High-altitude pseudo-satellite neural network for unmanned traffic management
A HAPS platform may execute a neural network (a “HAPSNN”) as it monitors air traffic; the neural network enables it to classify, predict, and resolve events in its airspace of coverage in real time as well as learn from new events that have never before been seen or detected. The HAPSNN-equipped HAPS platform may provide surveillance of nearly 100% of air traffic in its airspace of coverage, and the HAPSNN may process data received from a drone to facilitate safe and efficient drone operation within an airspace.
1. A platform for high-altitude flight and communication with unmanned aerial vehicles (UAVs), comprising:
a wireless transceiver;
a computer memory;
a communication facility for communicating, via the transceiver, with UAVs operating within a defined airspace; and
a computer including a processor and electronically stored instructions, executable by the processor, for using data received from the UAVs as input to a predictor that has been computationally trained to classify inspection data from the UAV as normal or anomalous, and identify actions to be taken based on a UAV state and a condition affecting its flight, in real-time, to enable the UAV to deviate from a preprogrammed flight path to inspect an anomalous detection,
wherein the UAV state comprises a spatial position and a velocity,
the computer being further configured to
while the UAV is traversing the preprogrammed flight path:
determine, prior to any communication between a UAV and a terrestrial communication source, based on the identified actions to be taken provided by the predictor, terrestrial features and their likelihood of interfering with current or future communications between the UAV and the terrestrial communication source during traversal of the deviation from the preprogrammed flight path, and
in response to a determination that the likelihood exceeds a threshold, establish a communication link bridging the UAV and the terrestrial communication source.
2. The platform of claim 1 , wherein the predictor is a neural network.
3. The platform of claim 1 , wherein the computer is further configured for communication with air-traffic control infrastructure.
4. The platform of claim 1 , wherein the terrestrial features are determined based on a locally or remotely stored map.
5. The platform of claim 1 , wherein the platform is a pseudo-satellite vehicle operating persistently at a high altitude while communicating with the UAVs.
6. A platform for high-altitude flight and communication with unmanned aerial vehicles (UAVs), comprising:
a wireless transceiver;
a computer memory;
a communication facility for communicating, via the transceiver, with UAVs operating within a defined airspace; and
a computer including a processor and electronically stored instructions, executable by the processor, for using data received from the UAVs as input to a predictor that has been computationally trained to classify inspection data from the UAV as normal or anomalous, and identify actions to be taken based on a UAV state and a condition affecting its flight, in real-time, to enable the UAV to deviate from a preprogrammed flight path to inspect an anomalous detection wherein the computer is configured for communication with air-traffic control infrastructure,
wherein the UAV state comprises a spatial position and a velocity, the computer being further configured to
(i) predictively determine, based on an anomalous detection and the identified actions to be taken provided by the predictor, a need for an altered flight plan for the UAV, and
(ii) in response to a determination, based on the identified actions to be taken provided by the predictor, that the altered flight plan is needed, cause the transceiver to wirelessly obtain authorization for the altered flight plan from the air-traffic control infrastructure and thereupon communicate the authorized altered flight plan to the UAV.
7. The platform of claim 6 , wherein the altered flight plan avoids a possible hazard.
8. The platform of claim 7 , wherein the hazard is a weather condition.
9. The platform of claim 7 , wherein the hazard is a possible collision with another UAV.
10. The platform of claim 6 , wherein the altered flight plan permits unplanned inspection of a terrestrial asset.
11. The platform of claim 6 , wherein the action to be taken is unplanned inspection of a terrestrial asset.
12. The platform of claim 6 , the computer being configured to, after predictively determining the need for the altered flight plan, predictively determine a region that encompasses the flight path and request airspace authorization for the region.
13. The platform of claim 6 , the computer being configured to, receive and monitor data from a plurality of UAVs including the respective UAV and manage airspace authorization requests for the plurality of UAVs in real time.
14. The platform of claim 6 , wherein the platform is a pseudo-satellite vehicle operating persistently at a high altitude while communicating with the UAVs.
15. A method of controlling a defined airspace using a high-altitude pseudosatellite, the method comprising the steps of:
wirelessly monitoring a state of at least one unmanned aerial vehicle (UAV) operating in the defined airspace, wherein the UAV state comprises a spatial position and a velocity;
detecting flight-affecting conditions in the defined airspace;
using data received from the at least one UAV as input to a predictor that has been computationally trained to classify inspection data from the UAV as normal or anomalous, and identify actions to be taken based on the UAV state and a detected flight-affecting condition, in real-time, to enable the UAV to deviate from a preprogrammed flight path to inspect an anomalous detection; and
using the predictor, causing the high-altitude pseudosatellite to:
while the UAV is traversing the preprogrammed flight path:
prior to any communication between a UAV and a terrestrial communication source, determine, based on the identified actions to be taken provided by the predictor, terrestrial features and their likelihood of interfering with current or future communications between the UAV and the terrestrial communication source during traversal of the deviation from the preprogrammed flight path, and
determine that the likelihood exceeds a threshold,
in response to a determination that the likelihood exceeds a threshold, establish a communication link bridging the UAV and the terrestrial communication source.
16. The method of claim 15 , wherein the predictor is a neural network.
17. The method of claim 15 , further comprising communicating with air-traffic control infrastructure.
18. The method of claim 15 , wherein the terrestrial features are determined based on a locally or remotely stored map.
19. A method of controlling a defined airspace using a high-altitude pseudosatellite configured for communication with air-traffic control infrastructure, the method comprising the steps of:
wirelessly monitoring a state of at least one unmanned aerial vehicle (UAV) operating in the defined airspace, wherein the UAV state comprises a spatial position and a velocity;
detecting flight-affecting conditions in the defined airspace;
using data received from the at least one UAV as input to a predictor that has been computationally trained to classify inspection data from the UAV as normal or anomalous, and identify actions to be taken based on the UAV state and a detected flight-affecting condition in real-time to enable the UAV to deviate from a preprogrammed flight path to inspect an anomalous detection; and
using the predictor, causing the high-altitude pseudosatellite to:
computationally determine, based on an anomalous detection and the identified actions to be taken provided by the predictor, a predicted need for an altered flight plan for the UAV; and
in response to a determination, based on the identified actions to be taken provided by the predictor, that the altered flight plan is needed, wirelessly obtain authorization for the altered flight plan from the air-traffic control infrastructure and communicate the authorized altered flight plan to the UAV.
20. The method of claim 19 , wherein the altered flight plan avoids a possible hazard.
21. The method of claim 20 , wherein the hazard is a weather condition.
22. The method of claim 20 , wherein the hazard is a possible collision with another UAV.
23. The method of claim 19 , wherein the altered flight plan permits unplanned inspection of a terrestrial asset.
24. The method of claim 19 , wherein the action to be taken is unplanned inspection of a terrestrial asset.