Aerial vehicle touchdown detection

Patent metadata

Field	Value
Publication number	US-11726498-B2
Application number	US-202117306204-A
Country	US
Kind code	B2
Filing date	May 3, 2021
Priority date	Feb 9, 2018
Publication date	Aug 15, 2023
Grant date	Aug 15, 2023

Abstract

A technique is introduced for touchdown detection during autonomous landing by an aerial vehicle. In some embodiments, the introduced technique includes processing perception inputs with a dynamics model of the aerial vehicle to estimate the external forces and/or torques acting on the aerial vehicle. The estimated external forces and/or torques are continually monitored while the aerial vehicle is landing to determine when the aerial vehicle is sufficiently supported by a landing surface. In some embodiments, semantic information associated with objects in the environment is utilized to configure parameters associated with the touchdown detection process.

First claim

What is claimed is:

1. An apparatus comprising:
one or more non-transitory computer readable storage media having program instructions stored thereon that, when executed by a processor, direct the processor to:
responsive to initiation of a landing sequence, generate a first control command configured to cause a propulsion system of an aerial vehicle to reduce thrust to land on a physical surface in a physical environment;
continually estimate, based on perception inputs, external forces acting on the aerial vehicle during the landing sequence,
wherein the perception inputs do not include data output by a tactile force sensor;

determine, based on the estimated external forces, that the aerial vehicle is in contact with the physical surface;
responsive to determining that the aerial vehicle is in contact with the physical surface, generate a second control command configured to cause the aerial vehicle to further reduce thrust;
determine, based on the estimated external forces, that the aerial vehicle is supported by the physical surface; and
responsive to determining that the aerial vehicle is supported by the physical surface, generate a third control command configured to cause the propulsion system to power down.

2. The apparatus of claim 1 , wherein the second control command is configured to cause the aerial vehicle to further reduce thrust gradually over a period of time.

3. The apparatus of claim 1 , wherein the external forces include external torques.

4. The apparatus of claim 1 , wherein the perception inputs include sensor data from sensors onboard the aerial vehicle, and wherein the program instructions, when executed by the processor, direct the processor to:
process the sensor data to generate semantic information associated with the physical environment; and
adjust a parameter used to determine that the aerial vehicle is supported by the physical surface based on the semantic information.

5. The apparatus of claim 1 , wherein the perception inputs include data output by any one or more of:
an image capture device onboard the aerial vehicle;
an accelerometer onboard the aerial vehicle;
a gyroscope onboard the aerial vehicle;
an inertial measurement unit (IMU) onboard the aerial vehicle;
a state observer; or
the propulsion system.

6. The apparatus of claim 1 , wherein to estimate external forces acting on the aerial vehicle, the program instructions, when executed by the processor, direct the processor to:
process the perception inputs using a dynamics model of the aerial vehicle.

7. The apparatus of claim 1 , wherein to determine that the aerial vehicle is supported by the physical surface, the program instructions, when executed by the processor, direct the processor to:
process information regarding changes in the estimated external forces using a machine learning model,
wherein the machine learning model is trained using data gathered by the aerial vehicle during one or more previous landings.

8. The apparatus of claim 1 , wherein the program instructions, when executed by the processor, direct the processor to:
estimate, based on the perception inputs, external forces acting on the aerial vehicle after the propulsion system has powered down;
detect, based on the estimate, that the aerial vehicle is no longer supported by the physical surface; and
generate a fourth control command configured to cause the propulsion system to power up and cause the aerial vehicle to take off.

9. The apparatus of claim 1 , wherein determining that the aerial vehicle is supported by the physical surface includes determining whether the physical surface is a ground surface in the physical environment or a hand of a person that has caught the aerial vehicle.

10. An aerial vehicle comprising:
a propulsion system;
a non-tactile force based sensor device; and
a navigation system communicatively coupled to the sensor device and the propulsion system, the navigation system configured to:
continually estimate, based on perception inputs sensed by the sensor device, external forces acting on the aerial vehicle while the aerial vehicle is descending to land on a physical surface in a physical environment;
determine, based on the estimated external forces, that the aerial vehicle is supported by the physical surface; and
responsive to determining that the aerial vehicle is supported by the physical surface, generate a control command configured to cause the propulsion system to power down.

11. The aerial vehicle of claim 10 , wherein the external forces include external torques.

12. The aerial vehicle of claim 10 , wherein to estimate external forces acting on the aerial vehicle, the navigation system is further configured to process the perception inputs using a dynamics model of the aerial vehicle.

13. The aerial vehicle of claim 10 , wherein to determine that the aerial vehicle is supported by the physical surface, the navigation system is further configured to:
process information regarding changes in the estimated external forces using a machine learning model, wherein the machine learning model is trained using data gathered by the aerial vehicle during one or more previous landings.

14. The aerial vehicle of claim 10 , wherein the non-tactile force based sensor device includes any of:
an image capture device;
an accelerometer;
a gyroscope;
an inertial measurement unit (IMU); or
a current sensor coupled to the propulsion system.

15. The aerial vehicle of claim 10 , wherein the navigation system is configured to:
determine that the aerial vehicle is within a threshold proximity to the physical surface in the physical environment;
wherein the navigation system continually estimates external forces acting on the aerial vehicle while the aerial vehicle is descending to land on the physical surface in the physical environment responsive to determining that the aerial vehicle is within the threshold proximity.

16. The aerial vehicle of claim 10 , wherein the navigation system is configured to:
estimate, based on the perception inputs, external forces acting on the aerial vehicle after the propulsion system has powered down;
detect, based on the estimate, that the aerial vehicle is no longer supported by the physical surface; and
generate another control command configured to cause the propulsion system to power up and cause the aerial vehicle to take off.

17. An autonomous navigation system for landing an unmanned aerial vehicle (UAV) on a physical surface in a physical environment, the autonomous navigation system comprising:
an external force estimation module configured to continually estimate, based on perception inputs, external forces acting on the UAV while the UAV is descending to land on the physical surface in the physical environment;
a touchdown detection module configured to determine, based on the estimated external forces, that the UAV is supported by the physical surface; and
a flight controller configured to generate a control command configured to cause the propulsion system to power down responsive to determine that the UAV is supported by the physical surface.

18. The autonomous navigation system of claim 17 , wherein the external forces include external torques and wherein the perception inputs do not include data output by a tactile force sensor.

19. The autonomous navigation system of claim 17 , wherein the perception inputs include data output by any one or more of:
an image capture device onboard the UAV;
an accelerometer onboard the UAV;
a gyroscope o

Assignees

• Skydio Inc

Inventors

• O'Flaherty Rowland Wilde
• Tomic Teodor
• Martirosyan Hayk
• Bachrach Abraham Galton
• Holtz Kristen Marie
• Zhu Jack Louis

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G05D1/654

  Landing (docking at a base station G05D1/661) · CPC title

• B64U2101/30

  for imaging, photography or videography · CPC title

• B64U10/14

  with four distinct rotor axes, e.g. quadcopters · CPC title