Autonomous control techniques for avoiding collisions with cooperative aircraft

1. A non-transitory computer-readable medium having logic stored thereon that, in response to execution by one or more processors of an unmanned aerial vehicle (UAV), causes the UAV to perform actions comprising:

receiving at least one ADS-B message from an intruder aircraft;

generating an intruder location prediction based on the at least one ADS-B message;

comparing the intruder location prediction for the intruder aircraft to an ownship location prediction for the UAV to detect conflicts; and

in response to detecting a conflict between the intruder location prediction and the ownship location prediction:

determining a safe landing location along a planned route for the UAV; and

descending to land at the safe landing location;

wherein the ownship location prediction for the UAV is based on at least a current location of the UAV, a planned route being traversed, and a prediction of windspeed experienced by the UAV.

2. The non-transitory computer-readable medium of claim 1 , wherein generating the intruder location prediction based on the at least one ADS-B message includes:

determining a first location based on a first ADS-B message;

determining a second location based on a second ADS-B message; and

generating the intruder location prediction based on a line extending through the first location and the second location.

3. The non-transitory computer-readable medium of claim 1 , wherein generating the intruder location prediction based on the at least one ADS-B message includes:

determining a location, a heading, an airspeed, and a climb rate based on a first ADS-B message; and

generating the intruder location prediction based on the location, the heading, the airspeed, and the climb rate.

4. The non-transitory computer-readable medium of claim 3 , wherein generating the intruder location prediction based on the location, the heading, the airspeed, and the climb rate includes determining a reachable volume based on the location, the heading, the airspeed, and the climb rate.

5. The non-transitory computer-readable medium of claim 1 , wherein generating the intruder location prediction based on the at least one ADS-B message includes:

determining a location based on a first ADS-B message; and

determining probabilities of the intruder aircraft being at respective locations within a first prediction volume.

6. The non-transitory computer-readable medium of claim 5 , wherein the actions further comprise generating the ownship location prediction to include probabilities of the UAV being at respective locations within a second prediction volume; and

wherein comparing the intruder location prediction to the ownship location prediction to detect conflicts includes:

determining an overlapping portion of the first prediction volume and the second prediction volume;

combining the probabilities within the overlapping portion of the first prediction volume with the probabilities within the overlapping portion of the second prediction volume; and

comparing the combined probabilities to a predetermined threshold.

7. The non-transitory computer-readable medium of claim 1 , wherein comparing the intruder location prediction to the ownship location prediction to detect conflicts includes:

conducting a comparison of the intruder location prediction to the ownship location prediction at a first level of detail; and

in response to detecting a conflict in the first level of detail, conducting a comparison of the intruder location prediction to the ownship location prediction at a second level of detail.

8. The non-transitory computer-readable medium of claim 7 , wherein the comparison at the first level of detail includes updating the intruder location prediction and the ownship location prediction at a first rate, and wherein the comparison at the second level of detail includes updating the intruder location prediction and the ownship location prediction at a second rate faster than the first rate.

9. The non-transitory computer-readable medium of claim 7 , wherein conducting the comparison of the intruder location prediction to the ownship location prediction at the first level of detail includes determining whether a volume of the intruder location prediction intersects with a volume of the ownship location prediction; and

wherein conducting the comparison of the intruder location prediction to the ownship location prediction at the second level of detail includes:

determining a first predicted location for the intruder aircraft at one or more points in time;

determining a second predicted location for the UAV at the one or more points in time; and

determining whether the first predicted location and the second predicted location are in conflict at any of the one or more points in time.

10. The non-transitory computer-readable medium of claim 7 , wherein conducting the comparison of the intruder location prediction to the ownship location prediction at the first level of detail includes:

determining a first predicted location for the intruder aircraft at a first plurality points in time;

determining a second predicted location for the UAV at the first plurality of points in time; and

determining whether the first prediction location and the second location are in conflict at any of the first plurality of points in time;

wherein conducting the comparison of the intruder location prediction to the ownship location prediction at the second level of detail includes:

determining a third predicted location for the intruder aircraft at a second plurality of points in time;

determining a fourth prediction location for the UAV at the second plurality of points in time; and

determining whether the third predicted location and the fourth predicted location are in conflict at any of the second plurality of points in time;

wherein the first plurality of points in time are farther apart from each other than the second plurality of points in time.

11. An unmanned aerial vehicle (UAV), comprising:

an ADS-B receiver device;

a first set of processing cores;

a second set of processing cores; and

at least one non-transitory computer-readable medium having logic stored thereon that, in response to execution by the first set of processing cores, causes the first set of processing cores to execute a route traversal engine to autonomously control one or more propulsion devices of the UAV; and

at least one non-transitory computer-readable medium having logic stored thereon that, in response to execution by the second set of processing cores, causes the second set of processing cores to perform actions for predicting and avoiding collisions between the UAV and an intruder aircraft, the actions comprising:

receiving, via the ADS-B receiver device, at least one ADS-B message from the intruder aircraft;

generating an intruder location prediction based on the at least one ADS-B message;

comparing the intruder location prediction for the intruder aircraft to an ownship location prediction for the UAV to detect conflicts; and

in response to detecting a conflict between the intruder location prediction and the ownship location prediction, transmitting a notification of the conflict to the route traversal engine;

wherein the ownship location prediction for the UAV is based on at least a current location of the UAV, a planned route being traversed, and a prediction of windspeed experienced by the UAV.

12. The UAV of claim 11 , wherein generating the intruder location prediction based on the at least one ADS-B message includes:

determining a first location based on a first ADS-B message;

determining a second location based on a second ADS-B message; and

generating the intruder location prediction based on a line extending through the first location and the second location.

13. The UAV of claim 11 , wherein generating the intruder location prediction based on the at least one ADS-B message includes:

determining a location, a heading, an airspeed, and a climb rate based on a first ADS-B message; and

generating the intruder location prediction based on the location, the heading, the airspeed, and the climb rate.

14. The UAV of claim 13 , wherein generating the intruder location prediction based on the location, the heading, the airspeed, and the climb rate includes determining a reachable volume based on the location, the heading, the airspeed, and the climb rate.

15. The UAV of claim 11 , wherein generating the intruder location prediction based on the at least one ADS-B message includes:

determining a location based on a first ADS-B message; and

determining probabilities of the intruder aircraft being at respective locations within a first prediction volume.

16. The UAV of claim 15 , wherein the actions further comprise generating the ownship location prediction to include probabilities of the UAV being at respective locations within a second prediction volume; and

wherein comparing the intruder location prediction to the ownship location prediction to detect conflicts includes:

determining an overlapping portion of the first prediction volume and the second prediction volume;

combining the probabilities within the overlapping portion of the first prediction volume with the probabilities within the overlapping portion of the second prediction volume; and

comparing the combined probabilities to a predetermined threshold.

17. The UAV of claim 11 , wherein comparing the intruder location prediction to the ownship location prediction to detect conflicts includes:

conducting a comparison of the intruder location prediction to the ownship location prediction at a first level of detail; and

in response to detecting a conflict in the first level of detail, conducting a comparison of the intruder location prediction to the ownship location prediction at a second level of detail.

18. The UAV of claim 17 , wherein the comparison at the first level of detail includes updating the intruder location prediction and the ownship location prediction at a first rate, and wherein the comparison at the second level of detail includes updating the intruder location prediction and the ownship location prediction at a second rate faster than the first rate.

19. The UAV of claim 17 , wherein conducting the comparison of the intruder location prediction to the ownship location prediction at the first level of detail includes determining whether a volume of the intruder location prediction intersects with a volume of the ownship location prediction; and

wherein conducting the comparison of the intruder location prediction to the ownship location prediction at the second level of detail includes:

determining a first predicted location for the intruder aircraft at one or more points in time;

determining a second predicted location for the UAV at the one or more points in time; and

determining whether the first predicted location and the second predicted location are in conflict at any of the one or more points in time.

20. The UAV of claim 17 , wherein conducting the comparison of the intruder location prediction to the ownship location prediction at the first level of detail includes:

determining a first predicted location for the intruder aircraft at a first plurality points in time;

determining a second predicted location for the UAV at the first plurality of points in time; and

determining whether the first prediction location and the second location are in conflict at any of the first plurality of points in time;

wherein conducting the comparison of the intruder location prediction to the ownship location prediction at the second level of detail includes:

determining a third predicted location for the intruder aircraft at a second plurality of points in time;

determining a fourth prediction location for the UAV at the second plurality of points in time; and

determining whether the third predicted location and the fourth predicted location are in conflict at any of the second plurality of points in time;

wherein the first plurality of points in time are farther apart from each other than the second plurality of points in time.