I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Ro
bo
t
ics a
nd
Aut
o
m
a
t
io
n (
I
J
RA)
Vo
l.
1
0
,
No
.
3
,
Sep
tem
b
er
2
0
2
1
,
p
p
.
1
6
1
~
1
6
9
I
SS
N:
2722
-
2586
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
r
a
.
v
1
0
i
3
.
pp
1
6
1
-
169
161
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
a
.
ia
esco
r
e.
co
m
Dev
elo
p
m
e
nt
o
f
a dy
na
m
ic
int
el
lig
ent
recog
nition
sy
ste
m
f
o
r
a
real
-
ti
m
e
t
ra
c
k
in
g
robo
t
T
ha
ir
Ali Sa
li
h,
M
o
ha
m
m
e
d
T
a
la
l G
ha
za
l,
Z
a
id
G
ha
ni
m
M
o
ha
m
m
e
d
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter E
n
g
.
T
e
c
h
n
o
l
o
g
y
,
Tec
h
n
ica
l
En
g
.
Co
ll
e
g
e
/
M
o
s
u
l,
N
o
rth
e
r
n
T
e
c
h
n
ica
l
Un
i
v
e
rsit
y
,
M
o
su
l,
Ira
q
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
1
1
,
2
0
2
0
R
ev
i
s
ed
A
p
r
2
3
,
2
0
2
1
A
cc
ep
ted
Ma
y
3
1
,
2
0
2
1
No
w
a
d
a
y
s,
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
c
o
m
p
u
ter v
isio
n
tec
h
n
o
lo
g
y
h
e
lp
to
o
v
e
rc
o
m
e
trac
k
a
n
d
id
e
n
ti
f
y
h
u
m
a
n
s
w
it
h
in
a
lo
c
a
ti
o
n
in
t
h
e
c
o
m
p
lex
e
n
v
iro
n
m
e
n
t
th
ro
u
g
h
m
o
b
il
e
ro
b
o
ts,
w
h
ich
g
iv
e
s
th
e
m
o
ti
v
a
ti
o
n
to
p
re
se
n
ts
a
v
i
sio
n
-
b
a
se
d
a
p
p
ro
a
c
h
to
a
m
o
b
il
e
se
c
u
rit
y
ro
b
o
t
.
T
h
e
p
ro
p
o
se
d
sy
st
e
m
u
ti
li
z
e
s
a
w
irel
e
ss
c
a
m
e
ra
to
d
e
tec
t
th
e
o
b
jec
ts
in
t
h
e
f
ield
o
f
ro
b
o
t
v
iew
.
P
r
in
c
ip
le
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
(P
CA
)
a
lg
o
rit
h
m
a
n
d
f
il
ters
a
re
u
se
d
to
im
p
le
m
e
n
t
a
n
d
d
e
m
o
n
stra
te
th
e
p
r
o
c
e
ss
o
f
th
e
ima
g
e
s.
T
h
is
g
iv
e
s
th
e
d
e
sig
n
e
d
s
y
ste
m
th
e
a
b
il
it
y
to
re
c
o
g
n
ize
o
b
jec
ts
in
d
e
p
e
n
d
e
n
tl
y
f
ro
m
c
u
rre
n
t
li
g
h
t
c
o
n
d
i
ti
o
n
s.
F
ra
m
e
trac
k
in
g
in
th
e
im
a
g
e
s
u
se
s
a
n
a
tt
e
n
ti
o
n
sy
ste
m
to
g
e
t
a
n
e
sti
m
a
te
o
f
th
e
p
o
siti
o
n
o
f
a
p
e
rso
n
.
T
h
is
e
sti
m
a
te
h
e
lp
s
th
e
a
p
p
l
ied
c
a
m
e
ra
to
i
d
e
n
ti
f
y
o
b
jec
ts
w
it
h
c
h
a
n
g
in
g
b
a
c
k
g
ro
u
n
d
li
g
h
ti
n
g
c
o
n
d
it
i
o
n
s
s
u
c
h
a
s
a
f
ire
in
sid
e
a
b
u
il
d
in
g
.
By
u
sin
g
th
is
e
sti
m
a
te,
th
e
a
p
p
li
e
d
c
a
m
e
ra
c
o
u
ld
id
e
n
ti
fy
o
b
jec
ts
w
it
h
c
h
a
n
g
in
g
b
a
c
k
g
ro
u
n
d
li
g
h
ti
n
g
c
o
n
d
it
io
n
s
su
c
h
a
s
a
f
ire
in
sid
e
p
re
m
ise
s.
T
h
e
s
y
ste
m
h
a
s
b
e
e
n
tes
ted
u
sin
g
th
e
M
A
TL
AB
e
n
v
iro
n
m
e
n
t
,
a
n
d
th
e
e
m
p
iri
c
a
l
p
e
rf
o
r
m
a
n
c
e
e
x
p
lain
s
th
e
e
ff
ici
e
n
c
y
a
n
d
stro
n
g
n
e
ss
o
f
th
e
su
g
g
e
ste
d
d
e
v
ice
.
K
ey
w
o
r
d
s
:
Mu
lti
-
s
e
n
s
o
r
s
y
s
te
m
s
Secu
r
it
y
m
o
n
ito
r
in
g
Su
r
v
e
illa
n
ce
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
T
h
air
A
li Sali
h
T
ec
h
n
ical
E
n
g
in
ee
r
i
n
g
C
o
lle
g
e/De
p
ar
t
m
en
t o
f
C
o
m
p
u
ter
E
n
g
in
ee
r
i
n
g
No
r
th
er
n
T
ec
h
n
ical
U
n
i
v
er
s
it
y
Mo
s
u
l,
I
r
aq
E
m
ail: t
h
air
ali5
9
@
n
t
u
.
ed
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
u
tili
za
tio
n
o
f
n
e
w
f
an
g
le
d
tech
n
o
lo
g
ies
in
m
ilit
ar
y
,
s
ec
u
r
it
y
,
an
d
s
u
r
v
eilla
n
ce
h
as
b
ec
o
m
e
n
o
te
w
o
r
t
h
y
ap
p
licatio
n
s
f
o
r
r
e
s
ea
r
ch
er
s
i
n
t
h
e
d
o
m
a
in
o
f
r
o
b
o
tics
,
w
h
er
e
t
h
e
e
m
p
lo
y
o
f
tec
h
n
iq
u
es
to
p
er
f
o
r
m
s
ec
u
r
it
y
a
n
d
co
n
tr
o
l
task
s
s
av
es
ef
f
o
r
t
an
d
co
s
ts
.
T
h
e
y
h
a
v
e
p
r
o
v
ed
t
o
p
e
r
f
o
r
m
t
h
ese
es
s
en
tia
l
p
u
r
p
o
s
es
to
h
ig
h
p
r
ec
is
io
n
,
h
o
w
ev
er
,
t
h
is
m
u
c
h
d
ep
en
d
s
o
n
t
h
e
tech
n
o
l
o
g
y
o
f
i
m
a
g
e
an
d
v
id
eo
p
r
o
ce
s
s
i
n
g
,
tr
ac
k
in
g
o
f
m
o
v
i
n
g
o
b
j
ec
ts
,
an
d
th
e
s
y
s
t
e
m
’
s
ab
ilit
y
to
r
ec
o
g
n
ize
p
eo
p
le.
T
h
e
d
ev
elo
p
m
e
n
t
o
f
r
ec
o
g
n
itio
n
alg
o
r
it
h
m
s
u
s
i
n
g
M
A
T
L
A
B
s
o
f
t
w
ar
e
h
a
s
b
ee
n
an
es
s
en
tial
to
o
l
to
i
n
cr
ea
s
e
t
h
e
ef
f
icie
n
c
y
o
f
o
b
j
ec
t
d
etec
tio
n
an
d
r
ec
o
g
n
itio
n
.
Fu
r
t
h
er
m
o
r
e,
th
e
av
ailab
ilit
y
o
f
s
m
all
an
d
ch
ea
p
h
ar
d
w
ar
e
d
ev
elo
p
m
en
t
b
o
ar
d
s
s
u
ch
a
s
A
r
d
u
in
o
an
d
R
asp
b
er
r
y
P
i
h
as
ass
is
te
d
in
cr
ea
tin
g
s
u
r
v
eilla
n
ce
s
y
s
te
m
s
t
h
at
h
a
v
e
lo
w
p
o
w
er
co
n
s
u
m
p
t
io
n
an
d
f
as
t
p
r
o
ce
s
s
in
g
ab
ilit
y
[
1
]
.
T
h
e
s
elf
-
au
to
n
o
m
o
u
s
n
av
i
g
atio
n
r
o
b
o
t
aim
s
to
r
ea
ch
w
a
y
p
o
in
ts
s
p
ec
i
f
ied
b
y
co
o
r
d
in
ates
in
a
r
o
u
te
s
tar
ti
n
g
f
r
o
m
a
s
tar
t
p
o
in
t
i
n
th
e
en
v
ir
o
n
m
e
n
t.
W
h
e
n
t
h
e
r
o
b
o
t
n
av
ig
ate
s
,
it
w
il
l
en
co
u
n
ter
o
b
s
tacle
s
o
r
ter
r
ain
s
th
at
w
ill
h
i
n
d
er
m
o
v
e
m
en
t
to
th
e
en
d
p
o
in
t,
w
h
ic
h
it
n
ee
d
s
to
av
o
id
it
[
2
]
.
T
h
e
e
m
p
lo
y
o
f
r
o
b
o
ts
co
n
s
id
er
ab
ly
in
cr
ea
s
es
t
h
e
p
o
s
s
ib
ilit
y
o
f
m
o
n
ito
r
i
n
g
d
e
v
ices,
w
h
ic
h
h
a
v
e
ev
o
l
v
ed
f
r
o
m
a
tr
ad
itio
n
al
f
u
n
c
tio
n
,
w
h
er
eb
y
th
e
d
ev
ice
o
n
l
y
d
etec
ts
i
n
cid
e
n
ts
a
n
d
ac
tiv
ate
alar
m
s
,
to
an
en
er
g
etic
co
m
p
le
x
co
o
p
er
ativ
e
o
b
s
er
v
atio
n
r
o
b
o
t,
w
h
ic
h
ca
n
m
ee
t
w
i
th
its
en
v
ir
o
n
m
en
t
an
d
co
llab
o
r
ate
w
i
th
p
eo
p
le
o
r
w
it
h
o
th
er
r
o
b
o
ts
[
3
]
.
A
n
ex
a
m
p
le
o
f
a
s
ec
u
r
it
y
r
o
b
o
t
d
ev
elo
p
e
d
at
th
e
U
n
iv
er
s
it
y
o
f
W
aik
a
to
,
Ha
m
ilto
n
,
Ne
w
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2722
-
2586
I
A
E
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
0
,
No
.
3
,
Sep
tem
b
er
2
0
2
1
:
1
6
1
–
169
162
Z
ea
la
n
d
n
a
m
ed
“
M
AR
VI
N
“
(
m
o
b
ile
a
u
to
n
o
m
o
u
s
r
o
b
o
tic
v
eh
icle
f
o
r
in
d
o
o
r
n
av
i
g
atio
n
)
h
as
b
ee
n
d
e
v
elo
p
ed
to
ac
t
as
a
s
ec
u
r
it
y
a
g
en
t
in
s
i
d
e
a
b
u
ild
in
g
.
I
n
o
r
d
er
to
m
e
et
w
i
th
h
u
m
a
n
n
ee
d
s
,
th
e
r
o
b
o
t
is
p
r
o
v
id
ed
w
it
h
sp
ee
ch
r
ec
o
g
n
i
tio
n
a
n
d
s
p
ee
ch
s
y
n
t
h
es
is
s
o
f
t
w
ar
e,
also
,
it
ca
n
co
n
v
e
y
e
m
o
tio
n
al
s
tates,
v
er
b
all
y
,
an
d
n
o
n
-
v
er
b
all
y
[
4
]
.
Milella
et
a
l.
a
p
r
o
ce
d
u
r
e
f
o
r
tr
ac
k
in
g
p
eo
p
l
e
in
t
h
e
i
n
d
o
o
r
m
ed
i
u
m
e
m
p
lo
y
s
a
m
u
lti
-
s
e
n
s
o
r
p
o
r
tab
le
p
latf
o
r
m
ar
e
p
r
esen
t
ed
[
5
]
.
I
t
u
s
ed
f
o
r
th
e
ap
p
r
o
ac
h
is
i
n
Hu
m
a
n
-
Au
g
m
en
ted
Ma
p
p
in
g
(
H
A
M)
.
P
ao
la,
et
a
l
.
in
2
0
1
0
s
u
g
g
e
s
te
d
an
elig
ib
le
d
ev
ice
i
n
d
ep
en
d
en
tl
y
p
u
b
lic
-
o
b
j
ec
tiv
e
m
is
s
io
n
s
an
d
co
m
p
o
u
n
d
ed
m
o
n
ito
r
i
n
g
m
at
ter
to
g
et
h
er
.
I
t
is
T
u
r
n
s
o
u
t
th
at
th
e
s
u
g
g
est
ed
r
o
b
o
tic
m
o
n
ito
r
in
g
p
r
o
j
ec
t
ef
f
ec
tiv
e
l
y
s
ev
er
a
l
r
eq
u
ests
is
s
u
e
s
co
n
ce
r
n
i
n
g
cli
m
ate
m
ap
p
i
n
g
,
an
d
i
n
d
ep
en
d
en
t
s
h
ip
p
in
g
,
as
w
e
ll
as
m
o
n
ito
r
in
g
d
u
t
ies,
s
u
ch
as
p
r
o
s
p
ec
t
tr
ea
t
m
en
t
to
r
ev
ea
l
d
eser
ted
o
r
ex
tr
ac
t
o
b
j
ec
ts
an
d
d
etec
t
an
d
f
o
llo
w
ed
p
eo
p
le
[
6
]
.
Salh
a
n
d
Na
y
e
f
[
7
]
,
a
s
m
ar
t
s
a
f
et
y
r
o
b
o
t
u
tili
z
es
f
ield
p
r
o
g
r
a
m
m
ab
le
an
a
lo
g
ar
r
ay
(
FP
AA
)
f
o
r
cr
ash
-
f
r
ee
m
o
v
e
m
e
n
t,
p
r
in
cip
le
co
m
p
o
n
e
n
t
a
n
al
y
s
i
s
(
P
C
A
)
a
n
d
lin
ea
r
d
is
cr
i
m
i
n
an
t
a
n
al
y
s
is
(
L
D
A
)
f
o
r
ch
ar
ac
ter
is
tic
e
x
tr
ac
tio
n
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
clas
s
i
f
ier
f
o
r
f
ac
e
-
r
ec
o
g
n
itio
n
a
n
d
a
g
as
s
e
n
s
o
r
(
MQ
4
)
f
o
r
d
is
co
v
er
in
g
g
as
lea
k
ag
e
s
.
T
h
is
r
o
b
o
t
is
u
s
ed
to
ca
p
tu
r
e
d
au
d
io
-
v
is
u
al
d
ata.
B
ah
r
u
d
in
et
a
l
.
p
r
esen
t
in
th
eir
p
ap
er
s
ev
er
al
s
t
u
d
ies
an
d
m
an
y
m
o
d
els
o
f
s
ec
u
r
it
y
an
d
s
u
r
v
eilla
n
ce
s
y
s
te
m
s
h
av
e
b
ee
n
estab
lis
h
ed
u
s
in
g
n
u
m
er
o
u
s
p
latf
o
r
m
s
.
Su
c
h
as
th
e
d
esi
g
n
o
f
a
f
ir
e
alar
m
s
y
s
t
e
m
u
s
i
n
g
R
asp
b
er
r
y
P
i
Mo
d
el
-
B
s
in
g
le
-
b
o
ar
d
co
m
p
u
ter
,
th
o
s
e
s
y
s
te
m
s
ca
n
aler
t
th
e
s
ec
u
r
it
y
m
a
n
i
m
m
ed
iatel
y
w
h
en
a
n
y
p
r
o
b
le
m
o
cc
u
r
s
a
n
d
r
eq
u
est
f
o
r
co
n
s
e
n
t
f
r
o
m
t
h
e
s
ec
u
r
i
t
y
m
an
to
in
f
o
r
m
th
e
f
ir
e
f
ig
h
ter
.
T
h
e
y
u
s
e
t
h
e
P
HP
p
r
o
g
r
am
m
i
n
g
la
n
g
u
a
g
e
to
d
esig
n
a
w
eb
p
ag
e
f
o
r
d
is
p
lay
in
g
t
h
e
w
ar
n
in
g
m
es
s
ag
e
s
[
8
]
.
A
h
u
m
a
n
tr
ac
k
i
n
g
ab
ilit
y
p
r
o
g
r
a
m
m
ed
o
n
a
r
o
b
o
t
is
a
h
elp
to
id
en
tify
p
eo
p
le
an
d
s
ev
er
a
l
m
et
h
o
d
s
h
av
e
b
ee
n
d
ev
elo
p
ed
.
On
e
s
u
ch
m
et
h
o
d
p
r
esen
t
b
y
A
h
m
ad
an
d
Yo
u
s
s
e
f
[
9
]
en
ab
les
th
e
r
o
b
o
t
to
tr
ac
k
th
e
ce
n
ter
o
f
m
a
s
s
o
f
a
h
u
m
an
s
k
eleto
n
u
s
in
g
a
3
D
s
en
s
o
r
f
r
o
m
Mic
r
o
s
o
f
t
(
Kin
ec
t)
.
I
t
ca
n
d
etec
t
a
h
u
m
a
n
m
o
v
e
m
e
n
t
i
n
it
s
v
ici
n
it
y
an
d
av
o
id
p
eo
p
le
an
d
o
b
s
tacle
s
i
n
it
s
p
ath
.
W
a
n
g
et
a
l
.
[
1
0
]
s
h
o
w
s
a
s
m
ar
t
ca
r
d
b
ased
o
n
A
r
d
u
i
n
o
,
w
h
ic
h
is
a
n
in
te
g
r
al
p
ar
t
o
f
th
i
s
w
o
r
k
,
i
s
in
s
p
ir
ed
b
y
ca
r
co
n
tr
o
l
s
y
s
t
e
m
s
d
esi
g
n
ed
u
s
i
n
g
t
w
o
m
e
th
o
d
s
,
th
e
f
ir
s
t
is
w
ir
e
less
l
y
u
s
in
g
a
s
m
ar
tp
h
o
n
e
v
ia
B
lu
eto
o
th
an
d
th
e
s
ec
o
n
d
is
b
y
t
h
e
g
r
av
itatio
n
a
l
s
en
s
o
r
(
th
e
ac
ce
ler
o
m
eter
s
en
s
o
r
)
b
u
ilt
-
i
n
to
t
h
e
An
d
r
o
id
s
m
ar
tp
h
o
n
e.
B
alo
g
h
[
1
1
]
,
a
m
o
d
er
n
r
o
b
o
t,
ca
lled
A
cr
o
b
at
w
a
s
ex
a
m
i
n
ed
an
d
esti
m
ated
at
s
o
m
e
d
if
f
er
en
t
ca
s
es.
A
r
o
b
o
tic
ca
p
ital
lect
u
r
e
f
o
r
s
tu
d
en
ts
is
p
r
o
v
id
ed
b
y
th
e
Au
to
m
o
tiv
e
s
ec
tio
n
o
f
t
h
e
s
tu
d
y
.
T
h
e
m
a
j
o
r
aim
w
as
to
g
i
v
e
th
e
m
a
co
n
ce
p
t
o
f
m
o
b
ile
r
o
b
o
ts
.
T
h
r
o
u
g
h
t
w
o
s
es
s
io
n
s
s
tu
d
e
n
ts
w
er
e
eli
g
ib
le
to
p
r
o
g
r
a
m
b
asic
m
o
v
e
m
e
n
ts
a
n
d
i
n
ter
ac
tiv
e
t
h
e
b
eh
a
v
io
r
o
f
th
e
r
o
b
o
ts
.
T
h
is
p
ap
er
ch
a
r
ac
ter
izes
th
e
h
u
m
an
ac
t
iv
i
t
y
h
o
ld
an
al
y
s
es
s
y
s
te
m
o
n
a
C
A
N
b
u
s
b
asis
.
T
h
e
m
o
d
el
e
m
b
r
ac
e
s
a
d
is
tr
ib
u
ted
s
y
s
te
m
ar
ch
itect
u
r
e,
to
co
m
p
ile
in
f
o
r
m
atio
n
i
n
cl
u
s
i
v
e
p
lan
tar
ef
f
o
r
t,
ex
ter
n
al
s
tr
u
ct
u
r
e
co
r
n
er
,
a
n
d
s
u
p
p
l
y
i
n
f
o
r
m
atio
n
b
ac
k
i
n
g
f
o
r
f
o
llo
w
i
n
g
m
o
v
e
m
e
n
t
r
ec
o
g
n
itio
n
a
lg
o
r
ith
m
.
I
t
h
a
s
ea
s
y
m
ea
s
u
r
e
m
e
n
t
p
r
o
ce
d
u
r
es
an
d
m
i
n
i
m
al
s
u
b
j
ec
tio
n
o
n
t
h
e
m
e
asu
r
e
m
en
t
m
ilie
u
.
T
h
is
s
y
s
te
m
m
ee
t
s
t
h
e
n
ee
d
s
o
f
p
er
ce
iv
in
g
h
u
m
a
n
m
o
v
e
m
en
t
w
h
e
n
co
n
tr
o
lli
n
g
t
h
e
r
eh
ab
ilit
atio
n
e
x
ter
io
r
s
tr
u
c
tu
r
e
[
12
]
.
T
h
is
p
ap
er
ch
ar
ac
ter
izes t
h
e
h
u
m
a
n
ac
tiv
i
t
y
h
o
ld
an
al
y
s
es
s
y
s
te
m
o
n
a
C
A
N
b
u
s
b
as
is
.
T
h
e
m
o
d
el
e
m
b
r
ac
e
s
a
d
i
s
tr
ib
u
ted
s
y
s
te
m
ar
ch
itect
u
r
e,
w
h
ich
ca
n
co
m
p
ile
d
ata
i
n
cl
u
s
i
v
e
p
la
n
t
ar
ef
f
o
r
t,
ex
ter
n
al
s
tr
u
ct
u
r
e
a
n
g
le,
an
d
s
u
p
p
l
y
d
ata
s
u
p
p
o
r
t
f
o
r
f
o
llo
w
i
n
g
m
o
tio
n
r
ec
o
g
n
it
io
n
al
g
o
r
ith
m
.
I
t
h
as
a
s
i
m
p
le
m
ea
s
u
r
e
m
e
n
t
p
r
o
ce
s
s
an
d
m
i
n
i
m
al
s
u
b
j
ec
tio
n
o
n
t
h
e
m
ea
s
u
r
e
m
e
n
t
e
n
v
ir
o
n
m
en
t.
T
h
is
s
y
s
te
m
m
ee
ts
t
h
e
n
ee
d
s
o
f
p
er
ce
iv
i
n
g
h
u
m
a
n
m
o
v
e
m
e
n
t
w
h
e
n
co
n
tr
o
llin
g
t
h
e
r
eh
ab
ilit
atio
n
ex
ter
io
r
s
tr
u
c
tu
r
e
[
1
3
]
.
T
h
e
p
r
im
ar
y
o
b
j
ec
tiv
e
o
f
th
e
s
ec
u
r
it
y
s
u
r
v
eil
lan
c
e
s
y
s
te
m
p
r
o
p
o
s
ed
in
th
is
p
ap
er
is
to
p
r
o
v
id
e
a
r
eliab
le
n
atu
r
al
tech
n
iq
u
e
f
o
r
a
s
el
f
-
a
u
to
n
o
m
o
u
s
r
o
b
o
t
to
n
av
i
g
ate
a
n
d
d
etec
t
m
o
v
i
n
g
o
b
j
ec
ts
,
av
o
id
o
b
s
tacle
s
,
an
d
d
etec
t
s
m
o
k
e.
T
o
d
er
e
an
et
a
l
.
[
1
4
]
p
r
o
p
o
s
itio
n
a
m
o
d
el
t
h
at
d
is
p
la
y
s
a
p
r
o
ce
s
s
to
p
er
f
o
r
m
a
r
o
b
o
tic
d
ev
ice
w
ith
a
d
ee
p
lear
n
in
g
-
b
ased
tar
g
et
d
is
co
v
er
ed
in
an
e
m
u
latio
n
a
m
b
ian
ce
.
T
h
e
e
m
u
latio
n
a
m
b
ia
n
ce
is
d
ev
elo
p
ed
in
Gaz
eb
o
an
d
tu
r
n
s
o
n
o
n
th
e
r
o
b
o
t
o
p
er
atin
g
s
y
s
t
e
m
(
R
OS)
T
h
is
r
esear
ch
in
s
er
t
s
th
e
s
t
r
id
es
to
cr
ea
te
a
r
o
b
o
t
ar
m
m
o
d
el
co
n
tr
o
lled
b
y
R
OS
an
d
d
is
co
v
er
ed
th
e
tar
g
e
t
[
1
5
]
.
R
o
b
o
t
-
aid
p
r
o
s
tate
i
n
v
o
l
v
e
m
en
t
b
y
h
e
lp
in
g
m
ag
n
etic
r
e
s
o
n
a
n
ce
i
m
ag
i
n
g
(
MRI)
d
ir
ec
tin
g
is
a
ho
p
ef
u
l
p
r
o
ce
s
s
to
g
et
b
etter
clin
ical
p
u
r
s
u
an
ce
to
co
n
tr
ast
w
ith
t
h
e
m
a
n
u
a
l
s
u
r
g
er
y
p
r
o
ce
s
s
.
Ultr
aso
n
ic
m
o
to
r
s
ar
e
u
s
ed
to
f
u
l
l
o
p
er
atio
n
an
MRI
-
g
u
id
ed
6
-
DOF
p
r
o
s
tate
in
v
o
lv
e
m
e
n
t
s
er
ial
r
o
b
o
t
is
p
r
ep
ar
ed
an
d
th
e
co
n
tr
o
l
p
lan
n
i
n
g
i
s
p
r
o
p
o
s
ed
.
T
h
e
m
ec
h
a
n
ical
la
y
o
u
t
o
f
th
e
s
u
g
g
e
s
ted
r
o
b
o
t
is
o
f
f
er
ed
f
o
r
d
ep
en
d
s
o
n
th
e
la
y
o
u
t
d
e
m
an
d
s
o
f
th
e
p
r
o
s
tat
e
in
v
o
l
v
e
m
en
t
r
o
b
o
t
d
ev
ice.
T
h
e
m
icr
o
s
co
p
e
v
ie
w
i
n
g
is
d
ep
en
d
en
t
as
t
h
e
in
-
v
itro
n
ee
d
le
p
iece
s
ize
p
atter
n
an
d
t
h
e
r
o
b
o
tic
m
o
d
el
j
o
in
ed
w
it
h
t
h
e
b
in
o
cu
lar
ca
m
er
as
ar
e
c
lar
if
y
[
16
]
.
Vis
u
a
l
g
r
asp
i
s
a
f
u
n
d
a
m
e
n
tal
ab
ilit
y
n
ee
d
f
u
l
f
o
r
in
tell
ig
e
n
t
m
o
b
ile
r
o
b
o
ts
to
r
ea
ct
co
m
p
let
el
y
a
n
d
s
af
e
l
y
w
i
t
h
h
u
m
a
n
s
in
th
e
ac
tu
al
w
o
r
ld
.
I
n
th
is
p
ap
er
,
a
v
i
s
ib
le
p
er
ce
p
tio
n
s
tr
u
c
tu
r
e
f
o
r
an
in
te
lli
g
en
t
m
o
b
ile
r
o
b
o
t
is
p
r
esen
t.
T
h
e
f
r
a
m
e
w
o
r
k
m
er
g
es
a
b
r
o
ad
s
et
o
f
d
ev
elo
p
ed
alg
o
r
ith
m
s
elig
ib
le
f
o
r
r
ec
o
g
n
izi
n
g
p
eo
p
le,
o
b
j
ec
tiv
es,
a
n
d
h
u
m
a
n
tr
ic
k
s
,
as
w
ell
as
p
o
r
tr
ay
in
g
o
b
s
er
v
e
d
s
ce
n
e
s
[
17
]
.
th
i
s
ar
ticle
s
i
tti
n
g
s
a
n
o
v
el
R
GB
-
D
lear
n
in
g
-
f
r
ee
d
ef
o
r
m
ab
le
tar
g
et
tr
ac
k
er
in
co
llect
io
n
w
it
h
a
ca
m
er
a
p
lace
o
p
ti
m
izatio
n
m
o
d
el
f
o
r
o
p
ti
m
al
d
ef
o
r
m
ab
le
o
b
j
ec
t
g
r
asp
.
T
h
e
tactic
is
b
ased
o
n
t
h
e
ap
p
r
ec
iatio
n
o
f
th
e
tar
g
et
's
v
is
ib
l
e
ar
ea
th
r
o
u
g
h
th
e
p
r
o
d
u
ctio
n
o
f
a
s
u
p
er
v
o
x
el
g
r
ap
h
th
a
t
allo
w
s
w
ei
g
h
ti
n
g
n
e
w
s
u
p
er
v
o
x
el
ca
n
d
id
ate
s
a
m
o
n
g
tar
g
et
s
tate
s
o
v
er
ti
m
e.
O
n
ce
a
d
is
to
r
tio
n
s
tate
o
f
th
e
o
b
j
ec
t
is
s
p
ec
if
ic,
s
u
p
er
v
o
x
el
s
o
f
it
s
r
elate
d
g
r
ap
h
s
e
r
v
e
as
i
n
p
u
t
f
o
r
th
e
ca
m
er
a
p
o
s
itio
n
o
p
ti
m
izat
io
n
p
r
o
b
lem
[
18
]
.
I
n
th
is
w
o
r
k
,
m
o
d
er
n
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es
ar
e
u
s
ed
f
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2586
Dev
elo
p
men
t o
f a
d
yn
a
mic
in
t
ellig
en
t reco
g
n
itio
n
s
ystem
fo
r
a
r
ea
l
-
time
tr
a
ck
in
g
r
o
b
o
t
(
Th
a
ir
A
li S
a
lih
)
163
ef
f
ec
tiv
e
a
n
d
s
tr
o
n
g
v
eh
icle
d
is
co
v
er
ed
m
et
h
o
d
2
D
L
iD
AR
w
it
h
a
les
s
ex
p
e
n
s
i
v
e.
T
h
is
p
ap
er
s
u
g
g
est
s
a
n
ed
u
ca
tio
n
-
b
ased
p
r
o
ce
s
s
w
it
h
th
e
in
p
u
t
o
f
p
s
e
u
d
o
-
i
m
ag
e
s
,
w
h
ich
d
en
o
m
i
n
ate
th
e
ca
s
ca
d
e
p
y
r
a
m
id
r
eg
io
n
p
r
o
p
o
s
al
co
n
v
o
lu
t
io
n
n
e
u
r
al
n
et
w
o
r
k
(
ca
s
ca
d
e
p
y
r
a
m
id
R
C
N
N)
.
R
es
u
lts
p
r
o
v
e
t
h
at
th
is
m
et
h
o
d
o
f
f
er
s
a
cc
u
r
ac
y
a
n
d
s
u
p
er
io
r
ac
h
iev
e
m
en
t
o
f
t
h
e
r
ap
id
it
y
an
d
li
g
h
t
w
ei
g
h
t
p
atter
n
[
19
]
.
A
h
y
b
r
id
co
n
tr
o
l
m
o
d
el
i
s
s
u
g
g
e
s
ted
in
t
h
is
p
ap
er
to
r
e
alize
f
u
ll
-
b
o
d
y
co
n
f
lict
e
v
asi
o
n
in
in
ter
n
et
r
o
b
o
t
r
ig
g
er
s
.
T
h
e
p
r
o
p
o
s
al
m
en
d
s
v
in
tag
e
m
o
v
e
m
en
t
d
esig
n
alg
o
r
ith
m
s
b
y
in
s
er
ti
n
g
a
d
ee
p
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
(
DR
L
)
p
ath
tr
ain
ed
ad
h
o
c
f
o
r
i
m
p
le
m
en
tin
g
h
u
r
d
le
ev
a
s
i
o
n
an
d
r
ea
lizin
g
attai
n
ed
d
u
t
y
in
t
h
e
ef
f
ec
ti
v
e
ar
ea
.
Fu
r
t
h
er
p
ar
ticu
lar
l
y
,
c
h
an
g
e
m
ec
h
a
n
izat
io
n
b
ec
o
m
e
s
s
tr
o
n
g
w
h
e
n
a
s
it
u
atio
n
o
f
n
ea
r
n
es
s
to
t
h
e
h
u
r
d
le
is
ac
h
iev
ed
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
h
as
b
ee
n
last
l
y
e
x
a
m
in
ed
r
e
l
y
i
n
g
o
n
an
ac
t
u
al
r
o
b
o
t
r
ig
g
er
s
i
m
u
lated
in
a
V
-
R
E
P
m
ed
iu
m
[
20
]
.
T
h
e
h
eter
o
g
e
n
eo
u
s
m
u
l
ti
-
r
o
b
o
t
f
r
a
m
e
w
o
r
k
is
o
n
e
o
f
th
e
m
o
s
t
s
u
b
s
ta
n
tial
r
esear
ch
tr
en
d
s
i
n
th
e
r
o
b
o
tic
f
ield
.
I
n
th
is
r
e
s
ea
r
ch
,
a
n
a
m
e
n
d
ed
r
ea
l
-
ti
m
e
p
at
h
d
elin
ea
t
io
n
m
et
h
o
d
is
o
f
f
er
ed
f
o
r
a
h
eter
o
g
en
eo
u
s
m
u
lti
-
r
o
b
o
t
s
y
s
te
m
,
w
h
ic
h
i
s
o
r
g
a
n
ized
o
f
n
u
m
er
o
u
s
u
n
m
an
n
ed
ae
r
ial
v
eh
icles
(
U
A
V
s
)
an
d
u
n
m
a
n
n
ed
ea
r
t
h
v
e
h
icle
s
(
UGVs)
.
I
n
th
e
s
u
g
g
e
s
ted
m
et
h
o
d
,
th
e
3
D
en
v
ir
o
n
m
e
n
t
is
p
l
an
ed
as
a
n
eu
r
o
n
to
p
o
lo
g
y
m
a
p
,
b
ased
o
n
th
e
g
r
id
m
et
h
o
d
m
u
tu
al
w
i
th
t
h
e
b
io
-
in
s
p
ir
ed
n
e
u
r
al
n
et
w
o
r
k
.
T
h
e
r
esu
lts
d
i
s
p
la
y
t
h
at
t
h
e
s
u
g
g
ested
m
eth
o
d
ca
n
ef
f
icien
tl
y
g
u
id
e
th
e
h
eter
o
g
e
n
eo
u
s
U
A
V/U
GV
s
y
s
te
m
to
th
e
ai
m
,
an
d
h
as
b
etter
ex
ec
u
tio
n
th
an
co
n
v
e
n
tio
n
al
m
et
h
o
d
s
in
t
h
e
r
ea
l
-
ti
m
e
p
at
h
d
elin
ea
tio
n
tas
k
s
[
21
].
T
h
is
p
ap
er
is
o
r
g
an
ized
as:
Sectio
n
2
d
em
o
n
s
tr
ates
t
h
e
s
y
s
te
m
ar
ch
i
tectu
r
e;
Sectio
n
3
s
h
o
w
s
t
h
e
f
lo
w
c
h
ar
t
f
o
r
t
h
e
f
u
n
ct
io
n
o
f
t
h
e
d
es
ig
n
ed
s
y
s
te
m
w
i
th
t
h
e
o
b
tain
ed
r
esu
lt
s
.
Sectio
n
4
co
n
cl
u
s
io
n
s
w
h
ic
h
o
b
tain
ed
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
A
r
o
b
o
t
is
a
h
u
m
a
n
-
m
ad
e
elec
tr
o
m
ec
h
a
n
ical
d
ev
ice
th
at
ca
n
m
o
v
e
o
n
its
o
w
n
ac
co
r
d
in
g
to
a
s
et
o
f
p
lan
n
ed
co
m
m
a
n
d
s
in
s
ti
g
ated
in
s
o
f
t
w
ar
e
an
d
u
p
d
ated
b
y
s
en
s
o
r
y
p
er
ce
p
tio
n
.
T
h
is
w
o
r
k
d
ev
elo
p
s
a
R
o
b
o
t
th
at
d
etec
ts
a
n
o
b
j
ec
t in
r
ea
l
-
ti
m
e.
T
h
e
f
o
llo
w
in
g
is
a
d
escr
ip
tio
n
o
f
t
h
e
p
ar
ts
o
f
th
e
p
r
o
p
o
s
ed
r
o
b
o
t sy
s
te
m
.
2
.
1
.
Ro
bo
t
pla
t
f
o
rm
de
s
ig
ned
As
s
h
o
w
n
i
n
Fi
g
u
r
e
1
th
e
p
r
o
p
o
s
ed
m
o
d
el
in
clu
d
es
all
th
e
elec
tr
ical
an
d
m
ec
h
an
ica
l
co
m
p
o
n
en
t
s
r
eq
u
ir
ed
to
b
u
ild
th
e
p
r
o
p
o
s
ed
r
o
b
o
t
s
y
s
te
m
,
in
c
lu
d
i
n
g
th
e
m
o
to
r
d
r
iv
er
,
w
h
ee
ls
,
ch
as
s
is
,
A
r
d
u
in
o
A
T
m
a
g
a2
5
6
m
icr
o
co
n
tr
o
ller
,
m
i
n
i
-
HD
W
i
-
Fi ca
m
er
a
w
i
th
S
G
-
9
s
er
v
o
m
o
to
r
s
a
n
d
s
p
ec
if
ic
s
en
s
o
r
s
.
Fig
u
r
e
1
.
T
h
e
r
o
b
o
t
p
latf
o
r
m
T
h
e
r
o
b
o
t
s
y
s
te
m
is
co
n
tr
o
lle
d
b
y
a
n
A
r
d
u
i
n
o
A
T
m
e
g
a2
5
6
b
o
ar
d
,
w
h
ic
h
i
s
o
p
en
-
s
o
u
r
ce
elec
tr
o
n
ics
p
r
o
to
ty
p
in
g
p
lat
f
o
r
m
.
I
t
is
a
s
i
m
p
le
b
o
ar
d
co
n
tai
n
in
g
a
m
ic
r
o
co
n
tr
o
ller
,
p
er
ip
h
er
al
in
ter
f
ac
es,
p
o
w
er
s
u
p
p
l
y
cir
cu
its
,
w
h
ic
h
i
s
p
r
o
g
r
a
m
m
e
d
b
y
a
n
e
x
is
t
in
g
s
o
f
t
w
ar
e
p
lat
f
o
r
m
[
2
2
]
.
A
p
o
r
tab
le
m
i
n
i
-
H
D
W
i
-
Fi
ca
m
er
a
i
s
attac
h
ed
o
n
th
e
r
o
b
o
t
p
latf
o
r
m
;
it
ad
o
p
ts
P
2
P
tech
n
o
lo
g
y
,
w
h
ic
h
allo
w
s
u
s
er
s
to
ea
s
il
y
c
o
n
f
i
g
u
r
e
th
e
ca
m
er
a
m
o
u
n
ted
o
n
a
n
SG
-
9
0
s
er
v
o
m
o
to
r
f
o
r
o
b
j
ec
t
tr
ac
k
in
g
p
u
r
p
o
s
e
[
2
3
]
.
A
n
S
R
F
-
0
5
m
o
d
el
u
ltra
s
o
n
ic
s
e
n
s
o
r
is
also
attac
h
ed
o
v
er
a
n
SG
-
9
0
s
er
v
o
m
o
to
r
f
o
r
o
b
s
tacle
a
v
o
id
an
ce
,
it
ca
n
s
e
n
s
e
o
b
s
tacle
s
f
r
o
m
0
.
0
1
-
to
4
m
eter
s
s
p
ac
e,
an
d
its
ab
ilit
y
co
n
n
ec
ts
to
th
e
A
r
d
u
in
o
b
o
ar
d
ea
s
il
y
.
I
t
o
p
er
ated
at
(
5
v
,
3
0
m
A
,
an
d
4
0
k
Hz)
.
I
ts
ab
ilit
y
to
d
is
co
v
er
th
e
3
c
m
d
ia
m
e
ter
b
o
d
y
f
r
o
m
f
u
r
th
er
t
h
a
n
2
m
s
p
ac
e
[
2
4
]
.
A
s
m
o
k
e
s
e
n
s
o
r
is
u
s
ed
to
m
ea
s
u
r
e
t
h
e
s
m
o
k
e
lev
el
; it
w
ill
m
ak
e
t
h
e
b
u
zz
er
s
o
u
n
d
w
h
en
r
ea
c
h
es a
ce
r
tain
lev
el.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2722
-
2586
I
A
E
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
0
,
No
.
3
,
Sep
tem
b
er
2
0
2
1
:
1
6
1
–
169
164
2
.
2
.
O
pera
t
io
ns
o
f
t
he
des
ig
ned r
o
bo
t
A
r
o
b
o
t
is
d
esi
g
n
ed
to
m
o
n
i
to
r
a
b
u
ild
i
n
g
o
r
g
o
v
er
n
m
e
n
t
d
ep
ar
t
m
en
t
w
h
en
e
m
p
lo
y
ee
s
leav
e
to
p
r
o
v
id
e
s
ec
u
r
it
y
an
d
to
av
o
i
d
lo
s
s
o
f
lif
e
an
d
eq
u
ip
m
en
t
ca
u
s
ed
b
y
f
ir
es.
T
h
e
r
o
b
o
t
is
eq
u
ip
p
ed
w
it
h
a
s
u
r
v
eilla
n
ce
ca
m
er
a
to
m
o
n
ito
r
th
e
b
u
ild
in
g
d
u
r
i
n
g
th
e
r
o
a
m
in
g
p
er
io
d
an
d
w
ir
eless
l
y
tr
a
n
s
m
i
t
liv
e
i
m
a
g
es
to
th
e
ce
n
tr
al
co
m
p
u
ter
'
s
r
ec
o
g
n
i
tio
n
s
y
s
te
m
as
s
h
o
w
n
i
n
Fi
g
u
r
e
2
.
A
r
o
b
o
t
is
d
esig
n
ed
to
m
o
n
ito
r
a
b
u
ild
in
g
o
r
g
o
v
er
n
m
e
n
t
d
ep
ar
t
m
e
n
t
w
h
en
e
m
p
lo
y
ee
s
lea
v
e
to
p
r
o
v
id
e
s
ec
u
r
it
y
a
n
d
to
a
v
o
id
lo
s
s
o
f
lif
e
a
n
d
eq
u
ip
m
e
n
t
ca
u
s
ed
b
y
f
ir
es.
T
h
e
r
o
b
o
t
is
e
q
u
ip
p
ed
w
it
h
a
s
u
r
v
eilla
n
ce
ca
m
er
a
to
m
o
n
ito
r
th
e
b
u
ild
in
g
d
u
r
in
g
th
e
r
o
a
m
in
g
p
er
io
d
an
d
w
ir
ele
s
s
l
y
tr
a
n
s
m
it
liv
e
i
m
ag
e
s
to
th
e
ce
n
tr
al
co
m
p
u
ter
's
r
ec
o
g
n
itio
n
s
y
s
te
m
a
s
s
h
o
w
n
i
n
F
ig
u
r
e
2
.
T
h
e
r
o
b
o
t
w
il
l
k
ee
p
tr
ac
k
o
f
t
h
e
g
en
er
ated
p
ath
w
h
ile
co
n
s
t
an
tl
y
r
ea
d
in
g
i
n
f
o
r
m
atio
n
f
r
o
m
t
h
e
e
n
v
ir
o
n
m
e
n
t
u
s
i
n
g
u
ltra
s
o
n
ic
s
e
n
s
o
r
s
.
I
f
th
e
r
o
b
o
t
f
in
d
s
o
u
t
an
o
b
j
ec
t
th
at
b
lo
ck
s
th
e
p
ath
,
th
e
r
o
b
o
t
w
i
ll
p
au
s
e
an
d
u
p
d
ate
th
e
ch
ar
t
w
it
h
th
e
n
e
w
d
ata
an
d
m
a
k
e
th
e
d
ec
is
io
n
to
tu
r
n
9
0
d
eg
r
ee
s
to
th
e
r
ig
h
t
o
r
lef
t
o
r
tu
r
n
i
n
g
ar
o
u
n
d
1
8
0
d
eg
r
ee
s
ac
co
r
d
in
g
to
th
e
p
o
s
iti
o
n
esti
m
ate.
Fig
u
r
e
2
.
R
o
b
o
t m
o
d
el.
T
h
e
r
ec
o
g
n
itio
n
s
y
s
te
m
d
eter
m
i
n
es
t
h
e
r
o
tatio
n
a
n
g
le
a
n
d
f
lo
w
d
ir
ec
tio
n
.
T
h
e
r
o
b
o
t
ca
n
id
en
t
if
y
an
y
o
n
e
e
n
ter
in
g
u
s
i
n
g
f
ac
ial
r
ec
o
g
n
itio
n
tec
h
n
o
lo
g
y
an
d
co
m
p
ar
i
n
g
it
to
a
s
p
ec
ial
d
atab
a
s
e
o
f
f
ac
ial
i
m
a
g
e
s
,
an
d
th
i
s
is
d
o
n
e
u
s
i
n
g
a
s
tat
i
s
tical
tec
h
n
iq
u
e
t
h
at
u
s
e
s
t
h
e
m
ai
n
co
m
p
o
n
e
n
ts
a
n
al
y
s
i
s
P
C
A
o
r
E
ig
e
n
o
b
j
ec
t
tech
n
o
lo
g
y
[
2
5
]
,
[
2
6
]
,
th
er
e
ar
e
f
i
v
e
m
ai
n
s
tag
e
s
o
f
f
ac
ial
r
e
co
g
n
itio
n
s
ee
Fi
g
u
r
e
3
.
W
h
e
n
th
e
r
o
b
o
t
id
en
ti
f
ie
s
a
p
er
s
o
n
,
it st
ar
ts
to
tr
ac
k
h
i
m
an
d
tak
e
s
p
ictu
r
es o
f
h
is
f
ac
e.
T
h
ese
i
m
a
g
es a
r
e
co
n
s
id
er
ed
as in
p
u
ts
to
t
h
e
f
ac
e
r
ec
o
g
n
itio
n
s
y
s
te
m
,
p
r
e
-
p
r
o
ce
s
s
i
n
g
s
tep
s
ap
p
lied
to
th
e
n
o
r
m
aliza
tio
n
s
tag
e
(
i
m
a
g
e
s
ize,
tr
an
s
latio
n
,
r
o
tatio
n
,
an
d
illu
m
i
n
atio
n
)
,
b
ac
k
g
r
o
u
n
d
r
em
o
v
al
t
h
e
f
ac
e
i
m
a
g
e
p
ass
i
n
th
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
s
ta
g
e.
Fig
u
r
e
3
.
R
o
b
o
t selec
t
m
o
v
i
n
g
p
ath
T
h
e
d
atab
ase
o
f
Oliv
etti
r
ese
ar
ch
lab
o
r
ato
r
y
(
OR
L
)
is
u
s
e
d
in
th
is
p
ap
er
,
Fig
u
r
e
4
s
h
o
w
s
s
o
m
e
ex
a
m
p
le
s
o
f
O
R
L
d
ataset.
T
h
e
k
e
y
f
ea
t
u
r
es
ar
e
co
m
p
ar
ed
w
it
h
t
h
e
f
ea
tu
r
e
s
s
to
r
ed
in
t
h
e
f
ac
e
d
atab
ase
in
a
s
tep
ca
lled
p
atter
n
class
i
f
ier
as
s
h
o
w
n
i
n
Fi
g
u
r
e
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2586
Dev
elo
p
men
t o
f a
d
yn
a
mic
in
t
ellig
en
t reco
g
n
itio
n
s
ystem
fo
r
a
r
ea
l
-
time
tr
a
ck
in
g
r
o
b
o
t
(
Th
a
ir
A
li S
a
lih
)
165
Fig
u
r
e
4
.
So
m
e
o
f
OR
L
d
atase
t e
x
a
m
p
le
s
Fig
u
r
e
5
.
B
lo
ck
d
iag
r
a
m
o
f
f
a
ce
r
ec
o
g
n
itio
n
s
y
s
te
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2722
-
2586
I
A
E
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
0
,
No
.
3
,
Sep
tem
b
er
2
0
2
1
:
1
6
1
–
169
166
T
h
e
r
ec
o
g
n
itio
n
s
y
s
te
m
clas
s
i
f
ies
t
h
e
f
ac
e
i
m
a
g
e
a
n
d
aler
ts
th
e
s
ec
u
r
it
y
m
a
n
f
o
r
t
h
e
s
tr
an
g
er
p
er
s
o
n
.
I
n
th
e
P
C
A
alg
o
r
ith
m
t
h
e
f
ac
e
I
m
a
g
e
(
α
)
r
ep
r
esen
ted
b
y
a
tr
ain
i
n
g
s
et
o
f
(
Z
)
i
m
a
g
es
o
f
v
o
lu
m
e
(
W
x
W
)
is
p
er
f
o
r
m
ed
b
y
v
ec
to
r
s
o
f
v
o
lu
m
e
(
W
2
)
,
th
en
ca
lc
u
late
t
h
e
av
er
ag
e
f
ac
e
(
φ)
b
y
(
1
)
.
=
1
∑
=
1
(
1
)
W
h
er
e
(
I
=
1,
2
,
3
….
,
n
)
,
th
e
n
o
r
m
ali
za
t
io
n
(
Y)
is
p
er
f
o
r
m
e
d
b
y
ca
lc
u
lati
n
g
t
h
e
d
if
f
er
en
ce
b
et
w
ee
n
ea
ch
f
ac
e
an
d
av
er
ag
e
.
=
−
(
2
)
A
co
v
ar
ian
ce
m
atr
i
x
f
o
r
m
u
la
(
=
)
is
ca
lcu
lated
f
o
r
ea
ch
E
i
g
en
v
ec
to
r
,
w
h
er
e
A
is
a
v
ec
to
r
f
u
n
ctio
n
.
T
o
s
im
p
li
f
y
th
e
o
u
t
p
u
t
m
atr
i
x
A
TA
ca
lcu
late,
w
h
er
e
=
(
1
,
2
,
3
,
…
…
)
b
y
co
n
s
id
er
in
g
t
h
e
E
ig
en
v
ec
to
r
s
ei
o
f
A
T
A
s
u
c
h
t
h
at;
=
ʎ
(
3
)
W
h
er
e
λ
i is t
h
e
E
ig
e
n
v
al
u
e
a
n
d
Xi
is
th
e
E
ig
e
n
v
ec
to
r
.
No
w
m
u
ltip
l
y
b
o
th
s
id
es o
f
(
3
)
b
y
A
to
g
et
(
4
)
.
(
)
=
ʎ
(
)
(
4
)
T
h
e
in
p
u
t i
m
ag
e
(
α
)
,
d
is
p
la
y
s
in
to
th
e
f
ac
e
s
p
ac
e
to
g
et
a
v
ec
to
r
(
P).
=
(
−
)
(
5
)
T
h
e
s
p
ac
e
o
f
(
P)
to
ea
ch
f
ac
e
is
ca
lled
E
u
clid
ea
n
s
p
ac
e
an
d
r
ea
lized
by
(
6)
.
2
=
‖
−
‖
2
(
6
)
W
h
er
e
=
1
,
…
,
r
ep
r
esen
t
a
v
ec
to
r
o
f
k
th
f
ac
e
ca
teg
o
r
y
.
A
f
ac
e
is
r
ated
as
a
r
elatio
n
s
h
ip
to
ca
teg
o
r
y
k
w
h
e
n
th
e
lo
w
er
u
k
i
s
less
t
h
a
n
s
elec
tio
n
s
ill θ
c
,
els
e,
th
e
f
ac
e
is
s
o
r
ted
as u
n
k
n
o
wn
θ
c
.
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
T
h
e
s
y
s
te
m
w
as
te
s
ted
u
s
i
n
g
th
e
O
RL
d
atab
ase
o
f
f
ac
e
s
e
x
p
lain
in
Fi
g
u
r
e
5
.
T
h
e
ac
cu
r
ac
y
o
f
th
e
s
y
s
te
m
w
as
m
ea
s
u
r
ed
b
y
t
h
e
E
u
clid
ian
d
is
tan
ce
b
et
w
ee
n
t
h
e
test
f
ac
e
i
m
ag
e
s
an
d
tr
ai
n
f
ac
es.
T
h
e
r
o
b
o
t
is
eq
u
ip
p
ed
w
it
h
m
a
n
y
s
en
s
o
r
s
,
s
u
c
h
a
s
a
n
o
b
s
tacle
s
e
n
s
o
r
d
u
r
in
g
m
o
v
e
m
e
n
t
a
n
d
s
m
o
k
e
d
et
ec
to
r
s
,
w
h
er
eb
y
t
h
e
r
o
b
o
t
r
e
p
o
r
ts
an
y
s
ec
u
r
it
y
b
r
ea
ch
o
r
f
ir
e
th
a
t
o
cc
u
r
s
i
n
s
id
e
th
e
b
u
ild
i
n
g
to
th
e
ce
n
tr
al
co
m
p
u
ter
.
W
h
e
n
a
s
tr
an
g
e
s
itu
at
io
n
o
cc
u
r
s
i
n
s
id
e
th
e
b
u
ild
in
g
,
t
h
e
s
ec
u
r
it
y
s
y
s
te
m
w
ill
r
ep
o
r
t
it
b
y
is
s
u
in
g
v
o
ice
co
m
m
a
n
d
s
f
r
o
m
t
h
e
co
m
p
u
ter
to
t
h
e
s
ec
u
r
it
y
m
a
n
,
w
h
o
w
i
ll tak
e
t
h
e
n
e
ce
s
s
ar
y
ac
tio
n
.
T
h
er
e
h
av
e
b
ee
n
m
a
n
y
p
r
ac
ti
ca
l
ex
p
er
i
m
e
n
ts
an
d
s
ce
n
ar
io
s
to
co
n
tr
o
l
th
e
m
o
v
e
m
e
n
t
o
f
th
e
r
o
b
o
t.
Fig
u
r
e
6
s
h
o
w
s
th
e
co
n
s
tr
u
cti
o
n
o
f
a
s
u
g
g
e
s
ted
alg
o
r
it
h
m
f
o
r
a
r
o
b
o
t m
o
v
e
m
en
t
th
at
co
r
r
e
s
p
o
n
d
s
to
th
e
n
at
u
r
e
o
f
th
e
p
r
o
p
o
s
ed
b
u
ild
in
g
.
T
h
e
p
lace
w
a
s
d
esig
n
ed
co
n
ce
r
n
i
n
g
t
h
e
co
o
r
d
in
atio
n
o
f
th
e
co
lo
r
s
o
f
th
e
w
all
a
n
d
th
e
t
y
p
e
o
f
f
u
r
n
it
u
r
e
th
a
t f
ac
il
i
tates th
e
m
o
v
e
m
e
n
t o
f
t
h
e
r
o
b
o
t.
Fig
u
r
e
5
.
R
ec
o
g
n
i
tio
n
s
y
s
te
m
test
r
esu
lts
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2586
Dev
elo
p
men
t o
f a
d
yn
a
mic
in
t
ellig
en
t reco
g
n
itio
n
s
ystem
fo
r
a
r
ea
l
-
time
tr
a
ck
in
g
r
o
b
o
t
(
Th
a
ir
A
li S
a
lih
)
167
Fig
u
r
e
6
.
Flo
w
c
h
ar
t o
f
t
h
e
r
o
b
o
t m
o
tio
n
4.
C
ON
C
L
U
S
ION
S
T
h
is
p
ap
er
d
escr
ib
es
th
e
s
e
cu
r
it
y
,
s
a
f
et
y
,
a
n
d
i
n
d
ep
en
d
en
t
n
av
ig
atio
n
s
y
s
te
m
s
d
esi
g
n
ed
a
n
d
i
m
p
le
m
en
ted
o
n
a
m
u
l
ti
-
s
e
n
s
o
r
m
o
b
ile
s
ec
u
r
it
y
r
o
b
o
t.
T
h
e
wir
eless
ca
m
er
a
is
u
s
ed
to
d
etec
t
th
e
m
o
v
e
m
e
n
t
o
f
o
b
j
ec
ts
an
d
f
ir
e.
T
h
is
is
ac
h
ie
v
ed
th
r
o
u
g
h
u
ti
lize
b
o
th
t
h
e
i
m
ag
e
s
a
n
d
th
e
co
n
to
u
r
m
o
d
el
w
h
ic
h
ar
e
q
u
ick
l
y
p
r
o
ce
s
s
ed
w
it
h
t
h
e
p
ar
ticle
f
ilter
.
Usi
n
g
th
is
s
y
s
te
m
o
b
j
ec
ts
ca
n
b
e
d
is
co
v
er
ed
i
n
d
ep
en
d
en
tl
y
o
f
li
g
h
ti
n
g
co
n
d
itio
n
s
.
Fra
m
e
tr
ac
k
i
n
g
i
n
i
m
a
g
es
is
u
s
ed
as
a
n
at
tr
ac
tiv
e
s
y
s
te
m
to
g
et
an
esti
m
at
e
o
f
a
p
er
s
o
n
'
s
p
o
s
it
io
n
.
T
h
is
o
p
er
atio
n
w
ill s
u
p
p
o
r
t th
e
ca
m
er
a
to
d
etec
t a
f
ir
e
in
s
id
e
th
e
b
u
ild
i
n
g
.
RE
F
E
R
E
NC
E
S
[
1
]
.
S
.
Z.
M
u
rs
h
e
d
,
e
t
a
l
.
,
“
Co
n
tr
o
ll
in
g
a
n
e
m
b
e
d
d
e
d
r
o
b
o
t
t
h
ro
u
g
h
im
a
g
e
p
ro
c
e
ss
in
g
b
a
se
d
o
b
jec
t
trac
k
in
g
u
sin
g
M
AT
LAB,
”
2
0
1
6
1
0
th
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
I
n
telli
g
e
n
t
S
y
ste
ms
a
n
d
Co
n
tro
l
(
IS
CO)
,
2
0
1
6
,
p
p
.
1
-
6
,
d
o
i:
1
0
.
1
1
0
9
/I
S
CO.2
0
1
6
.
7
7
2
6
9
2
2
.
[
2
]
.
I.
M
.
A
riff
in
,
e
t
a
l
.
,
“
S
e
n
s
o
r
Ba
se
d
M
o
b
il
e
Na
v
ig
a
ti
o
n
Us
in
g
Hu
m
a
n
o
id
R
o
b
o
t
Na
o
,
”
Pro
c
e
d
ia
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
7
6
,
p
p
.
4
7
4
–
4
7
9
,
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2722
-
2586
I
A
E
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
0
,
No
.
3
,
Sep
tem
b
er
2
0
2
1
:
1
6
1
–
169
168
[
3
]
.
W
.
Bu
rg
a
rd
,
M
.
M
o
o
rs,
D.
F
o
x
,
R.
S
imm
o
n
s,
a
n
d
S
.
T
h
ru
n
,
“
Co
ll
a
b
o
ra
ti
v
e
m
u
lt
i
-
ro
b
o
t
e
x
p
lo
ra
ti
o
n
,
”
Pr
o
c
.
2
0
0
0
ICRA
.
M
il
len
n
.
Co
n
f.
IEE
E
I
n
t.
Co
n
f.
Ro
b
o
t
.
A
u
to
m.
S
y
mp
.
Pro
c
.
(
Ca
t.
No
.
0
0
CH3
7
0
6
5
)
,
2
0
0
0
,
p
p
.
4
7
6
-
4
8
1
v
o
l.
1
,
d
o
i:
1
0
.
1
1
0
9
/R
OBOT.
2
0
0
0
.
8
4
4
1
0
0
.
[
4
]
.
D.
Ca
rn
e
g
ie,
A
.
P
ra
k
a
sh
,
C.
C
h
it
t
y
a
n
d
B.
G
u
y
,
“
A
Hu
m
a
n
-
li
k
e
S
e
m
i
A
u
to
n
o
m
o
u
s
M
o
b
il
e
S
e
c
u
rit
y
Ro
b
o
t,
”
2
n
d
In
t
.
Co
n
f.
Au
t
o
n
.
R
o
b
o
t.
A
g
e
n
ts
,
2
0
0
4
,
p
p
.
6
4
–
69
.
[
5
]
.
A
.
M
il
e
ll
a
,
C.
Di
m
icc
o
li
,
G
.
Ci
c
irelli
a
n
d
A
.
Dista
n
te,
“
Las
e
r
-
b
a
se
d
P
e
o
p
le
-
F
o
ll
o
w
in
g
f
o
r
Hu
m
a
n
A
u
g
m
e
n
ted
M
a
p
p
i
n
g
o
f
In
d
o
o
r
En
v
ir
o
n
m
e
n
ts
,
”
Pro
c
e
e
d
in
g
s
o
f
th
e
2
5
th
IA
S
T
ED
I
n
ter
n
a
ti
o
n
a
l
M
u
lt
i
-
C
o
n
fe
re
n
c
e
:
a
rtif
icia
l
in
telli
g
e
n
c
e
a
n
d
a
p
p
li
c
a
ti
o
n
s
,
2
0
0
7
,
p
p
.
1
5
1
-
1
5
5
.
[
6
]
.
D.
Di
P
a
o
la,
A
.
M
il
e
ll
a
,
G
.
Cicir
e
ll
i,
a
n
d
A
.
Dista
n
te
,
“
A
n
a
u
to
n
o
m
o
u
s
m
o
b
il
e
ro
b
o
t
ic
s
y
ste
m
f
o
r
su
rv
e
il
lan
c
e
o
f
in
d
o
o
r
e
n
v
iro
n
m
e
n
ts,”
In
t.
J
.
Ad
v
.
Ro
b
o
t.
S
y
st
.
,
v
o
l.
7
,
n
o
.
1
,
p
p
.
1
9
–
2
6
,
2
0
1
0
,
d
o
i:
1
0
.
5
7
7
2
/
7
2
5
4
.
[
7
]
.
T
.
A
.
S
a
lh
a
n
d
M
.
Z.
Na
y
e
f
,
“
In
telli
g
e
n
t
su
rv
e
il
lan
c
e
ro
b
o
t
,”
2
0
1
3
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l
Co
mm
u
n
ica
ti
o
n
,
Co
mp
u
ter
,
P
o
we
r,
a
n
d
Co
n
tro
l
E
n
g
i
n
e
e
rin
g
(
ICECCP
CE)
,
2
0
1
3
,
p
p
.
1
1
3
-
1
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/IC
ECC
P
CE.
2
0
1
3
.
6
9
9
8
7
4
5
.
[
8
]
.
M
.
S
.
Bin
Ba
h
r
u
d
i
n
,
R.
A
.
Ka
ss
i
m
,
a
n
d
N.
Bu
n
iy
a
m
in
,
“
De
v
e
lo
p
m
e
n
t
o
f
F
ire
a
lar
m
s
y
ste
m
u
sin
g
Ra
sp
b
e
rry
P
i
a
n
d
A
rd
u
in
o
Un
o
,
”
2
0
1
3
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l,
El
e
c
tro
n
ics
a
n
d
S
y
ste
m
En
g
i
n
e
e
rin
g
(
ICEE
S
E)
,
2
0
1
3
,
p
p
.
4
3
-
4
8
,
d
o
i:
1
0
.
1
1
0
9
/ICE
E
S
E.
2
0
1
3
.
6
8
9
5
0
4
0
.
[
9
]
.
A
.
M
.
A
h
m
a
d
a
n
d
H.
A
l
Yo
u
ss
e
f
,
“
3
D
se
n
so
r
-
b
a
se
d
M
o
v
in
g
Hu
m
a
n
T
ra
c
k
in
g
Ro
b
o
t
w
it
h
Ob
sta
c
le
Av
o
id
a
n
c
e
,
”
2
0
1
6
IEE
E
In
ter
n
a
ti
o
n
a
l
M
u
lt
i
d
i
sc
ip
li
n
a
ry
Co
n
fer
e
n
c
e
o
n
E
n
g
in
e
e
rin
g
T
e
c
h
n
o
l
o
g
y
(
IM
CET
)
,
2
0
1
6
,
p
p
.
9
-
1
4
,
d
o
i:
1
0
.
1
1
0
9
/I
M
CET
.
2
0
1
6
.
7
7
7
7
4
1
8
.
[
1
0
]
.
Z.
W
a
n
g
,
E.
G
.
L
i
m
,
W
.
W
a
n
g
,
M
.
L
e
a
c
h
,
a
n
d
K.
L
.
M
a
n
,
“
De
sig
n
o
f
a
n
a
rd
u
in
o
-
b
a
se
d
sm
a
rt
c
a
r,
”
2
0
1
4
In
ter
n
a
t
io
n
a
l
S
o
C
De
sig
n
C
o
n
fe
re
n
c
e
(
IS
OCC)
,
2
0
1
4
,
p
p
.
1
7
5
-
1
7
6
,
d
o
i:
1
0
.
1
1
0
9
/I
S
OCC.2
0
1
4
.
7
0
8
7
6
8
3
.
[
1
1
]
.
R.
Ba
lo
g
h
,
“
E
d
u
c
a
ti
o
n
a
l
R
o
b
o
ti
c
P
latf
o
rm
b
a
se
d
o
n
A
rd
u
in
o
,
”
Pr
o
c
e
e
d
in
g
s
o
f
t
h
e
1
st
in
ter
n
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
o
n
Ro
b
o
ti
c
s in
Ed
u
c
a
ti
o
n
,
Ri
E
2
0
1
0
,
2
0
1
0
.
[
1
2
]
.
P
.
Ja
m
ies
o
n
,
“
A
rd
u
in
o
f
o
r
tea
c
h
in
g
e
m
b
e
d
d
e
d
sy
ste
m
s.
A
r
e
c
o
m
p
u
ter
sc
ien
ti
sts
a
n
d
e
n
g
in
e
e
rin
g
e
d
u
c
a
to
rs
m
issin
g
th
e
b
o
a
t?
,
”
Pro
c
e
e
d
in
g
2
0
1
0
I
n
t.
Co
n
f.
Fro
n
t.
E
d
u
c
.
Co
mp
u
t.
S
c
i.
Co
mp
u
t
.
E
n
g
.
,
p
p
.
2
8
9
–
2
9
4
,
2
0
1
0
.
[
1
3
]
.
G
.
Wall,
“
W
IF
I
-
M
D8
p
ro
d
u
c
t
in
str
u
c
ti
o
n
s
,
”
Him
a
la
y
a
n
so
lu
ti
o
n
,
[
On
li
n
e
]
A
v
a
il
a
b
le:
h
tt
p
s
:/
/h
im
a
la
y
a
n
so
lu
ti
o
n
.
c
o
m
/sto
ra
g
e
/d
o
w
n
lo
a
d
s/Ko
L
S
h
m
Ku
c
q
7
A
Cs3
g
a
v
3
B
G
Rq
z
BtL
9
V
6
j2
P
n
G
0
GL
x
1
.
p
d
f
.
[
1
4
]
.
M
.
T
a
h
e
r
U.
Zam
a
n
a
n
d
M
.
S
.
A
h
m
e
d
,
“
De
si
g
n
a
n
d
c
o
n
str
u
c
ti
o
n
o
f
a
m
u
lt
ip
u
rp
o
se
ro
b
o
t,
”
I
n
t.
J
.
Au
to
m
.
Co
n
tro
l
In
tell.
S
y
st
.
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
3
4
-
4
6
,
2
0
1
5
.
[
1
5
]
.
F
.
Ja
ll
e
d
,
“
F
a
c
e
Re
c
o
g
n
it
io
n
M
a
c
h
in
e
Visio
n
S
y
ste
m
U
sin
g
Ei
g
e
n
f
a
c
e
s
,
”
Co
rn
e
ll
Un
iv
e
sit
y
,
p
a
p
e
r
c
it
e
c
ti
o
n
:
a
rX
iv
:1
7
0
5
.
0
2
7
8
2
v
1
,
p
p
.
1
–
7
,
2
0
1
7
.
[
1
6
]
.
X
.
Y
ue
,
A
.
Z
hu
,
J.
S
ong
,
G
.
C
ao
,
D.
A
n
,
a
n
d
Z.
G
UO
,
“
T
h
e
De
sig
n
a
n
d
Im
p
le
m
e
n
tatio
n
o
f
Hu
m
a
n
M
o
ti
o
n
Ca
p
t
u
re
S
y
st
e
m
Ba
se
d
o
n
C
A
N
Bu
s,
”
2
0
2
0
1
7
th
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Ub
iq
u
it
o
u
s
Ro
b
o
ts
(
UR)
,
2
0
2
0
,
p
p
.
4
1
5
-
4
2
0
,
d
o
i:
1
0
.
1
1
0
9
/UR4
9
1
3
5
.
2
0
2
0
.
9
1
4
4
8
5
8
.
[
1
7
]
.
X
.
Ho
u
,
W
.
L
i,
Y.
Ha
n
,
A
.
W
a
n
g
,
Y.
Ya
n
g
,
L
.
L
iu
,
a
n
d
Y
T
ian
,
“
A
n
o
v
e
l
m
o
b
il
e
ro
b
o
t
n
a
v
ig
a
ti
o
n
m
e
th
o
d
b
a
se
d
o
n
h
a
n
d
-
d
ra
w
n
p
a
th
s
,
”
IEE
E
S
e
n
so
rs
J
o
u
rn
a
l
,
v
o
l.
2
0
,
n
o
.
1
9
,
p
p
.
1
1
6
6
0
-
1
1
6
7
3
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/JS
EN.
2
0
2
0
.
2
9
9
7
0
5
5
.
[
1
8
]
.
B.
T
o
d
e
re
a
n
,
R.
Ru
su
-
Bo
t
h
,
Ov
id
iu
S
tan
,
“
G
u
id
a
n
c
e
a
n
d
s
a
fe
t
y
s
y
ste
m
s
f
o
r
m
o
b
il
e
ro
b
o
ts
,
”
2
0
2
0
IEE
E
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Au
to
m
a
ti
o
n
,
Qu
a
li
ty
a
n
d
T
e
stin
g
,
Ro
b
o
ti
c
s
(
AQT
R)
,
2
0
2
0
,
p
p
.
1
-
6
,
d
o
i
:
1
0
.
1
1
0
9
/A
QT
R4
9
6
8
0
.
2
0
2
0
.
9
1
3
0
0
1
5
.
[
1
9
]
.
H.
Ju
n
g
,
M
.
Kim
,
Y.
Ch
e
n
,
H.
Gi
M
in
,
a
n
d
T
.
P
a
rk
,
“
Im
p
le
m
e
n
tat
io
n
o
f
a
u
n
if
ied
si
m
u
latio
n
f
o
r
ro
b
o
t
a
rm
c
o
n
tro
l
w
it
h
o
b
jec
t
d
e
tec
ti
o
n
b
a
se
d
o
n
R
OS
a
n
d
G
a
z
e
b
o
,
”
2
0
2
0
1
7
t
h
In
te
rn
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
U
b
iq
u
it
o
u
s
R
o
b
o
ts
(
UR
),
2
0
2
0
,
p
p
.
3
6
8
-
3
7
2
,
d
o
i:
1
0
.
1
1
0
9
/
UR4
9
1
3
5
.
2
0
2
0
.
9
1
4
4
9
8
4
.
[
2
0
]
.
Y.
L
in
,
Y.
S
h
i,
J.
Zh
a
n
g
,
F
.
W
a
n
g
,
W
.
W
u
,
a
n
d
H.
S
u
n
,
“
De
sig
n
a
n
d
Co
n
tr
o
l
o
f
a
P
iez
o
e
lec
tri
c
Ac
tu
a
ted
P
ro
sta
te
In
terv
e
n
ti
o
n
Ro
b
o
t
ic
S
y
ste
m
,
”
2
0
2
0
1
7
th
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ub
i
q
u
it
o
u
s
R
o
b
o
ts
(
UR)
,
2
0
2
0
,
p
p
.
1
7
5
-
1
8
0
,
d
o
i:
1
0
.
1
1
0
9
/UR4
9
1
3
5
.
2
0
2
0
.
9
1
4
4
7
6
8
.
[
2
1
]
.
C
.
L
e
e
,
H.
L
e
e
1
,
I.
Hw
a
n
g
a
n
d
B.
Zh
a
n
g
,
“
Visu
a
l
P
e
rc
e
p
ti
o
n
F
r
a
m
e
w
o
rk
f
o
r
a
n
In
telli
g
e
n
t
M
o
b
i
le
Ro
b
o
t
,
”
2
0
2
0
1
7
t
h
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ub
iq
u
it
o
u
s
Ro
b
o
ts
(
UR)
,
2
0
2
0
,
p
p
.
6
1
2
-
6
1
6
,
d
o
i:
1
0
.
1
1
0
9
/UR
4
9
1
3
5
.
2
0
2
0
.
9
1
4
4
9
3
2
.
[
2
2
]
.
I.
Cu
iral
-
Z
u
e
c
o
,
a
n
d
G
.
L
ó
p
e
z
-
Nic
o
lás
,
“
RG
B
-
D
T
ra
c
k
in
g
a
n
d
Op
ti
m
a
l
P
e
rc
e
p
ti
o
n
o
f
De
f
o
r
m
a
b
le
Ob
jec
ts
,
”
IEE
E
Acc
e
ss
,
v
o
l.
8
,
p
p
.
1
3
6
8
8
4
-
1
3
6
8
9
7
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/A
CCES
S
.
2
0
2
0
.
3
0
1
2
0
6
7
.
[
2
3
]
.
G
.
Ch
e
n
,
F
.
Wan
g
,
S
.
Qu
,
K.
C
h
e
n
,
J.
Yu
,
X
.
L
iu
,
L
.
X
io
n
g
,
a
n
d
A
.
Kn
o
ll
,
“
P
se
u
d
o
-
Im
a
g
e
a
n
d
S
p
a
rse
P
o
in
ts:
V
e
h
icle
De
tec
ti
o
n
w
it
h
2
D
L
iD
AR
Re
v
isit
e
d
b
y
D
e
e
p
L
e
a
rn
in
g
-
Ba
se
d
M
e
th
o
d
s,
”
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
In
tell
ig
e
n
t
T
ra
n
sp
o
rta
ti
o
n
S
y
ste
ms
,
d
o
i:
1
0
.
1
1
0
9
/T
IT
S
.
2
0
2
0
.
3
0
0
7
6
3
1
.
[
2
4
]
.
B.
S
a
n
g
io
v
a
n
n
i
,
G
.
P
.
In
c
re
m
o
n
a
,
M
.
P
ias
tra,
a
n
d
A
.
F
e
rra
ra
,
“
S
e
lf
-
Co
n
f
ig
u
rin
g
Ro
b
o
t
P
a
th
P
lan
n
in
g
w
it
h
Ob
sta
c
le
Av
o
id
a
n
c
e
v
ia
De
e
p
Re
in
f
o
rc
e
m
e
n
t
L
e
a
rn
in
g
,
”
IEE
E
Co
n
tro
l
S
y
st
e
ms
L
e
tt
e
rs
,
v
o
l.
5
,
n
o
.
2
,
p
p
.
3
9
7
-
4
0
2
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
0
9
/L
CS
YS.
2
0
2
0
.
3
0
0
2
8
5
2
.
[
2
5
]
.
J.
Ni,
X
.
W
a
n
g
,
M
.
T
a
n
g
,
W
.
cao
,
P
.
S
hi
,
a
n
d
S
.
Y
a
n
g
,
“
A
n
Im
p
ro
v
e
d
Re
a
l
-
ti
m
e
P
a
th
P
lan
n
i
n
g
M
e
th
o
d
Ba
se
d
o
n
Dra
g
o
n
f
l
y
A
l
g
o
rit
h
m
f
o
r
He
tero
g
e
n
e
o
u
s
M
u
l
ti
-
ro
b
o
t
S
y
ste
m
,
”
IEE
E
Acc
e
ss
,
v
o
l.
8
,
p
p
.
1
4
0
5
5
8
-
1
4
0
5
6
8
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/A
CCES
S
.
2
0
2
0
.
3
0
1
2
8
8
6
.
[
2
6
]
.
M
.
Z.
A
l
-
Da
b
a
g
h
,
M
.
H
.
M
o
h
a
m
m
e
d
A
lh
a
b
ib
,
d
a
n
F
.
H.
A
L
-
M
u
k
h
tar,
“
F
a
c
e
Re
c
o
g
n
it
i
o
n
S
y
ste
m
Ba
se
d
o
n
Ke
rn
e
l
Disc
ri
m
in
a
n
t
A
n
a
l
y
sis,
K
-
Ne
a
r
e
s
t
Ne
ig
h
b
o
r
a
n
d
S
u
p
p
o
rt
V
e
c
t
o
r
M
a
c
h
in
e
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Res
e
a
rc
h
a
n
d
En
g
i
n
e
e
rin
g
,
v
o
l.
5
,
n
o
.
3
,
p
p
.
3
3
5
–
3
3
8
,
2
0
1
8
,
d
o
i:
1
0
.
2
1
2
7
6
/i
jre.
2
0
1
8
.
5
.
3
.
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2586
Dev
elo
p
men
t o
f a
d
yn
a
mic
in
t
ellig
en
t reco
g
n
itio
n
s
ystem
fo
r
a
r
ea
l
-
time
tr
a
ck
in
g
r
o
b
o
t
(
Th
a
ir
A
li S
a
lih
)
169
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Dr
.
Th
a
ir
Ali
S
a
li
h
r
e
c
e
i
v
e
d
th
e
M
S
c
.
De
g
re
e
in
Co
m
m
u
n
ica
ti
o
n
e
n
g
in
e
e
rin
g
f
ro
m
th
e
T
e
c
h
n
o
lo
g
y
Un
iv
e
rsit
y
in
1
9
8
6
.
He
re
c
e
iv
e
d
th
e
P
h
.
D.
d
e
g
re
e
in
Co
m
m
u
n
ica
ti
o
n
f
ro
m
th
e
A
lep
p
o
Un
iv
e
rsit
y
in
2
0
1
0
.
C
u
rre
n
tl
y
,
h
e
is
a
L
e
c
tu
re
r
a
t
T
e
c
h
n
ica
l
Co
ll
e
g
e
/M
o
su
l.
His
re
se
a
rc
h
in
tere
sts i
n
c
lu
d
e
sp
re
a
d
s
p
e
c
tru
m
s
y
ste
m
s a
n
d
ro
b
o
ti
c
sy
ste
m
.
M
o
h
a
m
m
e
d
Ta
l
a
l
G
h
a
z
a
l
o
b
tain
e
d
h
is
M
.
S
c
.
d
e
g
re
e
f
ro
m
Co
m
p
u
ter
En
g
in
e
e
rin
g
T
e
c
h
n
o
lo
g
y
,
No
rth
e
rn
T
e
c
h
n
ica
l
Un
iv
e
rsity
,
M
o
su
l
,
Ira
q
in
2
0
1
6
.
His
M
.
S
c
.
th
e
sis
e
n
ti
tl
e
d
:
"
W
h
e
e
lch
a
ir
Ro
b
o
t
Co
n
t
ro
l
Us
in
g
EOG
sig
n
a
l
s"
.
His
r
e
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
th
e
d
e
sig
n
o
f
f
a
c
e
re
c
o
g
n
it
io
n
a
lg
o
rit
h
m
s,
d
e
e
p
lea
rn
in
g
CNN
s
m
o
d
e
ls an
d
o
b
jec
t
d
e
tec
ti
o
n
.
Za
id
G
h
a
n
i
m
M
o
h
a
m
m
e
d
o
b
tain
e
d
h
is
M
.
S
c
.
d
e
g
re
e
f
ro
m
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
T
e
c
h
n
o
lo
g
y
,
No
rth
e
rn
T
e
c
h
n
ica
l
Un
iv
e
rsit
y
,
M
o
su
l
,
Ira
q
i
n
2
0
1
0
.
His
re
se
a
rc
h
in
tere
sts
c
o
n
c
e
rn
e
d
w
it
h
Em
b
e
d
d
e
d
S
y
ste
m
s,
M
icro
c
o
n
tro
ll
e
rs,
A
rti
f
icia
l
In
telli
g
e
n
t
b
a
se
d
o
n
Ne
u
ra
l
n
e
tw
o
rk
,
a
n
d
De
e
p
L
e
a
rn
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.