Drones,
Год журнала:
2024,
Номер
8(10), С. 530 - 530
Опубликована: Сен. 28, 2024
With
the
increase
in
UAV
scale
and
mission
diversity,
trajectory
planning
systems
faces
more
complex
constraints,
which
are
often
conflicting
strongly
coupled,
placing
higher
demands
on
real-time
response
capabilities
of
system.
At
same
time,
conflicts
strong
coupling
pose
challenges
autonomous
decision-making
capability
system,
affecting
accuracy
efficiency
system
environments.
However,
recent
research
advances
addressing
these
issues
have
not
been
fully
summarized.
An
in-depth
exploration
constraint
handling
techniques
will
be
great
significance
to
development
large-scale
systems.
Therefore,
this
paper
aims
provide
a
comprehensive
overview
topic.
Firstly,
functions
application
scenarios
introduced
classified
detail
according
method,
realization
function
presence
or
absence
constraints.
Then,
described
detail,
focusing
priority
ranking
constraints
principles
their
fusion
transformation
methods.
importance
is
depth,
related
dynamic
adjustment
algorithms
introduced.
Finally,
future
directions
outlooked,
providing
references
for
fields
clustering
cooperative
flight.
Drones,
Год журнала:
2024,
Номер
8(5), С. 205 - 205
Опубликована: Май 16, 2024
Path
planning
is
one
of
the
most
essential
parts
autonomous
navigation.
Most
existing
works
are
based
on
strategy
adjusting
angles
for
planning.
However,
drones
susceptible
to
collisions
in
environments
with
densely
distributed
and
high-speed
obstacles,
which
poses
a
serious
threat
flight
safety.
To
handle
this
challenge,
we
propose
new
method
Multiple
Strategies
Avoiding
Obstacles
High
Speed
Density
(MSAO2H).
Firstly,
extend
obstacle
avoidance
decisions
into
angle
adjustment,
speed
clearance.
Hybrid
action
space
adopted
model
each
decision.
Secondly,
state
environment
constructed
provide
effective
features
learning
decision
parameters.
The
instant
reward
ultimate
designed
balance
efficiency
parameters
ability
explore
optimal
solutions.
Finally,
innovatively
introduced
interferometric
fluid
dynamics
system
parameterized
deep
Q-network
guide
Compared
other
algorithms,
proposed
has
high
success
rates
generates
high-quality
planned
paths.
It
can
meet
requirements
autonomously
paths
dynamic
environments.
The Aeronautical Journal,
Год журнала:
2025,
Номер
unknown, С. 1 - 14
Опубликована: Янв. 17, 2025
Abstract
Aiming
at
the
problems
of
poor
coordination
effect
and
low
positioning
accuracy
unmanned
aerial
vehicle
(UAV)
formation
cooperative
navigation
in
complex
environments,
an
adaptive
time-varying
factor
graph
framework
UAV
algorithm
is
proposed.
The
proposed
uses
to
describe
relationship
between
state
fleet
its
own
measurement
information
as
well
relative
information,
detects
each
moment
by
double-threshold
detection
method
update
model
current
moment.
And
robust
estimation
combined
with
graph,
weight
function
measurements
are
used
construction
nodes
for
adjustment
make
system
highly
robust.
simulation
results
show
that
realises
effective
fusion
airborne
multi-source
sensing
which
effectively
improves
accuracy.
Biomimetics,
Год журнала:
2025,
Номер
10(3), С. 168 - 168
Опубликована: Март 10, 2025
To
address
the
challenges
of
low
optimization
efficiency
and
premature
convergence
in
existing
algorithms
for
unmanned
aerial
vehicle
(UAV)
3D
path
planning
under
complex
operational
constraints,
this
study
proposes
an
enhanced
honey
badger
algorithm
(LRMHBA).
First,
a
three-dimensional
terrain
model
incorporating
threat
sources
UAV
constraints
is
constructed
to
reflect
actual
environment.
Second,
LRMHBA
improves
global
search
by
optimizing
initial
population
distribution
through
integration
Latin
hypercube
sampling
elite
strategy.
Subsequently,
stochastic
perturbation
mechanism
introduced
facilitate
escape
from
local
optima.
Furthermore,
adapt
evolving
exploration
requirements
during
process,
employs
differential
mutation
strategy
tailored
populations
with
different
fitness
values,
utilizing
individuals
initialization
stage
guide
process.
This
design
forms
two-population
cooperative
that
enhances
balance
between
exploitation,
thereby
improving
accuracy.
Experimental
evaluations
on
CEC2017
benchmark
suite
demonstrate
superiority
over
11
comparison
algorithms.
In
task,
consistently
generated
shortest
average
across
three
obstacle
simulation
scenarios
varying
complexity,
achieving
highest
rank
Friedman
test.
Concurrency and Computation Practice and Experience,
Год журнала:
2025,
Номер
37(9-11)
Опубликована: Апрель 9, 2025
ABSTRACT
This
research
delves
into
the
intricacies
of
designing
trajectories
for
unmanned
aerial
vehicles
(UAVs)
within
a
multi‐UAV
system,
specifically
addressing
challenges
presented
during
simultaneous
rescue
operations
in
neighboring
states.
The
unique
scenario
introduces
potential
risk
UAVs
from
one
state
intersecting
with
those
others,
leading
to
communication
issues
and
looming
threat
collisions.
These
collisions
not
only
cause
delays
emergency
but
also
result
additional
costs
repairing
damaged
UAV
components.
In
response
this
critical
challenge,
study
proposes
an
innovative
approach
utilizing
Genetic
Algorithms
facilitate
collision
avoidance
environment,
tailored
explicitly
disaster
mitigation
scenarios.
technique
is
efficient
solution
enhance
safety
effectiveness
relief
efforts.
proposed
trajectory
planning
method
uses
genetic
algorithm,
fitness
function
strategically
designed
optimize
two
pivotal
objectives:
utility
(maximizing
number
people
saved
postdisaster)
(minimizing
conflicts
between
multiple
as
they
navigate
predetermined
paths).
overarching
goal
strike
balance,
aiming
maximize
while
concurrently
minimizing
By
adopting
approach,
significantly
contributes
advancing
field
strategies,
enhancing
overall
efficiency
systems
complex
dynamic
environments.
addresses
immediate
posed
by
underscores
importance
optimizing
achieve
maximum
postdisaster
