Many
real-world
optimization
problems
can
be
formulated
as
a
kind
of
constrained
multi-objective
(CMOPs).
The
main
difficulty
in
solving
these
is
to
take
feasibility,
convergence
and
diversity
into
account
simultaneously.
To
address
this
issue,
paper
proposes
push
pull
search
algorithm
based
on
early
followed
by
(PPS-CFD).
proposed
composed
three
different
stages,
each
respectively
focusing
convergence,
feasibility.
In
the
first
stage,
population
rapidly
converges
unconstrained
Pareto
front
(UPF)
$M$
directions,
where
number
objectives
CMOPs.
second
further
UPF
meanwhile
its
enhanced.
last
constraints
are
taken
from
(CPF).
addition,
strategy
objective
space
division
at
two
stages.
Finally,
PPS-CFD
tested
fourteen
benchmark
problems,
compared
with
other
six
algorithms,
demonstrate
superiority.
Computer-Aided Civil and Infrastructure Engineering,
Journal Year:
2023,
Volume and Issue:
39(12), P. 1743 - 1765
Published: Oct. 3, 2023
Abstract
Cracks
are
the
most
common
damage
type
on
pavement
surface.
Usually,
cracks,
especially
small
difficult
to
be
accurately
identified
due
background
interference.
Accurate
and
fast
automatic
road
crack
detection
play
a
vital
role
in
assessing
conditions.
Thus,
this
paper
proposes
an
efficient
lightweight
encoder–decoder
network
for
automatically
detecting
cracks
at
pixel
level.
Taking
advantage
of
novel
architecture
integrating
new
hybrid
attention
blocks
residual
(RBs),
proposed
can
achieve
extremely
model
with
more
accurate
pixels.
An
image
dataset
consisting
789
images
acquired
by
self‐designed
mobile
robot
is
built
utilized
train
evaluate
network.
Comprehensive
experiments
demonstrate
that
performs
better
than
state‐of‐the‐art
methods
self‐built
as
well
three
other
public
datasets
(CamCrack789,
Crack500,
CFD,
DeepCrack237),
achieving
F1
scores
94.94%,
82.95%,
95.74%,
92.51%,
respectively.
Additionally,
ablation
studies
validate
effectiveness
RBs
mechanisms.
By
introducing
depth‐wise
separable
convolutions,
even
version
created,
which
has
comparable
performance
achieves
fastest
inference
speed
parameter
size
only
0.57
M.
The
developed
system
effectively
detect
real
scenarios
25
frames
per
second.
Machines,
Journal Year:
2025,
Volume and Issue:
13(1), P. 55 - 55
Published: Jan. 14, 2025
This
review
summarizes
the
important
properties
required
for
applying
soft
grippers
to
agricultural
harvesting,
focusing
on
their
actuation
methods
and
structural
types.
The
purpose
of
is
address
challenges
limited
load
capacity
stiffness,
which
significantly
hinder
broader
application
in
agriculture.
paper
examines
research
progress
variable
stiffness
over
past
five
years.
We
categorize
various
techniques
analyze
advantages
disadvantages
enhancing
capacity,
dexterity,
degree
integration,
responsiveness,
energy
consumption
grippers.
applicability
limitations
these
context
harvesting
are
also
discussed.
concludes
that
combined
material
technology
with
a
motor
claw
structure
better
suited
operations
woody
crops
(e.g.,
apples,
citrus)
herbaceous
tomatoes,
cucumbers)
unstructured
environments.
Applied Sciences,
Journal Year:
2023,
Volume and Issue:
13(19), P. 10920 - 10920
Published: Oct. 2, 2023
This
study
addresses
dynamic
task
allocation
challenges
in
coordinated
surveillance
involving
multiple
unmanned
aerial
vehicles
(UAVs).
A
significant
concern
is
the
increased
UAV
flight
distance
resulting
from
assignment
of
new
missions,
leading
to
decreased
reconnaissance
efficiency.
To
tackle
this
issue,
we
introduce
a
collaborative
multi-target
and
multi-UAV
scheme.
Initially,
multitasking
constrained
multi-objective
optimization
framework
(MTCOM)
employed
optimize
time
static
scenarios.
Subsequently,
case
emergency,
iteratively
refine
outcomes
through
an
enhanced
auction-based
distributed
algorithm,
effectively
reducing
costs
response
withdrawal,
or
damage.
Simulation
results
demonstrate
efficacy
our
proposed
cooperative
scheme
resolving
issues.
Additionally,
approach
achieves
5.4%
reduction
compared
traditional
methods.
The
main
contribution
paper
consider
scenario
model
damage
emergence
areas.
Then
propose
innovative
address
issue
and,
finally,
conduct
experimental
simulations
verify
effectiveness
algorithm.
This
paper
tackles
the
challenge
of
collaborative
control
in
multi-agent
systems
by
introducing
a
motion
strategy
based
on
hierarchical
gene
regulatory
network
(GRN)
model.
At
GRN
model's
upper
layer,
we
define
an
influence
area
for
each
agent,
aiding
them
making
autonomous
decisions
through
dynamics
these
areas.
The
lower
layer
incorporates
three
core
behavioral
principles:
obstacle
avoidance,
aggregation,
and
co-directional
movement,
enabling
self-organized,
coordinated
movement
settings.
effectiveness
our
approach
is
validated
experimental
simulations
two
distinct
environments:
forest
channel.
results
demonstrate
superiority
proposed
method
environments.
