IEEE - Aerospace and Electronic Systems - May 2022 - Tutorial XV - 14

Monocular Visual Autonomous Landing System for Quadcopter Drones Using Software in the Loop
Table 5.
Experimental Landing Errors Measured From the
Center of the Pad to the Center of the Vehicle
Controller
PD
Average
Standard
deviation
Centroid
X [m]
Centroid
Y [m]
0.1314 0.1592
0.1041 0.1344
less than 16 centimeters. Compared to the results in
Table 3, the error in the real-world implementation of
the PD controller is around five times that of the simulation.
Although these results seem undesirable, the
rotor-craft is capable of precisely landing on the
desired platform and accomplishing the autonomous
landing task, as expected from the simulation results.
CONCLUSION
the system. The size of the image was also reduced to
320 240 pixels to obtain a frame rate of 15 FPS and
to ensure system convergence. The SIFT feature detector-descriptor
was used (based on the simulation
results) to carry out these tests.
To bridge the algorithms developed during the simulation
phase with the real-world, it was necessary to unplug the
SITL component. This was achieved by connecting the Pixhawk
FCU to the on-board computer and launching all the
nodes developed in ROS. This process guaranteed that the
system was connected with the physical FCU, bypassing the
need for the SITL component. The detection and control
pipeline will, therefore, operate directly in the custom rotorcraft,
enabling it to carry out autonomous landing maneuvers.
All the parameters used during the simulation where transferred
to the aircraft withoutfinetuning to demonstrate that
the use of simple vision and control models allow for zeroshot
domain transfer.
Figure 12 presents the results obtained with the PD
. As expected, the system
controller for each state Xði¼1:5Þ
t
is capable of landing the rotor-craft on the landing platform
within approximately 35 s. The real-world system
displays more spiky behavior than the simulated vehicle
[Figure 8 (orange line)]; however, as the test advances, the
response of the controller stabilizes, guaranteeing the
appropriate landing of the UAV.
Comparably, the RMSE ofthe controller during the landing
procedure was also assessed and presented in Table 4.
This error was computed over the three landing trials conducted
with the real-world rotor-craft while the vehicle was
trying landing. Altogether, it is possible to appraise that the
vehicle maintains strikingly similar values of RMSE for the
variables X; Y; u when compared with the RMSE presented
for the simulation in Table 2. In fact, the RMSE is slightly
reduced within the real-world landing trials. The plots of
these errors are not shown as their dynamic behavior is similar
as the ones presented in Figure 9 (orange line).
Finally, to complete the assessment process, Table 5 [33]
presents the position error between the vehicle and the landing
platform. This error was computed as the distance from
the center of the pad to the center of the rotor-craft once it
had landed. It can be seen that the average value is
14
This article presents an SITL approach to developing a
monocular image-based autonomous landing system
for quadcopter drones. The proposed method and system,
which integrates ROS, Gazebo, and PX4's SITL
tools, enables users to not only endow quadcopters
with low-cost vision-based autonomous landing capabilities,
but also to fine-tune all the parameters of a
potentially dangerous device in a safe simulated environment.
With minimal modifications, both the vision
and control modules developed in our simulated environment,
were successfully validated in a physical DJI
F450 with an Odroid XU4 on-board computer and a
Pixhawk 1 flight controller.
ACKNOWLEDGMENTS
This work was supported by Universidad Autonoma de
Occidente (UAO), project 17INTER-297. The authors
would like to thank the Robotics and Autonomous Systems
(RAS) research incubator and UAO's Vicerrectorıa
de Investigaciones, Innovacion y Emprendimiento for
their support.
REFERENCES
[1] S. Bayraktar and E. Feron, " Experiments with small
unmanned helicopter nose-up landings, " J. Guid., Control,
Dyn., vol. 32, no. 1, pp. 332-337, 2009, doi: 10.2514/
1.36470.
[2] D.H.Ye,J.Li, Q. Chen,J.Wachs,and C.Bouman, " Deep
learning for moving object detection and tracking from a
single camera in unmanned aerial vehicles (UAVs), " Electron.
Imag., vol. 2018, no. 10, pp. 4661-4666, 2018,
doi: 10.2352/ISSN.2470-1173.2018.10.IMAWM-466.
[3] R. Jin, H. M. Owais, D. Lin, T. Song, and Y. Yuan,
" Ellipse proposal and convolutional neural network discriminant
for autonomous landing marker detection, " J.
Field Robot., vol. 36, no. 1, pp. 6-16, 2018, doi: 10.1002/
rob.21814.
[4] T. Tomic et al., " Toward a fully autonomous UAV:
Research platform for indoor and outdoor urban search
and rescue, " IEEE Robot. Autom. Mag., vol. 19, no. 3,
pp. 46-56, Sep. 2012, doi: 10.1109/MRA.2012.2206473.
IEEE A&E SYSTEMS MAGAZINE
MAY 2022

http://dx.doi.org/10.2514/1.36470 http://dx.doi.org/10.2514/1.36470 http://dx.doi.org/10.2352/ISSN.2470-1173.2018.10.IMAWM-466 http://dx.doi.org/10.1002/rob.21814 http://dx.doi.org/10.1002/rob.21814 http://dx.doi.org/10.1109/MRA.2012.2206473

IEEE - Aerospace and Electronic Systems - May 2022 - Tutorial XV

Table of Contents for the Digital Edition of IEEE - Aerospace and Electronic Systems - May 2022 - Tutorial XV