IEEE Transactions on Vehicular Technology,
Journal Year:
2023,
Volume and Issue:
73(1), P. 1175 - 1190
Published: Sept. 22, 2023
This
article
considers
an
internet
of
vehicles
(IoV)
network,
where
multi-access
edge
computing
(MAEC)
servers
are
deployed
at
base
stations
(BSs)
aided
by
multiple
reconfigurable
intelligent
surfaces
(RISs)
for
both
uplink
and
downlink
transmission.
An
task
offloading
methodology
is
designed
to
optimize
the
resource
allocation
scheme
in
vehicular
network
which
based
on
state
criticality
priority
size
tasks.
We
then
develop
a
multi-agent
deep
reinforcement
learning
(MA-DRL)
framework
using
Markov
game
optimizing
decision
strategy.
The
proposed
algorithm
maximizes
mean
utility
IoV
improves
communication
quality.
Extensive
numerical
results
were
performed
that
demonstrate
RIS-assisted
MA-DRL
achieves
higher
than
current
state-of-the
art
networks
(not
RISs)
other
baseline
DRL
algorithms,
namely
soft
actor-critic
(SAC),
deterministic
policy
gradient
(DDPG),
twin
delayed
DDPG
(TD3).
method
data
rate
tasks,
reduces
delay
ensures
percentage
offloaded
tasks
completed
compared
DRL-based
non-RIS-assisted
frameworks.
IEEE Access,
Journal Year:
2022,
Volume and Issue:
10, P. 71481 - 71495
Published: Jan. 1, 2022
Multi-Access
Edge
Computing
(MEC)
is
a
standardized
architecture
that
enables
cloud
computing
capabilities
at
the
edge
of
heterogeneous
networks.
The
concept
to
reduce
network
congestion
by
running
applications
and
services
closer
end-users.
MEC
designed
be
implemented
key
locations
on
edge,
including
co-location
with
cellular
base
stations.
aims
facilitate
computation
intensive
delay
sensitive
applications,
such
as
vehicular
networks,
face
recognition,
augmented
reality
virtual
reality.
service
requirements
for
are
stochastic
time
varying.
Coupled
advances
in
artificial
intelligence,
vast
number
offloading
approaches
have
been
developed
based
intelligent
algorithms.
This
article
provides
comprehensive
review
critical
issues,
metrics
future
directions.
Sensors,
Journal Year:
2022,
Volume and Issue:
22(21), P. 8463 - 8463
Published: Nov. 3, 2022
When
it
comes
to
some
essential
abilities
of
autonomous
ground
vehicles
(AGV),
detection
is
one
them.
In
order
safely
navigate
through
any
known
or
unknown
environment,
AGV
must
be
able
detect
important
elements
on
the
path.
Detection
applicable
both
on-road
and
off-road,
but
they
are
much
different
in
each
environment.
The
key
environment
that
identify
drivable
pathway
whether
there
obstacles
around
it.
Many
works
have
been
published
focusing
components
various
ways.
this
paper,
a
survey
most
recent
advancements
methods
intended
specifically
for
off-road
has
presented.
For
this,
we
divided
literature
into
three
major
groups:
positive
negative
obstacles.
Each
portion
further
multiple
categories
based
technology
used,
example,
single
sensor-based,
how
data
analyzed.
Furthermore,
added
critical
findings
technology,
challenges
associated
with
possible
future
directions.
Authors
believe
work
will
help
reader
finding
who
doing
similar
works.
IEEE Transactions on Intelligent Transportation Systems,
Journal Year:
2023,
Volume and Issue:
25(3), P. 2522 - 2533
Published: Oct. 27, 2023
The
continuous
evolution
of
cellular
networks
has
resulted
in
the
rapid
increase
both
mobile
applications
and
devices
Internet
Vehicles.
introduction
multi-access
edge
computing
method
makes
it
possible
for
vehicles
remote
areas
to
offload
their
computational
tasks,
which
can
effectively
relieve
pressure
local
reduce
delay
as
well.
Tasks
offloading
multi-user
is
a
resource
competition
problem,
especially
dynamic
environments,
difficult
be
solved
by
traditional
algorithms.
In
this
article,
we
propose
two-layer
hybrid
system
with
computing,
providing
convenient
services
vehicle
users
dual
scenarios
task
generation
mobility.
queuing
situations
are
considered
comprehensively
formulated
optimization
proposed
deep
deterministic
policy
gradient-based
computation
algorithm.
process
tasks
transformed
into
Markov
decision
obtain
strategy.
Simulation
results
demonstrate
performance
advantages
two-tier
architecture.
Compared
random
offloading,
Q
network-based
algorithm
article
gains
highest
average
reward
tasks.
Besides
that,
numerical
also
prove
that
our
lowest
under
different
capabilities
servers.
IEEE Transactions on Vehicular Technology,
Journal Year:
2023,
Volume and Issue:
73(1), P. 1175 - 1190
Published: Sept. 22, 2023
This
article
considers
an
internet
of
vehicles
(IoV)
network,
where
multi-access
edge
computing
(MAEC)
servers
are
deployed
at
base
stations
(BSs)
aided
by
multiple
reconfigurable
intelligent
surfaces
(RISs)
for
both
uplink
and
downlink
transmission.
An
task
offloading
methodology
is
designed
to
optimize
the
resource
allocation
scheme
in
vehicular
network
which
based
on
state
criticality
priority
size
tasks.
We
then
develop
a
multi-agent
deep
reinforcement
learning
(MA-DRL)
framework
using
Markov
game
optimizing
decision
strategy.
The
proposed
algorithm
maximizes
mean
utility
IoV
improves
communication
quality.
Extensive
numerical
results
were
performed
that
demonstrate
RIS-assisted
MA-DRL
achieves
higher
than
current
state-of-the
art
networks
(not
RISs)
other
baseline
DRL
algorithms,
namely
soft
actor-critic
(SAC),
deterministic
policy
gradient
(DDPG),
twin
delayed
DDPG
(TD3).
method
data
rate
tasks,
reduces
delay
ensures
percentage
offloaded
tasks
completed
compared
DRL-based
non-RIS-assisted
frameworks.
