STUDIES IN ENGINEERING AND EXACT SCIENCES,
Journal Year:
2024,
Volume and Issue:
5(2), P. e9515 - e9515
Published: Oct. 22, 2024
Visual
servoing
is
a
commonly
employed
approach
in
robotics
and
unmanned
aerial
vehicles
(UAVs)
that
facilitates
accurate
object
positioning
movement
control
by
utilizing
visual
feedback.
As
quadrotors
gain
popularity,
more
methods
have
been
developed.
This
article
presents
method
for
enhancing
quadrotor
robustness
using
image-based
(IBVS)
with
fuzzy
logic.
Unlike
traditional
servoing,
which
relies
on
fixed
often
encounters
challenges
velocity
convergence
maintaining
the
field
of
view,
this
designed
to
enhance
servo
dynamically
adjusting
IBVS
system
through
logic
controller.
controller
adaptively
adjusts
response
feature
errors
depth
object's
points.
MATLAB
simulations
clearly
demonstrate
superior
performance
integrated
compared
classical
approaches,
showcasing
enhanced
capabilities
challenging
environments.
Sensors,
Journal Year:
2024,
Volume and Issue:
24(10), P. 3064 - 3064
Published: May 11, 2024
The
evolving
technologies
regarding
Unmanned
Aerial
Vehicles
(UAVs)
have
led
to
their
extended
applicability
in
diverse
domains,
including
surveillance,
commerce,
military,
and
smart
electric
grid
monitoring.
Modern
UAV
avionics
enable
precise
aircraft
operations
through
autonomous
navigation,
obstacle
identification,
collision
prevention.
structures
of
are
generally
complex,
thorough
hierarchies
intricate
connections
exist
between.
For
a
comprehensive
understanding
design,
this
paper
aims
assess
critically
review
the
purpose-classified
electronics
hardware
inside
UAVs,
each
with
corresponding
performance
metrics
thoroughly
analyzed.
This
includes
an
exploration
different
algorithms
used
for
data
processing,
flight
control,
protection,
communication.
Consequently,
enriches
knowledge
base
offering
informative
background
on
various
design
processes,
particularly
those
related
applications.
As
future
work
recommendation,
actual
relevant
project
is
openly
discussed.
International Journal of Computational Intelligence Systems,
Journal Year:
2025,
Volume and Issue:
18(1)
Published: Jan. 8, 2025
Visual
servoing
using
image
registration
is
a
method
employed
in
robotics
to
control
the
movement
of
system
visual
information.
In
this
context,
we
propose
new
intensity-based
algorithm
(IBIR)
that
uses
information
derived
from
images
acquired
at
different
times
or
views
determine
parameters
geometric
transformations
needed
align
these
images.
The
Arithmetic
Optimization
Algorithm
(AOA)
used
optimize
parameters,
minimizing
difference
between
be
aligned.
proposed
algorithm,
Intensity-Based
Image
Registration
via
Optimisation
(IBIRAOA),
robust
data
fluctuations
and
perturbations
can
avoid
local
optima.
Simulation
results
prove
importance
efficiency
terms
computation
time
similarity
aligned
compared
other
methods
based
on
various
metaheuristics.
addition,
our
confirm
significant
improvement
trajectory
wheeled
mobile
robot,
thus
reinforcing
overall
effectiveness
practical
navigation
robotic
applications.
Engineering Reports,
Journal Year:
2025,
Volume and Issue:
7(3)
Published: March 1, 2025
ABSTRACT
This
study
develops
and
evaluates
a
deep
learning
based
visual
servoing
(DLBVS)
control
system
for
guiding
industrial
robots
during
aircraft
refueling,
aiming
to
enhance
operational
efficiency
precision.
The
employs
monocular
camera
mounted
on
the
robot's
end
effector
capture
images
of
target
objects—the
refueling
nozzle
bottom
loading
adapter—eliminating
need
prior
calibration
simplifying
real‐world
implementation.
Using
learning,
identifies
feature
points
these
objects
estimate
their
pose
estimation,
providing
essential
data
precise
manipulation.
proposed
method
integrates
two‐stage
neural
networks
with
Efficient
Perspective‐n‐Point
(EPnP)
principle
determine
orientation
rotation
angles,
while
an
approximation
point
errors
calculates
linear
positions.
DLBVS
effectively
commands
robot
arm
approach
interact
targets,
demonstrating
reliable
performance
even
under
positional
deviations.
Quantitative
results
show
translational
below
0.5
mm
rotational
1.5°
both
adapter,
showcasing
system's
capability
intricate
operations.
work
contributes
practical,
calibration‐free
solution
enhancing
automation
in
aerospace
applications.
videos
sets
from
research
are
publicly
accessible
at
https://tinyurl.com/CiRAxDLBVS
.
Drones,
Journal Year:
2025,
Volume and Issue:
9(4), P. 250 - 250
Published: March 26, 2025
This
paper
presents
a
methodology
for
training
Deep
Learning
model
aimed
at
flight
management
tasks
in
fixed-wing
unmanned
aerial
vehicle
(UAV),
specifically
autopilot
control
and
GPS
prediction.
In
this
formulation,
sensor
data
the
most
recent
signal
are
first
processed
by
an
LSTM
to
produce
initial
coordinate
preliminary
estimate
is
then
merged
with
additional
inputs
passed
MLP,
which
replaces
conventional
algorithm
generating
commands
real-time
navigation.
The
approach
particularly
valuable
scenarios
where
aircraft
must
follow
predetermined
route—such
as
surveillance
operations—or
maintain
remote
ground
link
under
varying
availability.
study
focuses
on
Class
I
UAVs;
however,
proposed
can
be
adapted
larger
classes
(II
III)
adjusting
configurations
network
parameters.
To
collect
data,
small
was
instrumented
record
kinematic
inputs,
served
neural
network.
Despite
limited
suite
use
of
open-source
controller
(SpeedyBee),
flexibility
allows
easy
adaptation
more
complex
UAVs
equipped
sensors,
potentially
improving
prediction
accuracy.
performance
network,
implemented
PyTorch,
evaluated
comparing
its
predicted
actual
logs.
addition,
method
has
been
shown
robust
both
short
prolonged
outages,
it
relies
waypoint-based
navigation
along
previously
explored
routes,
ensuring
reliable
known
operational
contexts.
