Multi-sensor-based unmanned aerial vehicle and method for controlling same
An unmanned aerial vehicle may include: a sensor part configured to acquire inertia information or position information of the unmanned aerial vehicle; and a controller. The controller is configured to estimate the position of the unmanned aerial vehicle by applying the information acquired by the sensor part to an extended Kalman filter and control movement of the unmanned aerial vehicle, based on the estimated position of the unmanned aerial vehicle. The sensor part includes: an inertia sensor configured to acquire the inertia information of the unmanned aerial vehicle; a tag recognition sensor configured to recognize a tag attached to a rack and acquire absolute position information of the unmanned aerial vehicle; and an image sensor attached to the unmanned aerial vehicle so as to acquire an image of the movement environment of the unmanned aerial vehicle.
1. An unmanned aerial vehicle comprising:
a sensor part configured to acquire inertia information or position information of the unmanned aerial vehicle; and
a controller configured to estimate a position of the unmanned aerial vehicle and control movement of the unmanned aerial vehicle based on the estimated position of the unmanned aerial vehicle,
wherein the sensor part comprises:
an inertia sensor configured to acquire inertia information of the unmanned aerial vehicle,
a tag recognition sensor configured to recognize a tag attached to a fixed place, and acquire tag recognition information,
an image sensor attached to the unmanned aerial vehicle and configured to acquire an image of a movement environment of the unmanned aerial vehicle, and
a lower camera sensor attached to the unmanned aerial vehicle and configured to acquire image information of an area below a movement path of the unmanned aerial vehicle,
wherein the controller is further configured to:
acquire relative distance information and relative angle information for the recognized tag, compare the relative distance information and the relative angle information with absolute position information of the tag recorded in a predetermined tag map, and acquire absolute position information of the unmanned aerial vehicle based on the recognized tag,
calculate first visual movement distance information of the unmanned aerial vehicle based on the acquired absolute position information of the unmanned aerial vehicle or the acquired image of the movement environment of the unmanned aerial vehicle,
extract first edge information and second edge information based on the image information of the area below the movement path of the unmanned aerial vehicle acquired through the lower camera sensor,
compare the first edge information and the second edge information with a center line of the image information acquired through the lower camera sensor,
acquire lateral position information and yaw angle information based on the comparison,
perform a state prediction of the unmanned aerial vehicle by applying the inertia information to an extended Kalman filter, and
perform a measurement update of the unmanned aerial vehicle by applying the absolute position information, the first visual movement distance information, the acquired lateral position information, and the yaw angle information to the extended Kalman filter.
2. The unmanned aerial vehicle of claim 1 , wherein the controller is further configured to calculate the first visual movement distance information of the unmanned aerial vehicle by using a scan matching algorithm.
3. The unmanned aerial vehicle of claim 1 ,
wherein the sensor part further comprises an altitude sensor configured to acquire altitude information of the unmanned aerial vehicle, and
wherein the controller is further configured to estimate a position of the unmanned aerial vehicle by applying the altitude information to the extended Kalman filter.
4. The unmanned aerial vehicle of claim 1 , wherein the sensor part further comprises an upper camera sensor attached to the unmanned aerial vehicle and configured to acquire image information of an area above the unmanned aerial vehicle.
5. The unmanned aerial vehicle of claim 4 , wherein the controller is further configured to:
calculate second visual movement distance (visual odometry) information of the unmanned aerial vehicle based on the acquired image information of the area above the unmanned aerial vehicle, and
estimate a position of the unmanned aerial vehicle by applying the second visual movement distance information to the extended Kalman filter.
6. The unmanned aerial vehicle of claim 5 , wherein the controller is further configured to:
calculate pseudo-covariance from the image information of the area above the unmanned aerial vehicle by using a visual simultaneous localization and mapping (SLAM) algorithm; and
apply the calculated pseudo-covariance to the extended Kalman filter.
7. The unmanned aerial vehicle of claim 6 , wherein the visual SLAM algorithm is an oriented fast and rotated brief-SLAM (ORB-SLAM) algorithm.
8. The unmanned aerial vehicle of claim 1 , further comprising a barcode reader configured to recognize a barcode attached to an object.
9. The unmanned aerial vehicle of claim 1 , wherein the tag recognition sensor comprises:
a first tag recognition sensor configured to recognize a tag in front of the unmanned aerial vehicle; and
a second tag recognition sensor configured to recognize a tag behind the unmanned aerial vehicle.
10. The unmanned aerial vehicle of claim 1 , wherein the image sensor comprises at least one of a two-dimension (2D) lidar, a 3D lidar, a red, green, and blue-D (RGB D) sensor, and a camera.
11. The unmanned aerial vehicle of claim 1 , wherein the controller is further configured to:
calculate a Mahalanobis distance for at least one of the absolute position information, the first visual movement information, a second visual movement distance, the lateral position information, or the yaw angle information; and
determine whether to use information for the measurement update of the extended Kalman filter based on whether the calculated Mahalanobis distance is less than a designated value.
12. A method comprising:
acquiring inertia information of an unmanned aerial vehicle;
recognizing a tag attached to a fixed place through a tag recognition sensor;
acquiring relative distance information and relative angle information for the recognized tag;
comparing the relative distance and angle information with absolute position information of the tag recorded in a predetermined tag map;
acquiring absolute position information of the unmanned aerial vehicle based on the comparison;
acquiring an image of a movement environment of the unmanned aerial vehicle through an image sensor attached to the unmanned aerial vehicle;
acquiring first visual movement distance (visual odometry) information of the unmanned aerial vehicle, based on the acquired absolute position information of the unmanned aerial vehicle or the image of an unmanned aerial vehicle movement environment;
acquiring image information of an area below a movement path of the unmanned aerial vehicle through a lower camera sensor attached to the unmanned aerial vehicle;
extracting first edge information and second edge information based on the acquired image information of the area below the movement path of the unmanned aerial vehicle acquired through the lower camera sensor;
comparing the first edge information and the second edge information with a center line of the image information acquired through the lower camera sensor;
acquiring lateral position information and yaw angle information based on the comparison;
performing a state prediction to estimate a position of the unmanned aerial vehicle by applying the inertia information to an extended Kalman filter; and
perform measurement update to estimate the position of the unmanned aerial vehicle by applying the acquired absolute position information the first visual movement distance information, the acquired lateral position information, and the yaw angle information to the extended Kalman filter.
13. The method of claim 12 , further comprising;
acquiring altitude information of the unmanned aerial vehicle through an altitude sensor; and
estimating a position of the unmanned aerial vehicle by applying the altitude information to the extended Kalman filter.
14. The method of claim 12 , further comprising:
acquiring image information of an area above the unmanned aerial vehicle through an upper camera sensor;
calculating second visual movement distance (visual odometry) information of the unmanned aerial vehicle based on the acquired image information of the area above the unmanned aerial vehicle; and
estimating a position of the unmanned aerial vehicle by applying the second visual movement distance information to the extended Kalman filter.
15. The method of claim 14 , further comprising:
calculating pseudo-covariance from the image information of the area above the unmanned aerial vehicle by using a visual SLAM algorithm; and
applying the calculated pseudo-covariance to the extended Kalman filter.
16. The method of claim 14 , further comprising:
calculating a Mahalanobis distance for at least one of the absolute position information, the first visual movement distance, the second visual movement distance, the lateral position information, or the yaw angle information of the unmanned aerial vehicle; and
determining whether to use information to the measurement update of the extended Kalman filter based on whether the calculated Mahalanobis distance is less than a designated value.