Cooperative safe landing area determination

1. A method of performing a cooperative safe landing area determination, the method comprising:

receiving, at a vehicle, perception sensor data indicative of conditions at a plurality of potential landing areas;

updating, by a processing subsystem of the vehicle, a local safe landing area map based on the perception sensor data, the local safe landing area map defining safe landing area classifications and classification confidences associated with the potential landing areas;

receiving one or more remotely-generated safe landing area maps from one or more remote data sources, the one or more remotely-generated safe landing area maps corresponding to one or more additional potential landing areas and non-landing areas;

aggregating the local safe landing area map with the one or more remotely-generated safe landing area maps to form a fused safe landing area map; and

using the fused safe landing area map to make a final safe landing area determination, wherein using the fused safe landing area map to make a final safe landing area determination includes extracting one or more cells from a plurality of cells of the fused safe landing area map, a value of the one or more cells exceeding a threshold level indicative of a safe landing area.

2. The method of claim 1 , further comprising:

generating a list of ranked landing areas from the fused safe landing area map based on performing a mission-level optimization to order the list of ranked landing areas according to one or more of a mission model and constraints.

3. The method of claim 1 , further comprising:

tagging the local safe area landing map with a freshness indicator.

4. The method of claim 1 , further comprising:

storing the one or more remotely-generated safe landing area maps in a map cache; and sending the local safe area landing map to the one or more remote data sources.

5. The method of claim 4 , further comprising:

determining one or more identifiers and freshness indicators associated with data in the map cache;

sending the one or more identifiers and freshness indicators to a second vehicle;

receiving a response from the second vehicle indicating desired data based on the one or more identifiers and freshness indicators; and

sending the desired data to the second vehicle.

6. The method of claim 1 , wherein aggregating the local safe landing area map with the one or more remotely-generated safe landing area maps to form the fused safe landing area map further comprises:

computing a combination of the local safe area landing map with the one or more remotely-generated safe landing area maps; and

using classification confidence values as weights for overlapping areas.

7. The method of claim 6 , further comprising:

decaying the classification confidence values as time elapses.

8. The method of claim 1 , further comprising:

receiving position data for the vehicle;

determining positions of the potential landing areas and the vehicle based on the position data; and

correlating the perception sensor data to the position data.

9. The method of of claim 1 , further comprising:

exchanging the final safe landing area determination with one or more other vehicles; and

verifying that the final safe landing area determination does not conflict with one or more final safe landing area determinations of the one or more other vehicles.

10. The method of claim 1 , further comprising:

performing feature extraction based on the perception sensor data;

establishing values for the safe landing area classifications based on matching extracted features from the perception sensor data with expected safe landing characteristics; and

adjusting the classification confidences associated with the potential landing areas based on a measurement confidence in the safe landing area classifications.

11. A system for performing a cooperative safe landing area determination, the system comprising:

a processing subsystem; and

memory having instructions stored thereon that, when executed by the processing subsystem, cause the system to:

receive perception sensor data indicative of conditions at a plurality of potential landing areas;

update a local safe landing area map based on the perception sensor data, the local safe landing area map defining safe landing area classifications and classification confidences associated with the potential landing areas;

receive one or more remotely-generated safe landing area maps from one or more remote data sources, the one or more remotely-generated safe landing area maps correspond to one or more additional potential landing areas and non-landing areas;

aggregate the local safe landing area map with the one or more remotely-generated safe landing area maps to form a fused safe landing area map; and

use the fused safe landing area map to make a final safe landing area determination, wherein use of the fused safe landing area map to make a final safe landing area determination includes extracting one or more cells from a plurality of cells of the fused safe landing area map, a value of the one or more cells exceeding a threshold level indicative of a safe landing area.

12. The system of claim 11 , wherein the memory further comprises instructions stored thereon that, when executed by the processing subsystem, cause the system to:

store the one or more remotely-generated safe landing area maps in a map cache; and

send the local safe area landing map to the one or more remote data sources.

13. The system of claim 11 , wherein the system is a computer system of a vehicle, and the memory further comprises instructions stored thereon that, when executed by the processing subsystem, cause the system to:

determine one or more identifiers and freshness indicators associated with data in the map cache;

send the one or more identifiers and freshness indicators to a second vehicle;

receive a response from the second vehicle indicating desired data based on the one or more identifiers and freshness indicators; and

send the desired data to the second vehicle.

14. The system of claim 11 , wherein aggregation of the local safe landing area map with the one or more remotely-generated safe landing area maps to form the fused safe landing area map further comprises:

computation of a combination of the local safe area landing map with the one or more remotely-generated safe landing area maps; and

use of classification confidence values as weights for overlapping areas.

15. The system of claim 11 , wherein the memory further comprises instructions stored thereon that, when executed by the processing subsystem, cause the system to:

perform feature extraction based on the perception sensor data;

establish values for the safe landing area classifications based on matching extracted features from the perception sensor data with expected safe landing characteristics; and

adjust the classification confidences associated with the potential landing areas based on a measurement confidence in the safe landing area classifications.