coordinate frame and the second coordinate frame, determine respective poses for the first sensor and the second sensor in a common coordinate frame;

determine (i) a translation and (ii) a rotation between the respective poses for the first and second sensors in the common coordinate frame;

determine a calibration between the first sensor and the second sensor based on the determined (i) translation and (ii) rotation between the respective poses for the first sensor and the second sensor in the common coordinate frame; and

based on the determined calibration, carry out an action that facilitates recalibration of the first and second sensors, wherein the action comprises at least one of (i) causing issuance of a notification to recalibrate the first or second sensors, (ii) causing the vehicle to pull over, or (iii) updating a previously determined calibration between the first and second sensors.

12. The computer-readable medium of claim 11 , wherein the vehicle is stationary during the given period of operation.

13. The computer-readable medium of claim 12 , wherein the computer-readable medium further comprises program instructions stored thereon that are executable to cause the computing system to:

compare the determined translation to a previously determined translation between the respective poses for the first and second sensors in the common coordinate frame and (ii) the determined rotation to a previously determined rotation between the respective poses for the first and second sensors in the common coordinate frame.

14. The computer-readable medium of claim 13 , wherein the computer-readable medium further comprises program instructions stored thereon that are executable to cause the computing system to:

determine a difference between one or both of (i) the determined translation and the previously determined translation between the respective poses for the first and second sensors or (ii) the determined rotation and the previously determined rotation between respective poses for the first and second sensors; and

based on the difference, determine a change to the previously determined calibration between the first sensor and the second sensor.

15. The computer-readable medium of claim 14 , wherein the computer-readable medium further comprises program instructions stored thereon that are executable to cause the computing system to:

based on the difference between one or both of (i) the determined translation and the previously determined translation between the respective poses for the first and second sensors or (ii) rotation and the previously determined rotation between the respective poses for the first and second sensors, update the previously determined calibration between the first sensor and the second sensor to incorporate the difference.

16. The computer-readable medium of claim 14 , wherein the computer-readable medium further comprises program instructions stored thereon that are executable to cause the computing system to:

determine that the difference exceeds a threshold difference between one or both of (i) the determined translation and the previously determined translation between the respective poses for the first and second sensors or (ii) the determined rotation and the previously determined rotation between the respective poses for the first and second sensors; and

based on determining that the difference exceeds the threshold difference, cause issuance of the notification to recalibrate the first or second sensors.

17. The computer-readable medium of claim 11 , wherein the first sensor is a LiDAR unit and the first map layer is a LiDAR-based map layer, and wherein the second sensor is a camera and the second map layer is an image-based map layer.

18. The computer-readable medium of claim 11 , wherein the common coordinate frame is one of the first coordinate frame of the first map layer or the second coordinate frame of the second map layer.

19. The computer-readable medium of claim 11 , wherein the known transformation between the first coordinate frame and the second coordinate frame is determined during creation of a combined map.

20. A computing system comprising:

at least one processor;

a non-transitory computer-readable medium; and

program instructions stored on the non-transitory computer-readable medium that are executable by the at least one processor such that the computing system is capable of:

obtaining first sensor data captured by a first sensor of a vehicle during a given period of operation of the vehicle;

obtaining second sensor data captured by a second sensor of the vehicle during the given period of operation of the vehicle;

accessing a combined map comprising (i) a first map layer corresponding to a first type of the first sensor and (ii) a second map layer corresponding to a second type of the second sensor, wherein the first and second map layers are aligned such that there is a known transformation between a first coordinate frame of the first map layer and a second coordinate frame of the second map layer;

based on the first sensor data, localizing the first sensor within the first coordinate frame of the first map layer of the combined map;

based on the second sensor data, localizing the second sensor within the second coordinate frame of the second map layer;

based on the known transformation between the first coordinate frame and the second coordinate frame, determining respective poses for the first sensor and the second sensor in a common coordinate frame;

determining (i) a translation and (ii) a rotation between the respective poses for the first and second sensors in the common coordinate frame;

determining a calibration between the first sensor and the second sensor based on the determined (i) translation and (ii) rotation between the respective poses for the first sensor and the second sensor in the common coordinate frame; and

based on the determined calibration, carrying out an action that facilitates recalibration of the first and second sensors, wherein the action comprises at least one of (i) causing issuance of a notification to recalibrate the first or second sensors, (ii) causing the vehicle to pull over, or (iii) updating a previously determined calibration between the first and second sensors.