I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2020
,
p
p
.
1
0
5
3
~
1
0
6
2
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
0
i
1
.
pp
1
0
5
3
-
1
0
6
2
1053
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m/in
d
ex
.
p
h
p
/I
JE
C
E
Ass
ista
nt
ro
bo
t
th
ro
ug
h
deep learn
i
ng
Ro
bin
s
o
n J
i
m
é
nez
-
M
o
re
no
,
J
a
v
ier
O
.
P
inzó
n
-
Are
na
s
,
Césa
r
G
.
P
a
chó
n
-
Su
esc
ún
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
Nu
e
v
a
G
r
a
n
a
d
a
M
il
it
a
ry
Un
iv
e
rsit
y
,
Co
lo
m
b
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
17
,
2
0
1
9
R
ev
i
s
ed
O
ct
1
1
,
2
0
1
9
A
cc
ep
ted
Oct
2
0
,
2
0
1
9
T
h
is
a
rti
c
le
p
re
se
n
ts
a
w
o
rk
o
rien
ted
to
a
ss
isti
v
e
ro
b
o
ti
c
s,
w
h
e
re
a
sc
e
n
a
rio
is
e
sta
b
li
sh
e
d
f
o
r
a
ro
b
o
t
t
o
re
a
c
h
a
to
o
l
in
t
h
e
h
a
n
d
o
f
a
u
se
r
w
h
e
n
th
e
y
h
a
v
e
v
e
rb
a
ll
y
re
q
u
e
ste
d
it
b
y
h
is
n
a
m
e
.
F
o
r
th
is,
th
re
e
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s
a
re
train
e
d
,
o
n
e
f
o
r
re
c
o
g
n
it
io
n
o
f
a
g
ro
u
p
o
f
to
o
ls,
w
h
i
c
h
o
b
tain
e
d
a
n
a
c
c
u
ra
c
y
o
f
9
8
%
id
e
n
ti
fy
in
g
th
e
to
o
ls
e
sta
b
li
sh
e
d
f
o
r
th
e
a
p
p
li
c
a
ti
o
n
,
t
h
a
t
a
re
sc
a
lp
e
l,
sc
re
w
d
riv
e
r
a
n
d
sc
isso
rs;
o
n
e
f
o
r
s
p
e
e
c
h
re
c
o
g
n
it
i
o
n
,
tr
a
in
e
d
w
it
h
th
e
n
a
m
e
s
o
f
th
e
to
o
ls
in
S
p
a
n
i
sh
lan
g
u
a
g
e
,
w
h
e
re
it
s
v
a
li
d
a
ti
o
n
a
c
c
u
ra
c
y
re
a
c
h
es
a
9
7
.
5
%
in
th
e
re
c
o
g
n
it
io
n
o
f
th
e
w
o
rd
s;
a
n
d
a
n
o
t
h
e
r
f
o
r
r
e
c
o
g
n
it
io
n
o
f
th
e
u
se
r'
s
h
a
n
d
,
tak
in
g
in
c
o
n
sid
e
ra
ti
o
n
th
e
c
las
sif
ica
ti
o
n
o
f
2
g
e
stu
re
s:
Op
e
n
a
n
d
Cl
o
se
d
h
a
n
d
,
w
h
e
re
a
9
6
.
2
5
%
a
c
c
u
ra
c
y
w
a
s
a
c
h
iev
e
d
.
W
it
h
th
o
se
n
e
tw
o
rk
s,
tes
ts
in
re
a
l
-
ti
m
e
a
re
p
e
rf
o
r
m
e
d
,
p
re
se
n
ti
n
g
re
su
lt
s
in
t
h
e
d
e
li
v
e
r
y
o
f
e
a
c
h
to
o
l
w
it
h
a
1
0
0
%
o
f
a
c
c
u
ra
c
y
,
i.
e
.
th
e
ro
b
o
t
w
a
s
a
b
le
t
o
id
e
n
ti
f
y
c
o
rre
c
tl
y
w
h
a
t
th
e
u
se
r
re
q
u
e
ste
d
,
re
c
o
g
n
ize
c
o
rre
c
tl
y
e
a
c
h
to
o
l
a
n
d
d
e
li
v
e
r
th
e
o
n
e
n
e
e
d
w
h
e
n
th
e
u
se
r
o
p
e
n
e
d
th
e
ir
h
a
n
d
,
tak
in
g
a
n
a
v
e
ra
g
e
ti
m
e
o
f
4
5
se
c
o
n
d
s in
th
e
e
x
e
c
u
ti
o
n
o
f
th
e
a
p
p
li
c
a
ti
o
n
.
K
ey
w
o
r
d
s
:
3
D
en
v
ir
o
n
m
e
n
t
C
o
n
v
o
lu
tio
n
al
n
e
u
r
al
n
e
t
w
o
r
k
R
o
b
o
tic
ap
p
licatio
n
s
Co
p
y
rig
h
t
©
2
0
2
0
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
o
b
in
s
o
n
J
i
m
én
ez
Mo
r
en
o
,
Me
ch
atr
o
n
ic
s
E
n
g
in
ee
r
i
n
g
P
r
o
g
r
a
m
,
Fac
u
lt
y
o
f
E
n
g
i
n
ee
r
i
n
g
,
Nu
e
v
a
Gr
an
ad
a
Militar
y
Un
i
v
er
s
it
y
,
C
ar
r
er
a
1
1
#
1
0
1
-
8
0
,
B
o
g
o
tá
D
.
C
.
,
C
o
lo
m
b
ia.
E
m
ail:
r
o
b
in
s
o
n
.
j
i
m
en
ez
@
u
n
i
m
ilit
ar
.
ed
u
.
co
1.
I
NT
RO
D
UCT
I
O
N
I
n
r
ec
en
t
y
ea
r
s
,
r
o
b
o
tics
h
as
m
o
v
ed
f
r
o
m
t
h
e
in
d
u
s
tr
ial
en
v
ir
o
n
m
en
t
to
th
e
d
o
m
es
tic,
d
ab
b
lin
g
w
it
h
a
w
id
e
v
ar
iet
y
o
f
ap
p
licatio
n
s
s
u
c
h
as
en
ter
tai
n
m
e
n
t
r
o
b
o
ts
[
1
]
,
p
et
s
itter
s
,
f
lo
o
r
[
2
]
an
d
p
o
o
l
clea
n
er
s
[
3
]
,
la
w
n
m
o
w
er
s
,
an
d
h
ea
lth
ca
r
e
ass
is
tan
t
s
[
4
]
,
am
o
n
g
m
a
n
y
o
th
er
ap
p
licatio
n
s
.
Fo
r
th
is
r
ea
s
o
n
,
w
h
er
e
th
e
i
n
cr
ea
s
e
i
n
h
u
m
an
-
r
o
b
o
t
in
ter
ac
tio
n
i
s
ev
id
en
t,
it
i
s
n
ec
ess
a
r
y
to
d
ev
e
lo
p
tech
n
iq
u
es
t
h
at
p
r
o
v
id
e
s
ec
u
r
it
y
to
o
ls
in
s
aid
i
n
ter
ac
tio
n
[
5
]
.
W
ith
in
t
h
e
f
ield
o
f
h
u
m
an
-
r
o
b
o
t
in
ter
ac
tio
n
,
at
a
n
i
n
d
u
s
tr
ial
lev
el,
d
ev
e
lo
p
m
en
ts
h
av
e
b
ee
n
p
r
esen
ted
to
f
ac
ilit
ate
th
is
ta
s
k
s
a
f
el
y
.
Fo
r
ex
am
p
le,
in
[
6
]
,
t
h
e
d
ev
elo
p
m
e
n
t
o
f
a
co
llab
o
r
ativ
e
en
v
ir
o
n
m
e
n
t
b
ased
o
n
r
estrict
io
n
s
i
s
p
r
esen
ted
s
o
th
at
a
p
er
s
o
n
ca
n
s
h
ar
e
t
h
e
w
o
r
k
ar
ea
w
it
h
a
s
et
o
f
r
o
b
o
tic
ar
m
s
,
s
a
f
el
y
.
T
h
ese
ap
p
licatio
n
s
i
n
v
o
l
v
e
eq
u
ip
p
in
g
th
e
r
o
b
o
t
w
it
h
a
ce
r
tain
d
e
g
r
ee
o
f
ar
tif
i
cial
in
telli
g
e
n
ce
f
o
r
v
ar
io
u
s
ta
s
k
s
,
s
u
ch
a
s
f
i
n
e
co
n
tr
o
l (
Fin
e
m
o
tio
n
)
o
f
t
h
e
s
a
m
e
[
7
]
.
So
m
e
o
f
th
e
s
e
d
ev
e
lo
p
m
en
t
s
e
m
p
lo
y
n
o
n
-
li
n
ea
r
o
p
ti
m
i
za
tio
n
al
g
o
r
ith
m
s
a
n
d
m
ac
h
in
e
v
is
io
n
s
y
s
te
m
s
to
estab
li
s
h
a
s
ec
u
r
e
in
ter
ac
tio
n
s
p
ac
e,
as
d
is
cu
s
s
ed
in
[
8
]
.
A
d
d
itio
n
a
ll
y
,
t
h
e
s
y
s
te
m
s
t
h
at
u
s
e
ar
tif
icial
v
is
io
n
co
m
p
le
m
e
n
t
t
h
is
tas
k
b
y
n
e
u
r
o
n
al
lear
n
i
n
g
,
as
illu
s
tr
ated
in
[
9
]
,
w
h
er
e
th
e
g
en
er
al
f
r
a
m
e
w
o
r
k
o
f
an
a
s
s
i
s
ta
n
t
r
o
b
o
t
b
ased
o
n
ar
ti
f
icial
i
n
tell
ig
e
n
ce
i
s
s
et.
W
ith
i
n
t
h
ese
ar
ti
f
icial
in
te
lli
g
en
ce
tech
n
iq
u
e
s
,
th
e
ap
p
licatio
n
s
o
f
p
atter
n
r
ec
o
g
n
itio
n
th
r
o
u
g
h
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
e
t
w
o
r
k
s
(
C
NN)
ar
e
h
ig
h
li
g
h
ted
,
w
h
ic
h
in
te
g
r
ate
b
o
th
asp
ec
ts
,
id
en
ti
f
i
ca
tio
n
in
i
m
a
g
es (
v
is
io
n
)
an
d
p
atter
n
r
ec
o
g
n
itio
n
[
1
0
]
.
C
NNs
h
a
v
e
s
h
o
w
n
h
i
g
h
p
e
r
f
o
r
m
an
ce
in
th
e
r
ec
o
g
n
it
io
n
o
f
o
b
j
ec
ts
[
1
1
]
an
d
to
d
a
y
s
e
v
er
al
ar
ch
itect
u
r
es
o
f
t
h
is
t
y
p
e
o
f
n
e
t
w
o
r
k
ar
e
ap
p
lied
in
m
ac
h
i
n
e
v
is
io
n
ap
p
licatio
n
s
[
1
2
]
.
So
m
e
ex
a
m
p
le
s
o
f
C
NN
ap
p
licatio
n
ar
e
f
r
a
m
ed
in
f
i
eld
s
s
u
ch
as
te
x
t
c
lass
if
ica
t
io
n
,
w
it
h
w
eb
ap
p
licatio
n
s
[
1
3
]
o
r
s
ig
n
at
u
r
e
r
ec
o
g
n
itio
n
[
1
4
]
,
th
u
s
s
h
o
w
i
n
g
t
h
e
v
er
s
ati
l
it
y
o
f
th
e
s
e
n
et
wo
r
k
s
i
n
p
atter
n
r
ec
o
g
n
itio
n
.
H
o
w
e
v
er
,
v
ar
iatio
n
s
o
f
C
NN
b
ase
ar
c
h
itect
u
r
es
ar
e
s
t
ill
b
ein
g
d
ev
elo
p
ed
in
o
r
d
er
to
i
m
p
r
o
v
e
asp
ec
t
s
o
f
lear
n
i
n
g
,
s
u
c
h
as
th
e
ca
s
e
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
1
0
5
3
-
1
0
6
2
1054
v
ar
iatio
n
s
in
th
e
d
ep
th
at
w
h
ich
t
h
e
o
b
j
ec
ts
ar
e,
as
s
h
o
w
n
in
[
1
5
,
1
6
]
.
I
n
tu
r
n
,
m
an
y
f
i
eld
s
o
f
ap
p
licatio
n
r
eq
u
ir
e
v
ir
tu
a
l
test
en
v
ir
o
n
m
en
ts
i
n
o
r
d
er
to
v
alid
ate
t
h
e
alg
o
r
ith
m
s
to
b
e
u
s
ed
[
1
7
]
,
w
h
er
e
C
NNs
al
s
o
f
ac
ilit
ate
th
is
ta
s
k
f
o
r
r
o
b
o
tic
s
y
s
te
m
s
,
as
s
et
o
u
t
i
n
[
1
8
]
.
Ho
w
e
v
er
,
in
t
h
e
ar
ea
o
f
r
o
b
o
tics
,
s
o
m
e
w
o
r
k
s
h
a
v
e
j
u
s
t
s
tar
ted
to
b
e
d
e
v
elo
p
ed
w
it
h
th
i
s
tec
h
n
iq
u
e.
Fo
r
ex
a
m
p
le,
i
n
[
1
9
,
2
0
]
o
b
j
ec
t
g
r
ip
p
in
g
a
lg
o
r
i
t
h
m
s
ar
e
d
ev
elo
p
ed
b
y
m
ea
n
s
o
f
a
r
o
b
o
tic
m
a
n
ip
u
lato
r
,
p
er
f
o
r
m
i
n
g
r
ec
o
g
n
itio
n
b
y
C
NN.
An
d
in
th
e
ar
ea
o
f
h
u
m
a
n
-
r
o
b
o
t
in
ter
ac
tio
n
o
f
th
e
f
e
w
d
ev
elo
p
m
e
n
ts
f
o
u
n
d
,
i
s
t
h
e
o
n
e
p
r
esen
ted
in
[
2
1
]
,
w
h
er
e
th
e
y
d
e
s
cr
ib
e
th
e
d
ev
elo
p
m
e
n
t
o
f
a
s
o
cial
r
o
b
o
t
f
o
r
in
ter
ac
tio
n
in
a
d
o
m
e
s
tic
en
v
ir
o
n
m
e
n
t.
An
o
th
er
ar
ea
o
f
in
ter
est
ad
d
r
ess
ed
in
t
h
is
ar
t
icle
is
t
h
e
u
s
e
o
f
C
NN
s
f
o
r
s
p
ee
ch
r
ec
o
g
n
i
tio
n
[
2
2
]
,
d
e
m
o
n
s
tr
atin
g
t
h
e
v
er
s
ati
lit
y
o
f
th
i
s
n
et
w
o
r
k
f
o
r
a
w
id
e
r
an
g
e
o
f
a
p
p
li
ca
tio
n
s
.
Du
e
to
t
h
e
g
r
ea
t
v
er
s
a
tili
t
y
an
d
ef
f
icie
n
c
y
o
f
t
h
e
C
NN,
in
t
h
e
p
r
esen
t
p
ap
er
,
th
ese
a
r
e
u
s
ed
i
n
th
e
o
p
er
atio
n
o
f
an
ass
is
ta
n
t
r
o
b
o
t
ar
m
.
Said
ar
m
i
s
co
m
m
an
d
ed
b
y
th
e
tr
ain
in
g
o
f
t
h
r
ee
C
NN
n
et
w
o
r
k
s
,
o
n
e
f
o
r
id
en
ti
f
icatio
n
o
f
a
g
r
o
u
p
o
f
th
r
ee
to
o
l
s
,
a
n
o
th
er
f
o
r
s
p
ee
ch
r
ec
o
g
n
itio
n
a
n
d
an
o
t
h
e
r
f
o
r
id
en
tific
atio
n
of
th
e
u
s
er
'
s
h
an
d
.
T
h
e
ass
i
s
t
an
ce
s
y
s
te
m
w
ill
b
e
ab
le
to
lis
ten
to
w
h
at
to
o
l
is
d
esire
d
,
id
en
tify
it
w
it
h
i
n
a
g
r
o
u
p
,
tak
e
it a
n
d
d
eliv
er
it i
n
th
e
h
a
n
d
,
if
it i
s
o
p
en
,
o
f
a
u
s
er
.
T
h
is
ar
ticl
e
is
d
iv
id
ed
i
n
to
4
s
ec
tio
n
s
.
Sectio
n
t
w
o
s
h
o
w
s
t
h
e
C
NN
ar
ch
itec
tu
r
es
d
e
v
elo
p
ed
an
d
i
m
p
le
m
e
n
ted
i
n
t
h
is
w
o
r
k
.
Sectio
n
3
s
h
o
w
s
t
h
e
r
es
u
lt
s
o
b
tain
ed
an
d
th
e
r
esp
ec
tiv
e
a
n
al
y
s
i
s
.
I
n
s
ec
tio
n
4
,
th
e
d
er
iv
e
d
co
n
clu
s
io
n
s
ar
e
p
r
esen
ted
.
2.
CNN
ARCH
I
T
E
CT
U
RE
S
T
h
e
p
r
o
p
o
s
ed
elem
e
n
ts
t
h
at
m
ak
e
u
p
t
h
e
co
m
p
lete
i
m
p
le
m
e
n
tatio
n
o
f
t
h
e
ass
is
ta
n
t
r
o
b
o
t
is
p
r
esen
ted
in
F
ig
u
r
e
1
.
I
t
co
n
s
i
s
ts
o
f
a
u
s
er
th
at
v
er
b
all
y
i
n
d
icate
s
th
e
d
esire
d
to
o
l
s
o
t
h
at
th
r
o
u
g
h
a
s
u
p
er
v
is
o
r
y
ca
m
er
a,
w
h
ic
h
ta
k
es
t
h
e
to
p
v
ie
w
o
f
th
e
s
ce
n
e,
a
n
d
w
it
h
t
h
is
,
th
e
to
o
l
an
d
t
h
e
u
s
er
's
h
an
d
ar
e
ca
p
tu
r
ed
.
T
h
e
id
en
tif
icat
io
n
o
f
th
e
s
p
ee
ch
co
m
m
a
n
d
,
th
e
to
o
l,
an
d
t
h
e
h
an
d
i
s
d
o
n
e
t
h
r
o
u
g
h
t
h
e
u
s
e
o
f
C
NN.
T
h
is
t
y
p
e
o
f
n
et
w
o
r
k
in
v
o
l
v
es
th
e
ca
lc
u
latio
n
o
f
p
ar
ticu
lar
ar
ch
itec
t
u
r
es
b
ased
o
n
lay
er
s
o
f
th
e
C
o
n
v
o
lu
tio
n
-
R
e
L
U
-
P
o
o
lin
g
s
ets
[
8
]
.
Her
e,
th
e
in
p
u
t
v
o
l
u
m
e
f
o
r
th
e
in
iti
al
la
y
er
co
r
r
esp
o
n
d
s
to
m
atr
ices
th
at
co
n
tai
n
th
e
lear
n
in
g
p
atter
n
s
,
f
o
r
th
e
ca
s
e,
i
m
ag
e
s
,
an
d
a
u
d
io
in
f
o
r
m
at
io
n
,
u
s
i
n
g
th
r
ee
co
m
p
o
n
en
t
s
f
o
r
ea
ch
o
n
e
(
d
ep
th
)
.
Ho
w
ev
er
,
w
h
e
n
t
h
e
v
o
lu
m
e
p
a
s
s
es
th
r
o
u
g
h
t
h
e
n
ex
t
la
y
er
s
,
i
t
v
ar
ie
s
it
s
s
ize,
f
o
r
t
h
at
r
ea
s
o
n
,
th
e
(
1
)
to
(
3
)
illu
s
tr
ate
h
o
w
to
ca
lcu
la
te
th
e
v
o
l
u
m
es
f
o
r
th
e
f
o
llo
w
i
n
g
la
y
er
s
.
(
1
)
(
2
)
(
3
)
I
n
t
h
e
eq
u
at
io
n
s
,
n
an
d
n
+1
a
r
e
th
e
i
n
p
u
t
a
n
d
o
u
tp
u
t
v
o
lu
m
e,
r
esp
ec
ti
v
el
y
,
W
is
t
h
e
w
i
d
th
a
n
d
H,
th
e
h
ei
g
h
t
o
f
t
h
e
in
p
u
t
i
m
ag
e
o
f
la
y
er
n
,
P
is
th
e
ze
r
o
p
ad
d
in
g
,
F
i
s
th
e
s
ize
o
f
th
e
f
ilte
r
o
r
k
er
n
el
an
d
S,
th
e
s
tep
o
f
th
e
f
ilter
s
.
I
n
(
3
)
,
D
r
ep
r
esen
ts
h
o
w
d
ee
p
th
e
lay
er
is
a
n
d
K
,
th
e
n
u
m
b
er
o
f
f
ilter
s
u
s
ed
in
la
y
er
n
[
2
3
]
.
Fig
u
r
e
1
.
E
le
m
en
t
s
t
h
at
ar
e
p
ar
t o
f
th
e
w
o
r
k
2
.
1
.
I
m
ple
m
e
nte
d a
rc
hite
ct
u
re
s
Fo
r
th
e
d
e
s
ig
n
o
f
th
e
C
N
N
ar
c
h
itect
u
r
es,
t
h
r
ee
d
atab
ase
s
w
er
e
b
u
ilt
ac
co
r
d
in
g
to
t
h
e
a
f
o
r
em
en
tio
n
ed
ele
m
e
n
ts
.
Nex
t,
th
e
ch
ar
ac
t
er
is
tics
o
f
ea
c
h
ar
c
h
itect
u
r
e
i
m
p
le
m
e
n
ted
w
it
h
i
ts
r
esp
ec
tiv
e
d
atab
ase
ar
e
p
r
esen
ted
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
A
s
s
is
ta
n
t ro
b
o
t th
r
o
u
g
h
d
ee
p
l
ea
r
n
in
g
(
R
o
b
in
s
o
n
Jimé
n
ez
-
M
o
r
en
o
)
1055
2
.
1
.
1
Arc
hite
ct
ure
1
(
s
peec
h
)
T
h
e
d
atab
ase
co
n
s
is
ts
o
f
3
S
p
an
is
h
w
o
r
d
s
(
“
b
is
tu
r
í”
(
s
ca
l
p
el)
,
“
d
esto
r
n
illad
o
r
”
(
s
cr
e
w
d
r
iv
er
)
an
d
“
tij
er
as”
(
s
ciss
o
r
s
)
)
,
th
at
ar
e
th
e
to
o
ls
to
b
e
u
s
ed
,
f
r
o
m
wh
ich
5
5
r
ec
o
r
d
in
g
s
p
er
w
o
r
d
w
er
e
ta
k
en
f
r
o
m
d
if
f
er
e
n
t
u
s
er
s
,
ea
ch
au
d
io
i
s
2
s
ec
o
n
d
s
lo
n
g
.
T
h
e
d
atab
ase
is
d
iv
id
ed
in
to
2
s
e
ts
,
o
n
e
f
o
r
tr
ain
i
n
g
w
it
h
a
to
ta
l
o
f
3
7
5
au
d
io
s
,
an
d
o
n
e
f
o
r
v
alid
atio
n
w
i
th
9
0
s
a
m
p
les.
E
ac
h
au
d
io
is
ac
q
u
ir
ed
w
it
h
a
s
a
m
p
lin
g
f
r
eq
u
en
c
y
o
f
1
6
0
0
0
Hz
.
Fo
r
th
is
,
ex
tr
ac
ti
o
n
o
f
f
ea
tu
r
es
o
f
ea
ch
a
u
d
io
s
i
g
n
al
is
d
o
n
e,
i
n
o
r
d
er
to
o
b
tai
n
a
m
ap
t
h
at
allo
ws
s
ee
in
g
t
h
e
b
eh
av
io
r
o
f
th
e
s
ig
n
al
th
r
o
u
g
h
ti
m
e
at
d
i
f
f
er
en
t
f
r
eq
u
en
cie
s
.
T
h
is
ex
tr
ac
tio
n
is
ca
r
r
ied
o
u
t b
y
m
ea
n
s
o
f
an
ap
p
r
o
x
i
m
atio
n
o
f
t
h
e
M
F
C
C
o
b
tain
ed
b
y
t
h
e
Hid
d
en
Ma
r
k
o
v
Mo
d
el
T
o
o
lk
it
[
2
4
]
,
u
s
in
g
(
4
)
,
w
h
er
e
C
is
th
e
n
u
m
b
er
o
f
ce
p
s
tr
al
co
ef
f
ic
ien
ts
,
i
n
th
is
ca
s
e
,
is
1
3
;
M
is
th
e
n
u
m
b
er
o
f
f
ilter
ch
a
n
n
els
,
w
h
o
s
e
v
a
lu
e
i
s
2
0
;
L
is
th
e
v
al
u
e
r
esp
o
n
s
ib
le
f
o
r
in
cr
e
m
e
n
t
i
n
g
t
h
e
ce
p
s
tr
al
v
al
u
es,
u
s
in
g
a
v
al
u
e
o
f
L=2
2
,
w
h
ic
h
is
n
o
r
m
al
l
y
u
s
ed
to
g
e
n
er
ate
a
g
o
o
d
f
r
o
n
t
-
en
d
p
ar
a
m
eter
izatio
n
i
n
s
p
ee
c
h
r
ec
o
g
n
itio
n
s
y
s
te
m
s
;
a
n
d
m
j
is
th
e
lo
g
ar
it
h
m
o
f
th
e
m
a
g
n
it
u
d
e
s
p
ec
tr
u
m
.
A
f
ea
tu
r
e
m
ap
as
t
h
e
o
n
e
s
h
o
wn
in
Fig
u
r
e
2
is
o
b
tain
ed
,
an
d
,
f
o
r
r
o
b
u
s
tn
es
s
p
u
r
p
o
s
es
in
ter
m
s
o
f
t
h
e
n
et
wo
r
k
lear
n
in
g
,
its
f
ir
s
t
a
n
d
s
ec
o
n
d
d
er
iv
ativ
es
ar
e
ad
d
ed
to
t
h
e
m
atr
i
x
,
f
o
r
m
in
g
a
th
r
ee
-
c
h
an
n
el
i
n
p
u
t
v
o
lu
m
e.
(
(
)
)
√
∑
(
(
)
)
(
4
)
Fig
u
r
e
2
.
E
x
a
m
p
le
o
f
a
n
au
d
io
s
ig
n
al
f
r
o
m
th
e
d
atab
ase
a
n
d
th
e
MF
C
C
o
b
tain
ed
T
ab
le
1
s
h
o
w
s
t
h
e
ar
ch
i
tectu
r
e
u
s
ed
,
w
h
ic
h
i
s
b
ased
o
n
a
p
r
ev
io
u
s
d
e
v
elo
p
m
e
n
t
[
2
5
]
.
T
h
is
co
n
s
is
t
s
o
f
3
s
et
s
o
f
C
o
n
v
o
lu
tio
n
-
C
o
n
v
o
l
u
tio
n
-
P
o
o
lin
g
,
w
it
h
s
q
u
a
r
e
f
ilter
s
i
n
o
r
d
e
r
to
allo
w
t
h
e
n
et
w
o
r
k
to
lear
n
th
e
b
eh
a
v
io
r
o
f
th
e
w
o
r
d
s
i
n
ter
m
s
o
f
ti
m
e
a
n
d
f
r
eq
u
e
n
c
y
at
th
e
s
a
m
e
ti
m
e.
T
h
e
s
e
co
n
d
p
ar
a
m
et
er
o
f
th
e
k
er
n
el
i
s
g
i
v
e
n
as
S
/P
,
w
h
er
e
S
is
t
h
e
s
tr
id
e
o
f
th
e
m
o
v
e
m
e
n
t
o
f
th
e
f
ilter
a
n
d
P
is
th
e
ze
r
o
-
p
ad
d
in
g
ap
p
lied
to
th
e
in
p
u
t
v
o
lu
m
e.
I
n
ad
d
itio
n
,
2
f
u
ll
y
co
n
n
ec
te
d
lay
er
s
ar
e
ad
d
ed
,
allo
w
i
n
g
a
b
etter
lear
n
in
g
o
f
th
e
co
m
b
in
a
tio
n
o
f
t
h
e
d
if
f
er
en
t
f
ea
t
u
r
es.
Si
n
ce
in
MF
C
C
,
co
ef
f
icie
n
t
v
alu
e
s
h
a
v
e
v
ar
iatio
n
b
o
th
n
eg
a
tiv
e
a
n
d
p
o
s
itiv
e,
th
e
ac
ti
v
atio
n
f
u
n
ct
io
n
R
e
L
U
is
n
o
t
u
s
ed
,
in
o
r
d
er
to
k
ee
p
n
eg
ati
v
e
v
al
u
es.
W
ith
t
h
e
ar
ch
itect
u
r
e
an
d
th
e
d
atab
ase
b
u
i
lt,
th
e
tr
ai
n
in
g
i
s
p
er
f
o
r
m
ed
f
o
r
5
0
0
ep
o
ch
s
,
ac
h
ie
v
i
n
g
a
9
7
.
5
%
ac
cu
r
ac
y
w
it
h
th
e
v
al
id
atio
n
s
et.
T
ab
le
1
.
C
NN
A
r
ch
i
tectu
r
e
f
o
r
s
p
ee
ch
L
a
y
e
r
K
e
r
n
e
l
F
i
l
t
e
r
s
I
n
p
u
t
1
2
x
1
9
9
x
3
-
C
o
n
v
o
l
u
t
i
o
n
5
x
5
1
/
2
32
C
o
n
v
o
l
u
t
i
o
n
5
x
5
1
/
2
32
M
a
x
P
o
o
l
i
n
g
2
x
1
2
/
0
-
C
o
n
v
o
l
u
t
i
o
n
3
x
3
1
/
1
64
C
o
n
v
o
l
u
t
i
o
n
3
x
3
1
/
1
64
M
a
x
P
o
o
l
i
n
g
2
x
3
2
/
0
-
C
o
n
v
o
l
u
t
i
o
n
2
x
2
1
/
1
1
2
8
C
o
n
v
o
l
u
t
i
o
n
3
x
3
1
/
1
1
2
8
M
a
x
P
o
o
l
i
n
g
2
x
2
2
/
0
-
F
u
l
l
y
-
C
o
n
n
e
c
t
e
d
1
5
1
2
F
u
l
l
y
-
C
o
n
n
e
c
t
e
d
1
2
0
4
8
F
u
l
l
y
-
C
o
n
n
e
c
t
e
d
1
3
S
o
f
t
max
3
-
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
1
0
5
3
-
1
0
6
2
1056
2
.
1
.
2
.
Arc
hite
ct
ure
2
(
ha
nd
)
Fo
r
th
e
r
ec
o
g
n
itio
n
o
f
t
h
e
h
a
n
d
,
th
er
e
w
er
e
e
s
tab
lis
h
ed
2
ca
teg
o
r
ie
s
:
Op
e
n
an
d
C
lo
s
ed
,
s
in
ce
it
i
s
w
a
n
ted
to
k
n
o
w
th
e
s
e
t
w
o
g
estu
r
es.
W
it
h
th
i
s
,
a
d
ataset
w
a
s
b
u
ilt,
co
n
s
i
s
ti
n
g
o
f
1
9
0
0
i
m
ag
e
s
,
w
h
ic
h
w
as
d
iv
id
ed
to
h
av
e
a
s
et
f
o
r
tr
ain
i
n
g
a
n
d
an
o
t
h
er
f
o
r
v
a
lid
ated
th
e
n
et
w
o
r
k
p
er
f
o
r
m
a
n
ce
.
Fo
r
t
r
ain
in
g
,
7
0
0
i
m
a
g
es
o
f
th
e
o
p
en
h
a
n
d
an
d
7
0
0
o
f
th
e
clo
s
ed
h
a
n
d
w
er
e
ta
k
en
,
an
d
f
o
r
v
al
id
atio
n
,
2
5
0
i
m
ag
e
s
o
f
ea
c
h
ca
teg
o
r
y
w
er
e
u
s
ed
.
T
h
e
ar
ch
i
tectu
r
e
p
r
o
p
o
s
ed
is
b
ased
o
n
p
r
ev
io
u
s
w
o
r
k
,
s
h
o
w
n
in
[
2
3
]
an
d
th
at
ca
n
b
e
s
ee
n
in
T
ab
le
2
.
I
t
s
h
o
u
ld
b
e
h
i
g
h
lig
h
t
ed
t
h
at
ea
c
h
co
n
v
o
l
u
ti
o
n
an
d
f
u
l
l
y
co
n
n
ec
ted
h
a
v
e
a
R
e
L
U
la
y
er
.
T
h
is
ar
ch
itect
u
r
e,
af
ter
b
ein
g
t
r
ain
ed
,
ac
h
iev
ed
a
n
ac
cu
r
ac
y
o
f
9
6
.
2
5
% in
th
e
class
i
f
ica
tio
n
o
f
b
o
th
g
est
u
r
es.
T
ab
le
2
.
C
NN
A
r
ch
i
tectu
r
e
f
o
r
h
an
d
g
e
s
tu
r
e
L
a
y
e
r
K
e
r
n
e
l
F
i
l
t
e
r
s
I
n
p
u
t
6
4
x
6
4
x
3
-
C
o
n
v
o
l
u
t
i
o
n
4
x
4
1
/
2
20
C
o
n
v
o
l
u
t
i
o
n
4
x
4
1
/
0
20
Ma
x
Po
o
l
i
n
g
2
x
2
2
/
1
-
C
o
n
v
o
l
u
t
i
o
n
5
x
5
1
/
0
50
C
o
n
v
o
l
u
t
i
o
n
5
x
5
1
/
0
50
Ma
x
Po
o
l
i
n
g
2
x
2
2
/
0
-
C
o
n
v
o
l
u
t
i
o
n
4
x
4
1
/
0
2
0
0
Ma
x
Po
o
l
i
n
g
3
x
3
2
/
0
-
Fu
l
l
y
-
C
o
n
n
e
c
t
e
d
1
2
0
0
Fu
l
l
y
-
C
o
n
n
e
c
t
e
d
1
2
S
o
f
t
m
a
x
2
-
T
o
im
p
r
o
v
e
t
h
e
r
ec
o
g
n
itio
n
o
f
th
e
g
es
tu
r
es,
a
p
r
ep
r
o
ce
s
s
in
g
alg
o
r
ith
m
w
a
s
ap
p
lied
,
w
h
er
e
b
y
m
ea
n
s
o
f
ac
q
u
i
s
itio
n
o
f
th
e
m
ea
n
o
f
th
e
b
ac
k
g
r
o
u
n
d
a
n
d
m
o
r
p
h
o
lo
g
ic
f
ilter
s
,
th
e
lo
ca
tio
n
o
f
t
h
e
h
a
n
d
is
o
b
tain
ed
,
in
s
u
ch
a
w
a
y
th
at
t
h
e
alg
o
r
it
h
m
g
e
n
er
ates
a
b
o
u
n
d
i
n
g
b
o
x
o
f
th
e
n
e
w
o
b
j
ec
t
in
th
e
s
ce
n
e.
T
h
en
,
it
is
cr
o
p
p
e
d
an
d
,
d
ep
en
d
in
g
o
n
t
h
e
g
r
ea
ter
v
alu
e
o
f
t
h
e
b
o
x
s
id
e,
th
e
cr
o
p
p
e
d
i
m
a
g
e
i
s
p
asted
i
n
a
w
h
ite
s
q
u
ar
e,
to
th
e
b
ein
g
e
n
ter
ed
to
t
h
e
n
et
w
o
r
k
f
o
r
i
ts
r
ec
o
g
n
i
tio
n
.
T
h
e
f
i
n
al
r
es
u
lt
o
f
t
h
e
r
ec
o
g
n
itio
n
i
s
s
h
o
w
n
i
n
Fig
u
r
e
3
,
w
h
er
e
th
e
y
el
lo
w
b
o
x
is
th
e
f
ir
s
t
b
o
u
n
d
i
n
g
b
o
x
f
o
u
n
d
.
A
d
d
itio
n
all
y
,
t
h
e
n
u
m
b
er
g
iv
e
n
in
th
e
b
o
x
is
th
e
co
n
f
id
e
n
ce
o
f
t
h
e
n
et
w
o
r
k
w
it
h
r
esp
ec
t to
t
h
e
g
e
s
tu
r
e
r
ec
o
g
n
ized
,
w
h
er
e
t
h
e
h
i
g
h
e
f
f
ici
en
c
y
o
f
th
e
s
u
cc
es
s
is
ev
id
e
n
t
.
Fig
u
r
e
3
.
Han
d
r
ec
o
g
n
itio
n
2
.
1
.
3
.
Arc
hite
ct
ure
3
(
t
o
o
ls
)
T
h
e
th
ir
d
ar
ch
itec
tu
r
e
i
s
r
esp
o
n
s
ib
le
f
o
r
id
en
ti
f
y
i
n
g
t
h
e
t
h
r
ee
to
o
ls
to
b
e
u
s
ed
.
Fo
r
t
h
e
n
et
w
o
r
k
tr
ain
i
n
g
,
i
t
i
s
b
u
il
t
a
d
atab
as
e
th
at
is
co
m
p
o
s
ed
o
f
7
0
0
i
m
ag
e
s
.
D
u
e
to
t
h
e
f
ac
t
th
a
t
t
h
e
to
o
ls
h
a
v
e
m
o
r
e
f
ea
t
u
r
es
to
b
e
lear
n
ed
an
d
th
e
n
ee
d
o
f
d
if
f
er
en
tiati
n
g
s
o
m
e
o
f
th
e
s
i
m
ilar
ities
t
h
at
t
h
e
to
o
ls
h
av
e,
it
w
as
d
ec
id
ed
to
u
s
e
a
b
ig
g
er
i
m
a
g
e
s
ize,
th
at
f
o
r
th
is
ca
s
e,
it
w
as
1
2
8
x
1
2
8
p
ix
els
in
R
GB
s
ca
le.
T
o
allo
w
th
e
n
et
w
o
r
k
to
lear
n
g
lo
b
al
f
e
atu
r
es
o
f
t
h
e
to
o
ls
,
s
u
c
h
as
ed
g
es
a
n
d
s
h
ap
es,
t
h
e
f
ilter
s
ar
e
p
r
o
p
o
s
ed
w
it
h
s
izes
b
ig
g
er
th
a
n
t
h
e
n
o
r
m
al
l
y
u
s
ed
,
as
th
e
p
r
ev
io
u
s
n
et
w
o
r
k
.
I
n
t
h
is
ca
s
e,
f
ilter
s
t
h
at
v
ar
y
th
e
ir
s
izes
f
r
o
m
7
x
7
to
1
2
x
1
2
ar
e
u
s
ed
.
I
n
ad
d
itio
n
,
ea
ch
co
n
v
o
lu
tio
n
la
y
er
h
as
a
n
ac
ti
v
atio
n
f
u
n
ctio
n
o
f
R
e
L
U.
T
h
e
ar
ch
itect
u
r
e
p
r
o
p
o
s
ed
is
s
h
o
w
n
in
T
ab
le
3
.
Fig
u
r
e
4
illu
s
tr
ates
t
h
e
r
esu
lt
o
f
th
e
n
et
w
o
r
k
a
n
d
th
e
m
ai
n
ac
tiv
atio
n
s
o
b
tain
ed
,
th
ese
allo
w
to
d
e
m
o
n
s
tr
ate
t
h
e
clea
r
lear
n
in
g
o
f
ea
c
h
to
o
l,
w
h
er
e
an
ac
c
u
r
ac
y
o
f
9
8
%
o
f
ac
cu
r
ac
y
i
n
th
e
clas
s
i
f
icatio
n
o
f
t
h
e
t
h
r
ee
class
es
w
a
s
o
b
tain
ed
af
ter
it
s
tr
ain
i
n
g
w
i
th
t
h
e
d
atab
ase
b
u
ilt
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
A
s
s
is
ta
n
t ro
b
o
t th
r
o
u
g
h
d
ee
p
l
ea
r
n
in
g
(
R
o
b
in
s
o
n
Jimé
n
ez
-
M
o
r
en
o
)
1057
T
ab
le
3
.
C
NN
a
r
ch
itectu
r
e
f
o
r
t
ool
L
a
y
e
r
K
e
r
n
e
l
F
i
l
t
e
r
s
I
n
p
u
t
1
2
8
x
1
2
8
x
3
-
C
o
n
v
o
l
u
t
i
o
n
1
2
x
1
2
1
/
0
20
C
o
n
v
o
l
u
t
i
o
n
1
1
x
1
1
1
/
0
40
Ma
x
Po
o
l
i
n
g
3
x
3
2
/
0
-
C
o
n
v
o
l
u
t
i
o
n
1
0
x
1
0
1
/
0
80
C
o
n
v
o
l
u
t
i
o
n
9
x
9
1
/
0
1
6
0
Ma
x
Po
o
l
i
n
g
2
x
2
2
/
0
-
C
o
n
v
o
l
u
t
i
o
n
8
x
8
1
/
0
1
8
0
C
o
n
v
o
l
u
t
i
o
n
7
x
7
1
/
0
2
0
0
Fu
l
l
y
-
C
o
n
n
e
c
t
e
d
1
2
0
0
Fu
l
l
y
-
C
o
n
n
e
c
t
e
d
1
3
S
o
f
t
m
a
x
3
-
Fig
u
r
e
4
.
R
ec
o
g
n
i
tio
n
o
f
to
o
ls
2
.
2
.
K
inem
a
t
ic
m
o
del o
f
t
he
ro
bo
t
T
h
e
k
in
e
m
atic
m
o
d
el
o
f
t
h
e
ar
m
i
s
r
eq
u
ir
ed
to
b
e
ab
le
to
est
ab
lis
h
t
h
e
d
i
s
p
lace
m
e
n
t
o
f
t
h
is
w
ith
in
it
s
w
o
r
k
s
p
ac
e,
in
w
h
ich
b
o
th
t
h
e
to
o
ls
a
n
d
t
h
e
u
s
er
'
s
h
a
n
d
ar
e
lo
ca
ted
.
I
n
Fi
g
u
r
e
5
,
it
ca
n
b
e
o
b
s
er
v
ed
th
e
g
eo
m
etr
ic
m
o
d
el
th
at
allo
w
s
i
n
f
er
r
in
g
(
5
)
to
(
14
)
,
th
r
o
u
g
h
w
h
ic
h
it
ca
n
b
e
s
et
th
e
an
g
u
lar
m
o
v
e
m
e
n
ts
o
f
th
e
r
o
b
o
t.
Fro
m
th
e
to
p
v
ie
w
,
t
h
e
an
g
le
o
f
j
o
in
t 1
(
)
an
d
t
h
e
X
co
m
p
o
n
en
t o
f
p
o
in
t P
o
f
t
h
e
f
i
n
al
e
f
f
ec
to
r
ar
e
o
b
s
er
v
ed
,
th
r
o
u
g
h
w
h
ich
(
5
)
an
d
(
6
)
ar
e
estab
lis
h
ed
.
√
(
5
)
(
6
)
Fig
u
r
e
5
.
Kin
e
m
atics o
f
th
e
r
o
b
o
tic
ar
m
B
y
m
ea
n
s
o
f
t
h
e
f
r
o
n
ta
l
v
ie
w
,
th
e
a
n
g
le
s
o
f
j
o
in
t
s
2
an
d
3
ar
e
o
b
tain
ed
,
ca
lcu
lati
n
g
t
h
e
l
en
g
t
h
"
d
"
,
an
d
th
e
an
g
le
α
th
r
o
u
g
h
(
7
)
to
(
10
)
,
th
u
s
d
eter
m
in
in
g
t
h
e
an
g
le
o
f
j
o
in
t 3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
1
0
5
3
-
1
0
6
2
1058
√
(
)
(
7
)
(
8
)
√
(
9
)
(
√
)
(
1
0
)
T
h
e
an
g
le
o
f
j
o
in
t
2
is
ca
lcu
la
ted
u
s
i
n
g
β
a
n
d
α
u
s
i
n
g
(
11
)
an
d
(
13
)
.
Sin
ce
th
e
an
g
le
o
f
th
e
s
ec
o
n
d
j
o
in
t
ca
n
h
a
v
e
t
w
o
d
i
f
f
er
en
t
v
alu
es,
d
ep
en
d
i
n
g
o
n
t
h
e
g
r
ip
o
f
t
h
e
m
a
n
ip
u
lato
r
u
s
in
g
e
lb
o
w
u
p
o
r
elb
o
w
d
o
w
n
,
th
e
(
1
4
)
is
u
s
ed
.
(
1
1
)
(
1
2
)
(
1
3
)
{
|
|
|
|
(
1
4
)
W
ith
t
h
ese
p
ar
a
m
eter
s
,
it
i
s
p
o
s
s
ib
le
to
co
n
tr
o
l
t
h
e
m
o
v
e
m
e
n
t
o
f
t
h
e
r
o
b
o
t,
wh
er
e,
o
n
ce
o
b
tai
n
ed
th
e
p
o
s
itio
n
s
o
f
th
e
g
eo
m
etr
i
c
ce
n
ter
o
f
th
e
to
o
l
an
d
th
e
h
an
d
,
th
eta
an
g
les
ar
e
s
et
i
n
o
r
d
er
to
r
ea
ch
th
o
s
e
p
o
s
itio
n
s
,
tak
in
g
i
n
to
ac
co
u
n
t
th
at
t
h
e
r
ef
er
en
ce
i
s
th
e
r
o
b
o
t b
ase
.
3.
E
XP
E
R
I
M
E
NT
A
L
RE
SUL
T
S
T
h
e
ap
p
licatio
n
s
tar
ts
b
y
s
a
y
i
n
g
t
h
e
d
esire
d
to
o
l,
i.e
.
th
e
u
s
er
s
tar
ts
th
e
r
ec
o
r
d
in
g
,
w
h
er
e
th
eir
v
o
ice
is
ca
p
tu
r
ed
.
Af
ter
2
s
ec
o
n
d
s
,
th
e
v
o
ice
s
i
g
n
al
is
s
en
t
to
th
e
p
r
o
ce
s
s
in
g
al
g
o
r
ith
m
to
t
h
en
b
e
en
ter
ed
to
th
e
C
NN
f
o
r
s
p
ee
ch
.
On
ce
t
h
e
n
et
w
o
r
k
r
ec
o
g
n
ize
s
th
e
w
o
r
d
,
th
e
u
s
er
d
ec
id
es
if
it
w
as
co
r
r
ec
tl
y
r
ec
o
g
n
ized
o
r
n
o
t.
I
f
n
o
t,
it
r
etak
e
s
t
h
e
au
d
io
.
I
f
s
o
,
th
e
alg
o
r
ith
m
p
r
o
ce
ed
s
to
id
en
tify
th
e
to
o
l
r
eq
u
este
d
,
tak
i
n
g
a
ca
p
tu
r
e
o
f
th
e
to
o
ls
an
d
th
e
n
s
e
n
d
it
to
th
e
C
N
N
f
o
r
to
o
ls
.
W
h
en
t
h
e
o
n
e
w
a
n
ted
is
id
en
t
if
ied
an
d
lo
ca
ted
,
th
e
r
o
b
o
t
tak
es
it.
I
n
o
r
d
er
to
d
eliv
er
th
e
o
b
j
ec
t,
th
e
u
s
er
p
u
t
h
is
h
a
n
d
in
f
r
o
n
t
o
f
t
h
e
ca
m
er
a,
i
n
o
r
d
er
to
ca
p
tu
r
e
it
an
d
r
ec
o
g
n
ize
i
f
it
is
o
p
en
o
r
clo
s
e
d
.
W
h
en
i
t
id
e
n
ti
f
ies
th
e
o
p
en
h
an
d
f
o
r
2
s
ec
o
n
d
s
,
t
h
e
r
o
b
o
t
d
eliv
er
s
t
h
e
o
b
j
ec
t
to
th
e
p
o
s
itio
n
o
f
t
h
e
h
an
d
,
g
i
v
e
s
th
e
to
o
l,
an
d
t
h
en
r
etu
r
n
s
to
its
i
n
itia
l
p
o
s
itio
n
.
W
h
e
n
t
h
e
u
s
er
c
lo
s
es
th
eir
h
an
d
,
t
h
e
alg
o
r
it
h
m
e
n
d
s
a
c
y
cle
a
n
d
w
ai
t
s
f
o
r
t
h
e
u
s
er
t
o
s
tar
ts
a
n
o
t
h
er
r
ec
o
r
d
in
g
.
T
h
e
f
lo
w
c
h
ar
t
o
f
t
h
is
alg
o
r
ith
m
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
6
.
Fig
u
r
e
7
illu
s
tr
ates
t
h
e
f
ir
s
t
s
t
ep
o
f
th
e
p
r
o
ce
s
s
,
w
h
er
e
th
e
s
cr
e
w
d
r
i
v
er
to
o
l
is
ch
o
s
en
a
s
an
o
p
tio
n
an
d
th
e
r
ec
o
g
n
i
tio
n
o
f
it
s
u
cc
e
s
s
f
u
l
l
y
i
s
v
alid
ated
.
Fro
m
th
e
ca
p
tu
r
e
o
f
th
e
to
o
ls
,
th
e
r
ec
o
g
n
itio
n
a
n
d
p
o
s
itio
n
o
f
t
h
e
s
cr
e
w
d
r
i
v
er
ar
e
v
alid
at
ed
,
as
s
h
o
w
n
i
n
F
ig
u
r
e
8
.
Fig
u
r
e
9
ill
u
s
tr
ates
th
e
p
r
o
ce
s
s
o
f
m
o
v
in
g
th
e
r
o
b
o
tic
ar
m
to
th
e
lo
ca
tio
n
o
f
th
e
d
esire
d
to
o
l,
w
h
er
e
it
is
g
r
asp
ed
b
y
t
h
e
en
d
ef
f
ec
to
r
to
b
e
d
eli
v
er
ed
to
th
e
u
s
er
's
h
an
d
,
i
f
it
is
o
p
en
,
as
s
h
o
w
n
i
n
F
ig
u
r
e
1
0
.
T
h
e
p
r
o
ce
s
s
o
f
t
h
e
f
lo
w
c
h
ar
t
o
f
Fi
g
u
r
e
6
is
r
ep
ea
ted
w
it
h
ea
ch
o
f
th
e
t
h
r
ee
to
o
ls
,
s
u
cc
e
s
s
f
u
ll
y
a
ch
iev
in
g
t
h
e
th
r
ee
b
as
ic
p
r
o
ce
s
s
es:
s
p
ee
c
h
,
to
o
l
an
d
h
a
n
d
g
est
u
r
e
r
ec
o
g
n
itio
n
,
an
d
m
an
a
g
i
n
g
to
d
eli
v
er
ea
ch
to
o
l.
T
h
e
av
er
ag
e
e
x
ec
u
tio
n
ti
m
e
o
f
t
h
e
w
h
o
le
p
r
o
ce
s
s
is
4
5
s
ec
o
n
d
s
.
F
ig
u
r
e
1
1
s
h
o
w
s
t
h
e
g
r
ip
an
d
tr
a
n
s
f
er
o
f
t
h
e
to
o
l
s
cis
s
o
r
s
.
T
h
e
tes
ts
w
er
e
ca
r
r
ied
o
u
t
w
it
h
p
o
l
y
s
t
y
r
en
e
to
o
ls
,
i
n
s
u
c
h
a
w
a
y
t
h
at
t
h
e
y
e
m
u
lated
th
e
r
ea
l
d
im
e
n
s
io
n
s
,
d
u
e
to
th
e
u
s
e
o
f
a
n
ac
ad
e
m
ic
r
o
b
o
tic
ar
m
w
it
h
n
o
lo
ad
ca
p
ac
it
y
an
d
s
u
f
f
ic
ien
t
g
r
ip
f
o
r
m
a
n
ip
u
latio
n
o
f
th
e
r
ea
l to
o
ls
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
A
s
s
is
ta
n
t ro
b
o
t th
r
o
u
g
h
d
ee
p
l
ea
r
n
in
g
(
R
o
b
in
s
o
n
Jimé
n
ez
-
M
o
r
en
o
)
1059
Fig
u
r
e
6
.
A
l
g
o
r
ith
m
f
lo
w
ch
ar
t
Fig
u
r
e
7
.
Sp
ee
ch
r
ec
o
g
n
itio
n
t
est
Fig
u
r
e
8
.
R
ec
o
g
n
i
tio
n
o
f
t
h
e
t
o
o
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
1
0
5
3
-
1
0
6
2
1060
Fig
u
r
e
9
.
L
o
ca
ti
o
n
an
d
g
r
ip
Fig
u
r
e
1
0
.
Deliv
er
y
o
f
t
h
e
to
o
l
Fig
u
r
e
1
1
.
Valid
atio
n
w
i
th
s
c
i
s
s
o
r
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
A
s
s
is
ta
n
t ro
b
o
t th
r
o
u
g
h
d
ee
p
l
ea
r
n
in
g
(
R
o
b
in
s
o
n
Jimé
n
ez
-
M
o
r
en
o
)
1061
4.
CO
NCLU
SI
O
N
I
t
w
as
p
o
s
s
ib
le
to
o
b
tain
a
f
u
n
ctio
n
al
ap
p
licatio
n
o
f
ass
is
ti
v
e
r
o
b
o
tics
,
w
h
ich
i
s
ca
p
ab
le
o
f
r
ec
eiv
in
g
an
d
co
r
r
ec
tly
id
en
t
if
y
i
n
g
a
v
o
i
ce
co
m
m
a
n
d
,
a
s
s
o
ciatin
g
it
w
i
th
a
p
h
y
s
ical
o
b
j
ec
t,
tak
in
g
it
an
d
d
eliv
er
in
g
it
to
th
e
h
a
n
d
o
f
a
u
s
er
.
I
n
ad
d
itio
n
,
it
w
as
e
v
id
en
ce
d
b
y
t
h
e
v
e
r
s
atilit
y
o
f
C
NN
n
et
w
o
r
k
s
f
o
r
ass
is
t
iv
e
r
o
b
o
tics
ap
p
licatio
n
s
,
w
h
ich
r
eq
u
ir
e
p
atter
n
r
ec
o
g
n
itio
n
al
g
o
r
ith
m
s
.
W
h
ile
t
h
e
t
i
m
e
s
o
b
t
ain
ed
m
a
y
s
ee
m
h
i
g
h
,
it
i
s
n
o
te
w
o
r
t
h
y
th
a
t
a
co
m
p
u
ter
was
u
s
ed
th
at
d
o
es
n
o
t
o
p
er
ate
th
e
al
g
o
r
ith
m
i
n
r
ea
l
-
t
i
m
e,
s
o
t
h
at
it
s
ex
ec
u
tio
n
i
n
a
d
ed
icate
d
eq
u
ip
m
e
n
t
w
o
u
ld
b
e
r
ed
u
ce
d
.
T
h
e
d
ev
elo
p
ed
s
y
s
te
m
m
a
n
a
g
es
to
s
u
cc
es
s
f
u
l
l
y
d
eliv
er
th
e
tr
ai
n
ed
to
o
ls
,
h
o
w
e
v
e
r
,
in
cr
ea
s
i
n
g
t
h
e
s
et
o
f
t
h
ese
to
m
o
r
e
ca
t
eg
o
r
ies,
r
eq
u
ir
es
r
ed
esig
n
i
n
g
th
e
co
n
v
o
l
u
tio
n
a
l
n
et
w
o
r
k
s
,
w
h
ich
ca
n
in
v
o
l
v
e
ar
ch
itect
u
r
es
w
i
th
g
r
ea
ter
d
ep
th
a
n
d
co
n
s
eq
u
e
n
tl
y
ta
k
e
m
o
r
e
ti
m
e
to
e
x
ec
u
te
th
e
as
s
is
ti
v
e
tas
k
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
s
ar
e
g
r
atef
u
l
to
th
e
N
u
ev
a
Gr
an
ad
a
Mi
litar
y
U
n
i
v
er
s
it
y
f
o
r
t
h
e
s
u
p
p
o
r
t
g
i
v
e
n
i
n
th
e
d
ev
elo
p
m
e
n
t o
f
t
h
i
s
w
o
r
k
.
RE
F
E
R
E
NC
E
S
[1
]
E.
Jo
c
h
u
m
,
P
.
M
il
lar,
a
n
d
D.
N
u
ñ
e
z
,
“
S
e
q
u
e
n
c
e
a
n
d
c
h
a
n
c
e
:
De
sig
n
a
n
d
c
o
n
tr
o
l
m
e
th
o
d
s
f
o
r
e
n
terta
in
m
e
n
t
ro
b
o
ts,
”
Ro
b
o
ti
c
s a
n
d
Au
t
o
n
o
mo
u
s S
y
ste
ms
,
v
o
l.
8
7
,
p
p
.
3
7
2
-
3
8
0
,
2
0
1
7
.
DO
I:
1
0
.
1
0
1
6
/j
.
r
o
b
o
t.
2
0
1
6
.
0
8
.
0
1
9
[2
]
N.
K.
S
a
h
u
,
N.K
.
S
h
a
rm
a
,
M
.
R.
Kh
a
n
,
a
n
d
D
.
K.
G
a
u
ta
m
,
“
Co
m
p
a
ra
ti
v
e
S
tu
d
y
o
n
F
lo
o
r
Clea
n
e
r,
”
J
o
u
rn
a
l
o
f
P
u
re
Ap
p
li
e
d
a
n
d
In
d
u
stri
a
l
P
h
y
sic
s
,
v
o
l.
8
(1
2
),
p
p
.
2
3
3
-
2
3
6
,
2
0
1
8
.
[3
]
V
.
R.
Ba
ti
sta
a
n
d
F
.
A
.
Z
a
m
p
iro
ll
i,
“
Op
ti
m
isin
g
Ro
b
o
ti
c
P
o
o
l
-
Cl
e
a
n
in
g
w
it
h
a
G
e
n
e
ti
c
A
lg
o
rit
h
m
,
”
J
o
u
rn
a
l
o
f
In
telli
g
e
n
t
&
Ro
b
o
ti
c
S
y
ste
ms
,
v
o
l.
9
5
(2
),
p
p
.
4
4
3
-
4
5
8
,
2
0
1
9
.
DO
I:
1
0
.
1
0
0
7
/s
1
0
8
4
6
-
0
1
8
-
0
9
5
3
-
y
[4
]
R.
M
.
A
g
ri
g
o
ro
a
ie,
a
n
d
A
.
T
a
p
u
s,
“
De
v
e
lo
p
in
g
a
h
e
a
lt
h
c
a
re
ro
b
o
t
w
it
h
p
e
rso
n
a
li
z
e
d
b
e
h
a
v
io
rs
a
n
d
so
c
ial
sk
il
ls
f
o
r
th
e
e
ld
e
rly
,
”
In
2
0
1
6
1
1
th
AC
M
/IE
EE
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Hu
ma
n
-
R
o
b
o
t
In
ter
a
c
ti
o
n
(
HRI),
IEE
E
,
p
p
.
5
8
9
-
5
9
0
,
2
0
1
6
.
DO
I:
1
0
.
1
1
0
9
/HRI.
2
0
1
6
.
7
4
5
1
8
7
0
[5
]
J.
G
u
io
c
h
e
t,
M
.
M
a
c
h
i
n
,
a
n
d
H.
W
a
e
se
l
y
n
c
k
,
“
S
a
f
e
t
y
-
c
rit
ica
l
a
d
v
a
n
c
e
d
ro
b
o
ts:
A
su
rv
e
y
,
”
Ro
b
o
ti
c
s
a
n
d
Au
to
n
o
m
o
u
s
S
y
ste
ms
,
v
o
l.
9
4
,
p
p
.
4
3
-
5
2
,
2
0
1
7
.
DO
I:
1
0
.
1
0
1
6
/j
.
r
o
b
o
t.
2
0
1
7
.
0
4
.
0
0
4
[6
]
J.
De
Ge
a
F
e
rn
á
n
d
e
z
,
e
t
a
l
.
,
“
M
u
lt
im
o
d
a
l
se
n
so
r
-
b
a
se
d
w
h
o
le
-
b
o
d
y
c
o
n
tro
l
f
o
r
h
u
m
a
n
–
ro
b
o
t
c
o
ll
a
b
o
ra
ti
o
n
i
n
in
d
u
strial
se
tt
in
g
s,”
R
o
b
o
ti
c
s a
n
d
Au
to
n
o
m
o
u
s
S
y
ste
ms
,
v
o
l.
9
4
,
p
p
.
1
0
2
-
1
1
9
,
2
0
1
7
.
[7
]
J.
W
a
rc
z
y
ń
sk
i,
“
Ro
b
o
t
F
in
e
-
M
o
ti
o
n
C
o
n
tr
o
l,
”
IF
AC
Pro
c
e
e
d
i
n
g
s V
o
lu
me
s
,
v
o
l.
3
3
,
n
o
.
2
7
,
p
p
.
4
3
-
4
8
,
2
0
0
0
.
[8
]
R.
J.
M
o
re
n
o
,
M
.
M
a
u
led
o
u
x
,
a
n
d
O
.
F
.
A
v
il
é
s,
“
P
a
t
h
Op
ti
m
iz
a
ti
o
n
P
lan
n
in
g
f
o
r
H
u
m
a
n
-
Ro
b
o
t
I
n
tera
c
ti
o
n
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
A
p
p
li
e
d
En
g
i
n
e
e
rin
g
Res
e
a
rc
h
,
v
o
l.
1
1
,
n
o
.
2
2
,
p
p
.
1
0
8
2
2
-
1
0
8
2
7
,
2
0
1
6
.
[9
]
C.
Bo
u
sq
u
e
t
-
Je
tt
e
,
e
t
a
l
.
,
“
F
a
st
sc
e
n
e
a
n
a
l
y
sis
u
sin
g
v
isio
n
a
n
d
a
rti
f
icia
l
in
telli
g
e
n
c
e
f
o
r
o
b
jec
t
p
re
h
e
n
sio
n
b
y
a
n
a
ss
isti
v
e
ro
b
o
t,
”
En
g
in
e
e
rin
g
Ap
p
l
ica
ti
o
n
s
o
f
Arti
f
ici
a
l
In
telli
g
e
n
c
e
,
v
o
l.
6
3
,
p
p
.
33
-
4
4
,
2
0
1
7
.
DO
I:
1
0
.
1
0
1
6
/
j.
e
n
g
a
p
p
a
i.
2
0
1
7
.
0
4
.
0
1
5
[1
0
]
M
.
D.
Zeiler
a
n
d
R
.
F
e
rg
u
s,
“
V
is
u
a
li
z
in
g
a
n
d
u
n
d
e
r
sta
n
d
in
g
c
o
n
v
o
lu
ti
o
n
a
l
n
e
tw
o
rk
s,”
In
E
u
ro
p
e
a
n
c
o
n
fer
e
n
c
e
o
n
c
o
mp
u
ter
v
isio
n
,
S
p
ri
n
g
e
r,
C
h
a
m
,
2
0
1
4
,
p
p
.
8
1
8
-
8
3
3
,
S
e
p
2
0
1
4
.
D
OI:
1
0
.
1
0
0
7
/9
7
8
-
3
-
3
1
9
-
1
0
5
9
0
-
1
_
5
3
[1
1
]
A
.
Kriz
h
e
v
sk
y
,
I.
S
u
tsk
e
v
e
r,
a
n
d
G
.
E.
Hin
to
n
,
“
Im
a
g
e
n
e
t
c
las
si
f
ic
a
ti
o
n
w
it
h
d
e
e
p
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s,”
In
Ad
v
a
n
c
e
s in
n
e
u
r
a
l
i
n
fo
rm
a
ti
o
n
p
r
o
c
e
ss
in
g
sy
ste
ms
,
p
p
.
1
0
9
7
-
1
1
0
5
,
2
0
1
2
.
[1
2
]
F
.
T
u
,
e
t
a
l.
,
“
De
e
p
Co
n
v
o
l
u
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
A
rc
h
it
e
c
tu
re
w
it
h
Re
c
o
n
f
ig
u
ra
b
le
Co
m
p
u
tatio
n
P
a
tt
e
rn
s,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ver
y
L
a
rg
e
S
c
a
le
I
n
teg
ra
t
io
n
(
VL
S
I)
S
y
ste
ms
,
v
o
l.
2
5
(
8
)
,
p
p
.
2
2
2
0
-
2
2
3
3
,
2
0
1
7
.
DOI
:
1
0
.
1
1
0
9
/T
V
L
S
I.
2
0
1
7
.
2
6
8
8
3
4
0
[1
3
]
S
.
A
ich
,
S
.
Ch
a
k
ra
b
o
rt
y
,
a
n
d
H.C.
Kim
,
“
Co
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
-
b
a
s
e
d
m
o
d
e
l
f
o
r
w
e
b
-
b
a
se
d
te
x
t
c
las
si
f
ica
ti
o
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
(6
),
p
p
.
5
1
8
5
-
5
1
9
1
,
2
0
1
9
.
DO
I:
1
0
.
1
1
5
9
1
/
ij
e
c
e
.
v
9
i6
.
p
p
5
1
8
5
-
5
1
9
1
[1
4
]
J.O.
P
in
z
ó
n
-
A
re
n
a
s,
R.
Jim
é
n
e
z
-
M
o
re
n
o
,
a
n
d
C.
G
.
P
a
c
h
ó
n
-
S
u
e
sc
ú
n
,
“
Of
f
li
n
e
sig
n
a
tu
re
v
e
ri
f
ica
ti
o
n
u
si
n
g
DA
G
-
CNN
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
(4
),
p
p
.
3
3
1
4
-
3
3
2
2
,
2
0
1
9
.
DO
I:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
9
i4
.
p
p
3
3
1
4
-
3
3
2
2
[1
5
]
R.
Jim
e
n
e
z
-
M
o
re
n
o
a
n
d
D.
Ov
a
l
le
M
a
tri
n
e
z
,
“
A
No
v
e
l
P
a
ra
ll
e
l
Co
n
v
o
l
u
ti
o
n
a
l
Ne
tw
o
rk
A
r
c
h
it
e
c
tu
re
f
o
r
De
p
th
-
De
p
e
n
d
e
n
t
Ob
jec
t
Re
c
o
g
n
it
io
n
,
”
In
ter
n
a
ti
o
n
a
l
Rev
iew
o
f
Au
t
o
ma
ti
c
Co
n
tro
l
,
v
o
l.
1
2
(2
),
p
p
.
7
6
-
8
1
,
2
0
1
9
.
DO
I:
1
0
.
1
5
8
6
6
/i
re
a
c
o
.
v
1
2
i2
.
1
6
4
6
7
[1
6
]
M.
S.
H.
Al
-
Ta
m
i
m
i,
“
Co
m
b
in
in
g
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
t
w
o
rk
s
a
n
d
sla
n
tl
e
t
tran
sf
o
rm
fo
r
a
n
e
ff
e
c
ti
v
e
im
a
g
e
r
e
tri
e
v
a
l
s
c
h
e
m
e
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
(
5
)
,
p
p
.
4
3
8
2
-
4
3
9
5
,
2
0
1
9
.
DO
I:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
9
i5
.
p
p
4
3
8
2
-
43
95
[1
7
]
A
.
V
o
ro
to
v
a
,
V
.
F
in
a
e
v
,
V
.
S
o
l
o
v
iev
,
a
n
d
M
.
M
e
d
v
e
d
e
v
,
“
S
tati
stica
l
Da
ta
P
ro
c
e
ss
in
g
o
f
Tw
o
M
o
b
i
le
Ob
jec
ts
Be
h
a
v
io
r
in
Ra
n
d
o
m
En
v
iro
n
m
e
n
ts
Us
in
g
S
i
m
u
latio
n
M
o
d
e
li
n
g
M
e
th
o
d
,
”
In
ter
n
a
ti
o
n
a
l
Rev
iew
o
f
Au
to
ma
ti
c
Co
n
tro
l
,
v
o
l.
1
2
(4
)
,
2
0
1
9
.
[1
8
]
J.
O.
P
.
A
re
n
a
s,
R.
Jim
é
n
e
z
,
a
n
d
P
.
C.
U.
M
u
r
il
lo
,
“
F
a
ste
r
R
-
CNN
f
o
r
o
b
jec
t
l
o
c
a
ti
o
n
in
a
Virtu
a
l
E
n
v
iro
n
m
e
n
t
f
o
r
so
rti
n
g
tas
k
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
On
li
n
e
E
n
g
i
n
e
e
rin
g
(
iJO
E)
,
v
o
l.
1
4
(0
7
),
p
p
.
4
-
1
4
,
2
0
1
8
.
[1
9
]
Z.
W
a
n
g
,
Z.
L
i,
B.
W
a
n
g
,
a
n
d
H.
L
iu
,
“
Ro
b
o
t
g
ra
sp
d
e
tec
ti
o
n
u
sin
g
m
u
lt
im
o
d
a
l
d
e
e
p
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s,”
Ad
v
a
n
c
e
s in
M
e
c
h
a
n
i
c
a
l
En
g
in
e
e
rin
g
,
v
o
l
.
8
(
9
)
,
p
p
.
1
-
1
2
,
2
0
1
6
.
DO
I:
1
0
.
1
1
7
7
/
1
6
8
7
8
1
4
0
1
6
6
6
8
0
7
7
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
1
0
5
3
-
1
0
6
2
1062
[2
0
]
D.
Ka
las
h
n
ik
o
v
,
e
t
a
l
.
,
“
Qt
-
o
p
t:
S
c
a
lab
le
d
e
e
p
re
in
f
o
rc
e
m
e
n
t
lea
rn
in
g
f
o
r
v
isio
n
-
b
a
se
d
ro
b
o
ti
c
m
a
n
ip
u
latio
n
,
”
a
rXi
v
p
re
p
rin
t
a
rXiv:1
8
0
6
.
1
0
2
9
3
,
2
0
1
8
.
[2
1
]
M
.
A
.
G
u
ti
é
rre
z
,
L
.
J.
M
a
n
so
,
H.
P
a
n
d
y
a
a
n
d
P
.
Nú
ñ
e
z
,
“
A
P
a
ss
iv
e
Lea
rn
in
g
S
e
n
so
r
A
rc
h
it
e
c
tu
re
fo
r
M
u
lt
im
o
d
a
l
Im
a
g
e
L
a
b
e
li
n
g
:
A
n
A
p
p
li
c
a
ti
o
n
f
o
r
S
o
c
ial
Ro
b
o
ts
,
”
S
e
s
o
rs
(
Ba
se
l)
,
v
o
l.
1
7
(
2
)
,
p
.
3
5
3
,
2
0
1
7
.
[2
2
]
Y.
Qia
n
,
a
n
d
P
.
C.
W
o
o
d
lan
d
,
“
V
e
ry
d
e
e
p
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s
f
o
r
ro
b
u
st
sp
e
e
c
h
re
c
o
g
n
it
io
n
,
”
In
2
0
1
6
IEE
E
S
p
o
k
e
n
L
a
n
g
u
a
g
e
T
e
c
h
n
o
l
o
g
y
W
o
rk
sh
o
p
(
S
L
T
)
,
p
p
.
4
8
1
-
4
8
8
,
2
0
1
6
.
DO
I:
1
0
.
1
1
0
9
/S
L
T
.
2
0
1
6
.
7
8
4
6
3
0
7
[2
3
]
J.O.P
.
A
re
n
a
s,
R.
D.H.
Be
leñ
o
,
a
n
d
R.
J.
M
o
re
n
o
,
“
De
e
p
Co
n
v
o
lu
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
f
o
r
Ha
n
d
G
e
stu
re
Re
c
o
g
n
it
io
n
Us
e
d
f
o
r
Hu
m
a
n
-
Ro
b
o
t
I
n
tera
c
ti
o
n
,
”
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
A
p
p
li
e
d
S
c
ien
c
e
s
,
v
o
l.
1
2
(
11
)
,
p
p
.
9
2
7
8
-
9
2
8
5
,
2
0
1
7
.
[2
4
]
S
.
Yo
u
n
g
,
e
t
a
l
.
,
T
h
e
HTK
b
o
o
k
,
Ca
m
b
rid
g
e
Un
iv
e
rsit
y
En
g
in
e
e
rin
g
De
p
a
rt
m
e
n
t,
2
0
0
2
.
[2
5
]
J.O.
P
in
z
ó
n
A
re
n
a
s,
R.
Jim
é
n
e
z
M
o
re
n
o
,
R.
D.
He
rn
á
n
d
e
z
Be
l
e
ñ
o
,
“
W
o
rd
-
b
a
se
d
De
e
p
Co
n
v
o
l
u
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
a
rc
h
it
e
c
tu
re
f
o
r
S
p
e
e
c
h
Re
c
o
g
n
it
io
n
,
”
In
II
C
o
n
g
re
so
I
n
ter
n
a
c
i
o
n
a
l
d
e
Cien
c
i
a
s
Bá
sic
a
s
e
In
g
e
n
ier
ía
,
p
p
.
1
-
1
0
,
2
0
1
8
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Ro
b
i
n
s
o
n
J
i
m
é
n
e
z
M
o
r
e
n
o
w
a
s
b
o
rn
i
n
Bo
g
o
tá,
Co
l
o
m
b
ia,
in
1
9
7
8
.
He
re
c
e
iv
e
d
th
e
En
g
in
e
e
r
d
e
g
re
e
in
El
e
c
tro
n
ics
a
t
th
e
F
ra
n
c
isc
o
Jo
sé
d
e
Ca
ld
a
s
District
Un
iv
e
rsit
y
-
UD
-
in
2
0
0
2
.
M
.
S
c
.
i
n
In
d
u
strial
A
u
to
m
a
ti
o
n
f
ro
m
th
e
Un
iv
e
rsid
a
d
Na
c
io
n
a
l
d
e
Co
lo
m
b
ia
-
2
0
1
2
a
n
d
P
h
.
D.
in
En
g
in
e
e
ri
n
g
a
t
th
e
F
ra
n
c
isc
o
Jo
sé
d
e
Ca
ld
a
s
District
Un
iv
e
rsit
y
-
2
0
1
8
.
He
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
a
P
r
o
f
e
ss
o
r
in
th
e
M
e
c
h
a
tro
n
ics
En
g
in
e
e
rin
g
P
ro
g
ra
m
a
t
th
e
Nu
e
v
a
G
ra
n
a
d
a
M
il
it
a
r
y
Un
iv
e
rsit
y
-
UMNG
.
He
h
a
s
e
x
p
e
rien
c
e
in
th
e
a
re
a
s o
f
In
stru
m
e
n
tatio
n
a
n
d
El
e
c
tro
n
ic
Co
n
tro
l,
a
c
ti
n
g
m
a
in
l
y
in
Ro
b
o
ti
c
s,
c
o
n
tro
l
,
p
a
tt
e
r
n
re
c
o
g
n
i
ti
o
n
,
a
n
d
im
a
g
e
p
ro
c
e
ss
in
g
.
E
-
m
a
il
:
ro
b
in
so
n
.
ji
m
e
n
e
z
@u
n
im
il
it
a
r.
e
d
u
.
c
o
J
a
v
ier
O
r
l
a
n
d
o
Pi
n
z
ó
n
Ar
e
n
a
s
w
a
s
b
o
rn
in
S
o
c
o
rro
-
S
a
n
tan
d
e
r,
Co
lo
m
b
ia,
in
1
9
9
0
.
He
re
c
e
iv
e
d
h
is
d
e
g
re
e
in
M
e
c
h
a
tro
n
ics
E
n
g
in
e
e
rin
g
(Cu
m
Lau
d
e
)
in
2
0
1
3
,
S
p
e
c
ializa
ti
o
n
in
En
g
in
e
e
rin
g
P
r
o
jec
t
M
a
n
a
g
e
m
e
n
t
in
2
0
1
6
,
a
n
d
M
.
S
c
.
i
n
M
e
c
h
a
tro
n
ics
En
g
i
n
e
e
rin
g
in
2
0
1
9
,
a
t
th
e
Nu
e
v
a
G
ra
n
a
d
a
M
il
it
a
r
y
Un
iv
e
rsit
y
-
U
M
NG
.
He
h
a
s
e
x
p
e
rien
c
e
in
th
e
a
re
a
s
o
f
a
u
to
m
a
ti
o
n
,
e
lec
tro
n
i
c
c
o
n
tro
l,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
C
u
rre
n
tl
y
,
h
e
is
stu
d
y
in
g
a
P
h
.
D.
in
A
p
p
li
e
d
S
c
ien
c
e
s
a
n
d
w
o
rk
in
g
a
s a G
r
a
d
u
a
te A
ss
ist
a
n
t
a
t
th
e
U
M
NG
w
it
h
e
m
p
h
a
sis o
n
R
o
b
o
ti
c
s
a
n
d
M
a
c
h
i
n
e
L
e
a
rn
in
g
.
E
-
m
a
il
:
u
3
9
0
0
2
3
1
@
u
n
im
il
it
a
r.
e
d
u
.
c
o
Cé
sa
r
G
io
v
a
n
y
Pa
c
h
ó
n
S
u
e
sc
ú
n
w
a
s
b
o
rn
i
n
Bo
g
o
t
á
,
Co
l
o
m
b
ia,
in
1
9
9
6
.
He
re
c
e
iv
e
d
h
is
d
e
g
re
e
in
M
e
c
h
a
tro
n
ics
En
g
i
n
e
e
rin
g
f
ro
m
th
e
P
il
o
t
Un
iv
e
rsity
o
f
Co
lo
m
b
ia
in
2
0
1
8
.
C
u
rre
n
tl
y
,
h
e
is
stu
d
y
in
g
h
is
M
a
ste
r’s
d
e
g
re
e
in
M
e
c
h
a
tro
n
ics
E
n
g
in
e
e
rin
g
a
n
d
w
o
rk
in
g
a
s
a
Re
se
a
rc
h
As
sista
n
t
a
t
th
e
Nu
e
v
a
G
ra
n
a
d
a
M
il
it
a
ry
Un
iv
e
rsit
y
w
it
h
a
n
e
m
p
h
a
sis o
n
R
o
b
o
ti
c
s an
d
M
a
c
h
i
n
e
L
e
a
rn
in
g
.
E
-
m
a
il
:
u
3
9
0
0
2
5
9
@
u
n
im
il
it
a
r.
e
d
u
.
c
o
Evaluation Warning : The document was created with Spire.PDF for Python.