Initial location determination of uncrewed aerial vehicles from uncalibrated location observations

1 . A computing system configured to perform operations comprising:

determining a cluster-portion observation data corresponding to an aerial image of a portion of a ground-based cluster of charging pads for aerial vehicles, wherein;

the ground-based cluster comprises the charging pads arranged in a layout and a plurality of fiducial markers distributed at positions across the layout,

the aerial image was captured by an aerial vehicle (i) after the aerial vehicle initiated a flight from a particular charging pad within the portion of the ground-based cluster, (ii) while hovering above the particular charging pad, and (iii) prior to calibration of a navigation system of the aerial vehicle, and

the cluster-portion observation data comprises (i) information indicating a position of the particular charging pad and (ii) positions of one or more fiducial markers within the portion of the ground-based cluster relative to the particular charging pad;

identifying at least one mapped fiducial marker in a stored reference map of the ground-based cluster that matches at least one of the one or more fiducial markers in the cluster-portion observation data;

identifying a mapped charging pad in the stored reference map as a match to the particular charging pad in the cluster-portion observation data, wherein the mapped charging pad is identified based on the at least one mapped fiducial marker and its position in the stored reference map relative to the mapped charging pad;

determining a geolocation and an orientation of the particular charging pad according to a recorded geolocation and orientation for the identified mapped charging pad;

determining, based on the geolocation and the orientation of the particular charging pad, location information indicating an initial geolocation of the aerial vehicle after the aerial vehicle initiated the flight from the particular charging pad; and

causing the aerial vehicle to operate based on the location information to perform the calibration of the navigation system of the aerial vehicle.

2 . The computing system of claim 1 , wherein the aerial image was captured by the aerial vehicle while hovering above the particular charging pad at an altitude above ground level (AGL) that is below a threshold AGL at or above which at least one aviation regulation applies.

3 . The computing system of claim 1 , wherein the aerial image was captured by the aerial vehicle while hovering above the particular charging pad at an altitude above ground level (AGL) that is below a threshold AGL at or above which GPS-derived geolocation and/or orientation yields at least a threshold accuracy with at least a threshold likelihood.

4 . The computing system of claim 1 , wherein the cluster-portion observation data further comprises information indicating respective identifying and orientation markings on the one or more fiducial markers.

5 . The computing system of claim 4 , wherein identifying the at least one mapped fiducial marker in the stored reference map comprises:

comparing an identity and an orientation recorded for the at least one mapped fiducial marker to the respective identifying and orientation markings on the one or more fiducial markers in the cluster-portion observation data.

6 . The computing system of claim 5 , wherein identifying the at least one mapped fiducial marker in the stored reference map comprises:

based on comparing the identity and the orientation recorded for the at least one mapped fiducial marker to the respective identifying and orientation markings on the one or more fiducial markers in the cluster-portion observation data, reorienting at least part of the cluster-portion observation data to match an orientation of the stored reference map.

7 . The computing system of claim 1 , wherein the location information further indicates an orientation of the aerial vehicle, wherein the orientation of the aerial vehicle is reckoned with respect to an orientation of the particular charging pad.

8 . The computing system of claim 1 , wherein the location information further indicates that the aerial vehicle initiated the flight from the particular charging pad.

9 . The computing system of claim 1 , wherein causing the aerial vehicle to operate based on the location information comprises:

sending, via electronic transmission, the location information to the aerial vehicle.

10 . The computing system of claim 1 , wherein determining the cluster-portion observation data comprises:

receiving, from the aerial vehicle, the cluster-portion observation data.

11 . The computing system of claim 1 , comprising a server configured to perform one or more of:

determining of the cluster-portion observation data,

identifying of the at least one mapped fiducial marker,

identifying the mapped charging pad,

determining the geolocation and the orientation,

determining the location information, or

causing the aerial vehicle to operate to perform the calibration of the navigation system.

12 . The computing system of claim 1 , comprising the aerial vehicle, wherein the aerial vehicle is configured to perform one or more of:

determining of the cluster-portion observation data,

identifying of the at least one mapped fiducial marker,

identifying the mapped charging pad,

determining the geolocation and the orientation,

outputting determining the location information, or

causing the aerial vehicle to operate to perform the calibration of the navigation system.

13 . The computing system of claim 1 , wherein the flight from the particular charging pad comprises a vertical flight initiated upon power-up of the aerial vehicle after charging of the aerial vehicle using the particular charging pad.

14 . The computing system of claim 1 , wherein the cluster-portion observation data comprises:

one or more pixel locations of the particular charging pad in the aerial image;

one or more pixel locations of the one or more fiducial markers in the aerial image; and

for each respective fiducial marker of the one or more fiducial markers, a corresponding identifying marking and a corresponding orientation indicator, and wherein the cluster-portion observation data omits at least some pixels of the aerial image.

15 . The computing system of claim 1 , wherein the plurality of fiducial markers comprises two or more fiducial markers having non-unique identifying markings, and wherein identifying the mapped charging pad comprises:

distinguishing the particular charging pad from other charging pads of the charging pads based on relative positions and orientations of the two or more fiducial markers within the cluster-portion observation data.

16 . A computer-implemented method comprising:

determining a cluster-portion observation data corresponding to an aerial image of a portion of a ground-based cluster of charging pads for aerial vehicles, wherein;

the ground-based cluster comprises the charging pads arranged in a layout and a plurality of fiducial markers distributed at positions across the layout,

the aerial image was captured by an aerial vehicle (i) after the aerial vehicle initiated a flight from a particular charging pad within the portion of the ground-based cluster, (ii) while hovering above the particular charging pad, and (iii) prior to calibration of a navigation system of the aerial vehicle, and

the cluster-portion observation data comprises (i) information indicating a position of the particular charging pad and (ii) positions of one or more fiducial markers within the portion of the ground-based cluster relative to the particular charging pad;

identifying at least one mapped fiducial marker in a stored reference map of the ground-based cluster that matches at least one of the one or more fiducial markers in the cluster-portion observation data;

identifying a mapped charging pad in the stored reference map as a match to the particular charging pad in the cluster-portion observation data, wherein the mapped charging pad is identified based on the at least one mapped fiducial marker and its position in the stored reference map relative to the mapped charging pad;

determining a geolocation and an orientation of the particular charging pad according to a recorded geolocation and orientation for the identified mapped charging pad;

determining, based on the geolocation and the orientation of the particular charging pad, location information indicating an initial geolocation of the aerial vehicle after the aerial vehicle initiated the flight from the particular charging pad; and

causing the aerial vehicle to operate based on the location information to perform the calibration of the navigation system of the aerial vehicle.

17 . The computer-implemented method of claim 16 , wherein the aerial image was captured by the aerial vehicle while hovering above the particular charging pad at an altitude above ground level (AGL) that is below a threshold AGL at or above which at least one aviation regulation applies.

18 . The computer-implemented method of claim 16 , wherein the aerial image was captured by the aerial vehicle while hovering above the particular charging pad at an altitude above ground level (AGL) that is below a threshold AGL at or above which GPS-derived geolocation and/or orientation yields at least a threshold accuracy with at least a threshold likelihood.

19 . The computer-implemented method of claim 16 , wherein the cluster-portion observation data further comprises information indicating respective identifying and orientation markings on the one or more fiducial markers, and wherein identifying the at least one mapped fiducial marker in the stored reference map comprises:

comparing an identity and an orientation recorded for the at least one mapped fiducial marker to the respective identifying and orientation markings on the one or more fiducial markers in the cluster-portion observation data.

20 . An article of manufacture including a non-transitory computer-readable medium, having stored thereon program instructions that, upon execution by a computing device, cause the computing device to perform operations comprising:

determining a cluster-portion observation data corresponding to an aerial image of a portion of a ground-based cluster of charging pads for aerial vehicles, wherein:

the ground-based cluster comprises the charging pads arranged in a layout and a plurality of fiducial markers distributed at positions across the layout,

the aerial image was captured by an aerial vehicle (i) after the aerial vehicle initiated a flight from a particular charging pad within the portion of the ground-based cluster, (ii) while hovering above the particular charging pad, and (iii) prior to calibration of a navigation system of the aerial vehicle, and

the cluster-portion observation data comprises (i) information indicating a position of the particular charging pad and (ii) positions of one or more fiducial markers within the portion of the ground-based cluster relative to the particular charging pad;

identifying at least one mapped fiducial marker in a stored reference map of the ground-based cluster that matches at least one of the one or more fiducial markers in the cluster-portion observation data;

identifying a mapped charging pad in the stored reference map as a match to the particular charging pad in the cluster-portion observation data, wherein the mapped charging pad is identified based on the at least one mapped fiducial marker and its position in the stored reference map relative to the mapped charging pad;

determining a geolocation and an orientation of the particular charging pad according to a recorded geolocation and orientation for the identified mapped charging pad;

determining, based on the geolocation and the orientation of the particular charging pad, location information indicating an initial geolocation of the aerial vehicle after the aerial vehicle initiated the flight from the particular charging pad; and

causing the aerial vehicle to operate based on the location information to perform the calibration of the navigation system of the aerial vehicle.