Buoyancy and impact recovery system
View Patent ↗Methods, systems and apparatus for the deploying of buoyancy and impact reduction measures during operation of a UAV in the event of a failure, malfunction or collision. One or more airbags or bladders may be inflated to reduce the force transferred to the UAV as a result of a crash or collision. The bladders may both be used in the impact reduction as well as being used as a floatation device in the event a water landing/crash. The airbags may be configured to keep the UAV afloat so as to allow for the recovery of the UAV.
1. A buoyancy and impact recovery system attached to an unmanned aerial vehicle (UAV), the system comprising:
a communication module;
a battery module;
a global positioning module (GPS);
one or more sensor modules;
a controlled descent module; and
one or more inflatable bladders, wherein the one or more inflatable bladders are stored in an uninflated arrangement; and
wherein the system is configured to:
receive, from the one or more sensors, sensor data;
identify, based at least in part on the received sensor data, one or more threats to the UAV;
initiate, based at least in part on the identifying of the threats and received sensor data, one or more mitigation procedures, wherein the mitigation procedures comprise:
a controlled descent process, wherein the controlled descent process is configured to reduce a rate of descent of the UAV; and
an impact reduction process, wherein the impact reduction process comprises inflating one or more of the one or more inflatable bladders based at least in part on the threats identified;
transmit, by the communication module, a distress signal indicating an incident type, a position of the UAV when the controlled descent process was initiated, current position of the UAV and the status of the UAV and system.
2. The system of claim 1 , wherein the controlled descent module comprises a parachute.
3. The system of claim 1 , wherein the controlled descent module is configured to control one or more rotors, wherein the controlling of the one or more rotors establishes an autorotation descent.
4. The system of claim 1 , wherein the one or more threats are determined to be structures.
5. The system of claim 1 , wherein the one or more threats are determined to be a malfunction or failure of one or more rotors.
6. The system of claim 1 , wherein identification of the one or more threats comprises:
aggregating the received sensor data;
analyzing, by one or more machine learning models, the aggregated data;
classifying one or more possible threats;
determining a threat level of each of the one or more possible threats; and
tracking the one or more possible threats when their corresponding threat level is above a first predetermined threshold; and
wherein the one or more mitigation procedures are initiated when the threat level of one or more possible threats is above a second predetermined threshold.
7. The system of claim 6 , wherein the aggregated data comprises image data received from one or more camera sensors.
8. The system of claim 7 , wherein the one or more machine learning models are computer vision models and the threats identified are visual threats; and
wherein the tracking comprises maintaining a current record of a position, orientation and distance of a visual threat.
9. The system of claim 6 , wherein the aggregated data comprises inertial measurement unit data.
10. The system of claim 9 , wherein the one or more machine learning models are configured to predict component health for one or more critical components of the UAV and the threats identified are component failure threats; and
wherein determining a threat level for component failure threats comprises predicting a time to failure for critical components associated with the component failure threats.
11. A computer implemented method for initiating a buoyancy and impact recovery procedure of one or more buoyancy and impact recovery systems attached to an unmanned aerial vehicle (UAV), the method comprising:
receiving, from the one or more sensors, sensor data;
identifying, based at least in part on the received sensor data, one or more threats to the UAV;
initiating, based at least in part on the identifying of the threats and received sensor data, one or more mitigation procedures, wherein the mitigation procedures comprise:
a controlled descent process, performed by a controlled descent module, wherein the controlled descent process is configured to reduce a rate of descent of the UAV; and
an impact reduction process, wherein the impact reduction process comprises inflating, one or more inflatable bladders housed within the system, based at least in part on the threats identified; and
transmitting, by a communication module, a distress signal indicating an incident type, a position of the UAV when the controlled descent process was initiated, current position of the UAV and a status of the UAV and system.
12. The method of claim 11 , wherein the controlled descent module comprises a parachute.
13. The method of claim 11 , wherein the controlled descent module is configured to control one or more rotors, wherein the controlling of the one or more rotors establishes an autorotation descent.
14. The method of claim 11 , wherein the one or more threats are determined to be structures.
15. The method of claim 11 , wherein the one or more threats are determined to be a malfunction or failure of one or more rotors.
16. The method of claim 11 , wherein identification of the one or more threats comprises:
aggregating the received sensor data;
analyzing, by one or more machine learning models, the aggregated data;
classifying one or more possible threats;
determining a threat level of each of the one or more possible threats; and
tracking the one or more possible threats when their corresponding threat level is above a first predetermined threshold; and
wherein the one or more mitigation procedures are initiated when the threat level of one or more possible threats is above a second predetermined threshold.
17. The method of claim 16 , wherein the aggregated data comprises image data received from one or more camera sensors.
18. The method of claim 17 , wherein the one or more machine learning models are computer vision models and the threats identified are visual threats; and
wherein the tracking comprises maintaining a current record of a position, orientation and distance of a visual threat.
19. The method of claim 16 , wherein the aggregated data comprises inertial measurement unit data.
20. The method of claim 19 , wherein the one or more machine learning models are configured to predict component health for one or more critical components of the UAV and the threats identified are component failure threats; and
wherein determining a threat level for component failure threats comprises predicting a time to failure for critical components associated with the component failure threats.