IEEE - Aerospace and Electronic Systems - May 2022 - Tutorial XV - 3

Image Licensed by Ingram Publishing
Visual servoing is commonly used with classical computer
vision methods to track features over several image
frames and to create stable control references to land the aircraft
on a desired target. Despite the potential of IBVS in
terms of autonomous landing, additional assumptions are
required, for example that the features in the image are static
features of the object, or that the object does not leave the
field ofview [7]. Furthermore, the implementation ofvisualbased
autonomous landing systems requires rigorous assessments
in simulated environments to identify possible perils
before deploying the whole system in the real world.
Lately, deep learning has been proposed as an alternative
to replace feature-based methods with convolutional neural
networks (CNNs) for landmark detection [8]. The use of
CNN has exhibited robustness with diverse lighting conditions,
scale variations, and rotations. Notwithstanding the
potential ofdeep learning-based object detectors, these models
typically require extensive amount of human-labeled
datasets and vast computational resources that are usually
available only with off-board computing strategies [9].
In this work, we address these problems by proposing a
complete monocular visual-based perception and control
strategy for the autonomous landing of a UAV in a Gazebobased
simulated environment. This system aims to mitigate
the current limitations on classic computer vision-based
methods created by changes in the appearance in the image
by using a Kalman filter to estimate the position of the template
throughout the landing process. Additionally, the use of
only IBVS techniques for the control of the aircraft reduces
the computational cost ofthe system and eliminates the need
for expensive 3D position reconstruction calculations, thus
allowing for real-time control of small UAVs with low-cost
computers.
Figure 1 illustrates the general workflowofthe proposed
method. Initially, the system computes the homography
matrix between the current image frame and the predefined
template, using a feature-based detector. Next, the homography
matrix is used to compute the corners and the centroid of
the object in the current image frame. These points are then
passed to a Kalman filter estimation module. Finally, the Kalman
filter estimations are used to track the template in the
image frame, and as a process variable for a set ofthree PIDbased
controllers that perform the safe landing ofthe vehicle.
MAY 2022
The full system was developed and assessed in a
Gazebo-based simulated environment in order to bridge
the gap between real-world deployment and theory, and to
reduce the number of risks while the vehicle is tested. All
the parameters for the vision and control systems employed
in the Gazebo-based simulation were directly transferred to
the real-world quad-rotor in a zero-shot1 simulation to reality
fashion in order to validate that these simple approaches
can be effectively transferred to the vehicle without additional
tuning [16]. Overall, the principal contributions of
this work can be summarized as follows.
1) A complete, flexible, Gazebo-based simulation of a
visual-based landing system for low-cost UAVs.
2) The implementation of a Kalman-filter-based methodology
for landing platform tracking using monocular
vision in both a simulated and a physical drone.
3) A control strategy for quadcopter landing that is
seamlessly implemented using the popular PX4
software-in-the-loop (SITL) Gazebo interface,
which facilitates its transfer to a physical drone.
This article consists of five sections, as follows.
" Related Works " presents other pertinent research.
" Vision System " explains the feature-based detector and
Kalman filer. " Control System " describes the proposed
control strategy for the landing maneuver. Next, we present
" Simulation Results " and " Experimental Results "
respectively. Finally, we provide the " Conclusion. "
RELATED WORK
Autonomous landing for multirotor aircraft is a problem
that has been extensively studied. Various approaches
have relied on the use of vision-based techniques to
identifythe salientfeaturesinan image and toland
the vehicle on both static [18]-[20] and moving platforms
[10], [14], [15]. Classic computer vision
1It refers to when parameters are learned or set in a source domain
(simulation) and tested without fine-tuning in a target domain (realworld).
IEEE
A&E SYSTEMS MAGAZINE
3
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
