Navigating an unmanned aerial vehicle
Systems and methods for navigating an unmanned aerial vehicle are provided. One example aspect of the present disclosure is directed to a method for navigating an unmanned aerial vehicle. The method includes capturing, by one or more processors associated with a flight management system of an unmanned aerial vehicle, one or more images. The method includes assessing, by the one or more processors, signals from an inertial measurement unit (IMU). The method includes processing, by the one or more processors, the one or more captured images based on the assessed signals to generate one or more corrected images. The method includes processing, by the one or more processors, the one or more generated corrected images to approximate position data. The method includes causing, by the one or more processors, the unmanned aerial vehicle to be controlled based on the position data.
1. A method for controlling an unmanned aerial vehicle comprising:
capturing, by one or more processors associated with a flight management system of the unmanned aerial vehicle, more than one images, the capturing further comprising:
capturing a first image by a first optical device at a first time, the first image including an obstacle: and
capturing a second image by a second optical device at the first time, the second image including the obstacle, and the second optical device being situated a predetermined distance from the first optical device:
assessing, by the one or more processors, signals from an inertial measurement unit (TM U);
processing, by the one or more processors, the more than one images based on the assessed signals to generate one or more corrected images:
processing, by the one or more processors, the more than one generated corrected images to approximate a distance between the obstacle and the unmanned aerial vehicle, and
causing, by the one or more processors, the unmanned aerial vehicle to be controlled based on the approximated distance between the obstacle and the unmanned aerial vehicle, wherein processing to approximate the distance between the obstacle and the unmanned aerial vehicle is based, at least in part, on the predetermined distance and a pixel shift between the obstacle as included in the first image and the obstacle as included in the second image;
capturing a third image by the first optical device at a second time; and
capturing a fourth image by the second optical device at the second time,
estimating a first position of the obstacle at the first time;
estimating a second position of the obstacle at the second time;
estimating a velocity of the obstacle based on a difference between the first position and the second position and a difference between the first time and the second time;
capturing a fifth image by the first optical device at a third time;
capturing a sixth image by the second optical device at the third time;
estimating a third position of the obstacle at the third time; estimating a second velocity of the obstacle based on a difference between the second position and the third position and a difference between the second time and the third time; and
estimating an acceleration of the obstacle based, at least in part, on the first estimated velocity and the second estimated velocity, wherein processing the one or more captured images comprises stabilizing the one or more captured images.
2. The method of claim 1 , wherein the first optical device captures a first video stream, and wherein the second optical device captures a second video stream.
3. The method of claim 1 , wherein the IMU comprises an accelerometer, and wherein processing the one or more images comprises reducing blur.
4. The method of claim 1 , wherein the IMU comprises a microelectromechanical systems (MEMS) gyroscope.
5. The method of claim 1 , further including controlling the unmanned aerial vehicle based on the distance between the obstacle and the unmanned aerial vehicle, and wherein the controlling comprises causing, by the processor, the unmanned aerial vehicle to perform an avoidance maneuver.
6. The method of claim 1 , wherein estimating the distance between the obstacle and the unmanned aerial vehicle is further based on an instantaneous field of view (IFOV) associated with the first optical device.
7. The method of claim 1 , wherein estimating the distance between the obstacle and the unmanned aerial vehicle is further based on an instantaneous field of view (IFOV) associated with the second optical device.
8. The method of claim 6 , wherein the instantaneous field of view includes an amount of angular arc subtended by each pixel of the one or more images.
9. The method of claim 7 , wherein the instantaneous field of view includes an amount of angular arc subtended by each pixel of the one or more images.
10. The method of claim 5 , further comprising causing, by the processor, the unmanned aerial vehicle to return to a planned course after performing the avoidance maneuver.