System and method of controlling drone based on pressure
A system and a method of controlling a drone based on pressure are provided. The method includes: installing a pressure sensor under a bearing surface of a platform body; obtaining a pressure distribution map via the pressure sensor; obtaining a centroid on the bearing surface by inputting the pressure distribution map to a machine learning model; calculating a vector from a reference centroid on the bearing surface to the centroid; and controlling a flight of the drone according to the vector.
1. A system of controlling a drone based on pressure, comprising:
a transceiver, communicatively connected to the drone;
a storage medium, storing a machine learning model;
a platform body, comprising a bearing surface;
a pressure sensor, installed under the bearing surface; and
a processor, coupled to the storage medium, the transceiver, and the pressure sensor, wherein the processor is configured to:
obtain a pressure distribution map via the pressure sensor;
obtain a centroid on the bearing surface by inputting the pressure distribution map into the machine learning model;
calculate a vector from a reference centroid to the centroid on the bearing surface; control a flight of the drone according to the vector;
calculate an area difference between a reference pressure distribution map and the pressure distribution map based on changes in contact area on the bearing surface between the reference pressure distribution map and the pressure distribution map; and
control the drone to move vertically according to the area difference.
2. The system according to claim 1 , wherein the processor is further configured to:
control the drone to move horizontally according to the vector.
3. The system according to claim 2 , wherein the processor is further configured to:
in response to a magnitude of the vector decreasing to less than a threshold value while the drone is moving horizontally, control the drone to stop moving horizontally.
4. The system according to claim 1 , wherein the processor comprises a calibration mode, wherein the processor in the calibration mode is configured to:
obtain the reference pressure distribution map via the pressure sensor; and
obtain the reference centroid by inputting the reference pressure distribution map into the machine learning model.
5. The system according to claim 1 , wherein the processor is further configured to:
in response to the area difference being positive, control the drone to move vertically upward; and
in response to the area difference being negative, control the drone to move vertically downward.
6. The system according to claim 1 , wherein the processor is further configured to:
in response to the area difference changing from positive to negative or from negative to positive when the drone moves vertically, control the drone to stop moving vertically.
7. The system according to claim 1 , wherein the processor is further configured to:
obtain the reference pressure distribution map, wherein the reference pressure distribution map comprises a first reference pressure distribution and a second reference pressure distribution, wherein the pressure distribution map comprises a first pressure distribution and a second pressure distribution;
calculate a first area difference between the first reference pressure distribution and the first pressure distribution, and calculate a second area difference between the second reference pressure distribution and the second pressure distribution; and
control a yaw of the drone according to the first area difference and the second area difference.
8. The system according to claim 7 , wherein the processor is further configured to:
in response to the first area difference being greater than a threshold value and the second area difference being less than or equal to the threshold value, control the drone to yaw in a first direction.
9. The system according to claim 1 , wherein
the pressure sensor comprises a first region and a second region, wherein the first region and the second region are not connected, wherein the processor is further configured to:
obtain a pressure sensing value via the second region of the pressure sensor;
calculate a pressure difference between a reference pressure sensing value and the pressure sensing value; and
control the drone to move vertically according to the pressure difference.
10. The system according to claim 9 , wherein the first region is used to measure a pressure exerted by a hip of a user on the bearing surface, wherein the second region is used to measure a pressure exerted by a palm of the user on the bearing surface.
11. The system according to claim 9 , wherein the processor is further configured to:
in response to the pressure difference being negative, control the drone to move vertically upward; and
in response to the pressure difference being positive, control the drone to move vertically downward.
12. The system according to claim 9 , wherein the processor is further configured to:
in response to the pressure difference changing from positive to negative or from negative to positive when the drone moves vertically, control the drone to stop moving vertically.
13. The system according to claim 1 , wherein the platform body further comprises a handrail, wherein the system further comprises:
an accelerometer, installed in the handrail and coupled to the processor; and
a gyroscope, installed in the handrail and coupled to the processor.
14. The system according to claim 13 , wherein the processor is further configured to:
obtain acceleration via the accelerometer;
obtain angular velocity via the gyroscope; and
obtain the centroid on the bearing surface by inputting the pressure distribution map, the acceleration, and the angular velocity into the machine learning model.
15. The system according to claim 1 , further comprising:
a display device, communicatively connected to an image capturing device of the drone, wherein the display device displays an image provided by the image capturing device.
16. The system according to claim 15 , wherein the display device comprises
a head mounted display, receiving a first signal to provide a mixed reality scene associated with the image according to the first signal.
17. The system according to claim 16 , further comprising:
a remote control, communicatively connected to the head mounted display, wherein the remote control transmits a second signal to the head mounted display.
18. The system according to claim 16 , wherein the head mounted display is communicatively connected to the processor, wherein the processor is further configured to:
determine whether a stepping behavior occurs on the bearing surface via the pressure sensor; and
in response to the stepping behavior, transmit a second signal to the head mounted display.
19. The system according to claim 1 , further comprising:
the drone, comprising an altitude sensor, wherein the altitude sensor obtains an altitude, wherein the drone receives a second signal from the processor, and moves vertically downward according to the second signal, wherein
in response to the altitude being less than a threshold value, the drone stops moving vertically downward.
20. The system according to claim 19 , wherein
when the drone stops moving vertically downward, the drone lands in response to continuously receiving the second signal.
21. The system according to claim 1 , wherein the machine learning model comprises a deep learning model.
22. A method of controlling a drone based on pressure, comprising:
installing a pressure sensor under a bearing surface of a platform body;
obtaining a pressure distribution map via the pressure sensor;
obtaining a centroid on the bearing surface by inputting the pressure distribution map into a machine learning model;
calculating a vector from a reference centroid to the centroid on the bearing surface;
controlling a flight of the drone according to the vector;
calculating an area difference between a reference pressure distribution map and the pressure distribution map based on changes in contact area on the bearing surface between the reference pressure distribution map and the pressure distribution map; and
controlling the drone to move vertically according to the area difference.