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
.
6
,
Decem
b
er
2
0
2
0
,
p
p
.
6
3
0
0
~
6
3
0
8
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
10
i
6
.
pp
6
3
0
0
-
6
3
0
8
6300
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
To
o
l delivery
robo
t
using
conv
o
luti
o
na
l neural netw
o
rk
J
a
v
ier
P
inzo
n
-
Are
na
s
,
Ro
bin
s
o
n J
i
m
énez
-
M
o
re
no
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
M
il
it
a
r
N
u
e
v
a
G
ra
n
a
d
a
Un
iv
e
rsit
y
,
Co
lo
m
b
i
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oc
t 3
0
,
2
0
1
9
R
ev
i
s
ed
J
u
n
6
,
2020
A
cc
ep
ted
J
u
n
17
,
2
0
2
0
In
th
e
f
o
ll
o
w
in
g
a
rti
c
le,
it
is
p
re
se
n
ted
a
h
u
m
a
n
-
ro
b
o
t
i
n
tera
c
ti
o
n
sy
ste
m
w
h
e
re
a
l
g
o
rit
h
m
s
w
e
re
d
e
v
e
lo
p
e
d
to
c
o
n
tro
l
th
e
m
o
v
e
m
e
n
t
o
f
a
m
a
n
ip
u
lat
o
r
in
o
rd
e
r
t
o
a
ll
o
w
it
to
se
a
rc
h
a
n
d
d
e
li
v
e
r,
in
th
e
h
a
n
d
o
f
th
e
u
se
r,
a
d
e
sire
d
to
o
l
w
it
h
a
c
e
rtain
o
rien
tati
o
n
.
A
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
(CNN
)
w
a
s
u
se
d
to
d
e
tec
t
a
n
d
re
c
o
g
n
ize
th
e
u
se
r
'
s
h
a
n
d
,
g
e
o
m
e
tri
c
a
n
a
ly
sis
f
o
r
th
e
a
d
j
u
stm
e
n
t
o
f
th
e
d
e
li
v
e
ry
sta
tu
s
o
f
t
h
e
to
o
l
f
ro
m
a
n
y
p
o
siti
o
n
o
f
th
e
ro
b
o
t
a
n
d
a
n
y
o
rien
tatio
n
o
f
th
e
g
rip
p
e
r,
a
n
d
a
traje
c
to
r
y
p
lan
n
in
g
a
lg
o
rit
h
m
f
o
r
th
e
m
o
v
e
m
e
n
t
o
f
th
e
m
a
n
i
p
u
lato
r
.
It
w
a
s
p
o
ss
i
b
le
to
u
se
th
e
a
c
ti
v
a
ti
o
n
s
o
f
a
CNN
d
e
v
e
lo
p
e
d
in
p
re
v
io
u
s
w
o
rk
s
f
o
r
th
e
d
e
tec
ti
o
n
of
th
e
p
o
siti
o
n
a
n
d
o
rie
n
tatio
n
o
f
th
e
h
a
n
d
in
th
e
w
o
rk
sp
a
c
e
a
n
d
th
u
s
trac
k
it
in
re
a
l
ti
m
e
,
b
o
th
i
n
a
sim
u
late
d
e
n
v
iro
n
m
e
n
t
a
n
d
i
n
a
re
a
l
e
n
v
iro
n
m
e
n
t
.
K
ey
w
o
r
d
s
:
C
o
n
v
o
lu
tio
n
al
n
e
u
r
al
n
e
t
w
o
r
k
Deliv
er
y
s
tat
u
s
ad
j
u
s
t
m
e
n
t
Han
d
tr
ac
k
i
n
g
Hu
m
an
-
r
o
b
o
t in
ter
ac
tio
n
P
ath
p
lan
n
i
n
g
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
,
Militar
Nu
e
v
a
Gr
an
ad
a
U
n
iv
e
r
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
T
h
e
h
u
m
an
-
r
o
b
o
t
in
ter
ac
tio
n
r
eq
u
ir
es
a
m
ac
h
in
e
v
is
io
n
s
y
s
te
m
t
h
at
allo
w
s
th
e
r
o
b
o
t
to
r
ec
o
g
n
ize
th
e
h
u
m
an
m
o
v
e
m
e
n
t
an
d
i
n
t
er
p
r
et
it
as
an
in
s
tr
u
c
tio
n
f
o
r
th
e
ex
ec
u
tio
n
o
f
a
ce
r
tain
tas
k
,
as
clar
if
ied
i
n
[
1
]
an
d
[
2
]
.
So
m
e
o
f
th
e
s
e
co
o
p
e
r
ativ
e
w
o
r
k
s
lead
to
th
e
n
ee
d
to
d
ev
elo
p
alg
o
r
ith
m
s
th
at
al
lo
w
th
e
i
n
ter
ac
tio
n
b
et
w
ee
n
b
o
th
,
m
a
k
in
g
co
n
tr
o
l
o
v
er
th
e
f
o
r
ce
ex
er
ted
b
y
th
e
m
an
ip
u
lato
r
at
th
e
p
o
in
t
o
f
co
n
tact
w
i
t
h
th
e
h
u
m
a
n
,
as
ex
p
lai
n
ed
in
[
3
]
,
o
r
u
s
in
g
a
n
i
n
telli
g
e
n
t
s
u
p
p
o
r
t
s
y
s
te
m
i
n
t
h
e
ex
ec
u
tio
n
o
f
task
s
p
er
f
o
r
m
ed
b
y
an
o
p
er
ato
r
,
w
h
er
e
h
u
m
a
n
e
f
f
o
r
t is
m
in
i
m
ized
an
d
th
e
e
x
ec
u
tio
n
o
f
th
e
ta
s
k
i
s
o
p
ti
m
ized
,
as sh
o
w
n
i
n
[
4
]
.
Fo
r
th
e
d
ev
elo
p
ed
a
p
p
licatio
n
ex
p
o
s
ed
in
th
is
ar
ticle,
h
u
m
an
in
te
n
tio
n
is
r
ep
r
esen
ted
as
th
e
h
an
d
th
a
t
ex
p
ec
ts
to
r
ec
eiv
e
a
to
o
l,
an
d
th
e
task
o
f
t
h
e
r
o
b
o
t
is
to
g
o
an
d
d
eliv
er
th
e
to
o
l
in
it,
w
h
ich
ca
n
ch
a
n
g
e
p
o
s
itio
n
an
d
o
r
ien
ta
tio
n
at
a
n
y
ti
m
e.
T
h
is
t
y
p
e
o
f
ap
p
licati
o
n
s
r
eq
u
ir
es
a
m
ac
h
i
n
e
v
is
io
n
s
y
s
te
m
th
a
t
allo
w
s
th
e
m
a
n
ip
u
la
to
r
to
s
ee
an
d
f
o
llo
w
t
h
e
h
a
n
d
co
n
tin
u
o
u
s
l
y
as
w
ell
as
a
co
n
t
r
o
l
s
y
s
te
m
t
h
at
m
o
v
e
s
t
h
e
en
d
ef
f
ec
to
r
o
f
t
h
e
m
a
n
ip
u
la
to
r
to
its
d
e
s
ti
n
atio
n
,
r
e
g
ar
d
less
o
f
w
h
et
h
er
it
is
ch
a
n
g
i
n
g
,
a
n
d
th
at
i
n
tu
r
n
allo
w
s
ad
j
u
s
tin
g
th
e
o
r
ien
ta
tio
n
o
f
t
h
e
to
o
l to
b
e
d
eliv
er
ed
,
s
o
th
at
it c
an
b
e
h
eld
b
y
th
e
u
s
er
.
So
m
e
p
r
ev
io
u
s
s
tu
d
ie
s
r
el
ated
to
h
u
m
a
n
-
r
o
b
o
t
in
ter
ac
tio
n
in
v
o
lv
e
s
s
en
s
o
r
f
o
r
th
e
task
o
f
in
ter
ac
tio
n
in
t
h
e
g
r
ip
p
er
o
f
a
3
DO
F
r
o
b
o
t,
as
a
p
r
ev
io
u
s
s
ta
g
e
o
f
u
s
e
o
f
m
ac
h
in
e
v
i
s
io
n
,
a
s
ex
p
lai
n
ed
in
[
5
]
.
A
d
d
itio
n
al
l
y
,
it
m
u
s
t
h
av
e
t
h
e
ab
ilit
y
to
r
ec
o
g
n
ize
t
h
e
j
o
in
ts
o
f
th
e
h
an
d
a
n
d
i
ts
v
ar
ie
d
p
o
s
itio
n
s
[
6
]
f
o
r
th
e
d
ev
e
lo
p
m
en
t
o
f
co
m
p
le
x
t
ask
s
s
u
c
h
as
v
id
eo
g
a
m
es
a
n
d
h
u
m
a
n
-
co
m
p
u
ter
i
n
ter
ac
tio
n
s
.
E
v
en
ta
k
in
g
j
o
b
s
lik
e
w
ea
r
ab
le
r
o
b
o
ts
w
h
er
e
t
h
e
i
n
ter
ac
tio
n
allo
w
s
r
ed
u
ce
th
e
h
u
m
an
m
etab
o
lic
e
n
er
g
y
co
s
t
i
n
p
h
y
s
ical
m
o
v
e
m
e
n
ts
[
7
]
.
A
ll
th
i
s
s
et
o
f
ac
tiv
ities
i
n
v
o
l
v
es,
g
e
n
er
all
y
,
th
e
u
s
e
o
f
ca
m
er
as
o
r
d
ep
th
s
en
s
o
r
s
th
at
allo
w
to
ex
tr
ac
t
t
h
e
h
an
d
f
r
o
m
t
h
e
en
v
ir
o
n
m
e
n
t,
to
g
et
h
er
w
it
h
its
ar
tic
u
latio
n
s
,
as
s
h
o
w
n
i
n
[
8
,
9
]
,
an
d
th
at
s
i
m
u
lta
n
eo
u
s
l
y
,
m
an
a
g
e
to
tr
ac
k
w
ith
t
ec
h
n
iq
u
es
li
k
e
ar
tif
ic
ial
i
n
telli
g
e
n
ce
o
r
th
e
u
s
e
o
f
co
r
r
elatio
n
s
f
ilter
s
,
r
esp
ec
tiv
el
y
.
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:
2088
-
8708
To
o
l d
elive
r
y
r
o
b
o
t u
s
in
g
c
o
n
v
o
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
(
Ja
vier P
in
z
o
n
-
A
r
en
a
s
)
6301
A
r
ti
f
icial
i
n
telli
g
e
n
ce
tech
n
iq
u
e
b
ased
o
n
d
ee
p
lear
n
in
g
i
s
ex
p
o
s
ed
in
[
1
0
]
f
o
r
g
iv
e
s
m
ar
t
attr
ib
u
tes
to
a
r
o
b
o
t
u
s
ed
a
s
a
s
s
i
s
ta
n
t,
t
h
e
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
et
wo
r
k
(
C
NN)
w
as
u
s
ed
to
d
ev
e
l
o
p
th
e
al
g
o
r
ith
m
to
h
u
m
a
n
r
o
b
o
t
in
ter
ac
tio
n
.
C
o
n
v
o
l
u
tio
n
a
l
n
et
w
o
r
k
s
h
a
v
e
m
an
y
ap
p
licatio
n
s
in
t
h
e
to
p
o
f
th
e
s
tate
o
f
ar
t,
ex
a
m
p
le
li
k
e
b
io
lo
g
ical
i
m
a
g
e
class
if
icatio
n
[
1
1
]
,
h
an
d
w
r
itte
n
c
h
ar
ac
ter
r
ec
o
g
n
itio
n
[
1
2
]
an
d
d
etec
tio
n
o
f
p
ac
k
ed
a
n
d
u
n
p
ac
k
ed
m
a
l
w
ar
e
[
1
3
]
,
th
e
y
ar
e
r
ec
en
t
r
esear
ch
es
o
f
d
i
f
f
er
en
t
s
cie
n
ce
f
ield
's
t
h
at
u
s
e
th
is
tec
h
n
iq
u
e
.
B
ased
o
n
it,
th
i
s
w
o
r
k
i
s
o
r
ien
ted
to
in
te
g
r
ate
t
h
e
ab
o
v
e
co
n
ce
p
ts
in
th
e
d
e
v
elo
p
m
e
n
t
o
f
a
n
e
w
h
u
m
a
n
-
r
o
b
o
t
in
ter
ac
tio
n
s
y
s
t
e
m
,
in
c
h
ar
g
e
o
f
f
ac
ili
tatin
g
d
if
f
er
en
t
t
y
p
es
o
f
to
o
ls
t
o
a
u
s
er
th
r
o
u
g
h
an
an
th
r
o
p
o
m
o
r
p
h
ic
m
an
ip
u
lato
r
,
w
h
o
s
e
d
is
p
lace
m
en
t
d
ep
en
d
s
o
n
th
e
lo
ca
tio
n
o
f
th
e
h
an
d
,
w
h
er
e
th
e
en
v
ir
o
m
e
n
t
i
s
ca
p
tu
r
ed
b
y
a
ca
m
er
a
an
d
r
ec
o
g
n
ized
b
y
m
ea
n
s
o
f
a
C
NN.
Fo
r
th
e
f
i
n
al
o
r
ien
tatio
n
o
f
th
e
g
r
ip
p
er
o
f
th
e
m
a
n
ip
u
la
t
o
r
,
a
co
r
r
ec
tio
n
o
f
th
e
d
eliv
e
r
y
s
tat
u
s
o
f
th
e
to
o
l
is
g
en
er
ated
,
w
h
ich
allo
w
s
th
e
r
o
b
o
t
to
leav
e
th
e
in
s
tr
u
m
en
t
i
n
t
h
e
h
a
n
d
o
f
t
h
e
u
s
er
in
s
u
c
h
a
w
a
y
th
at
it
ca
n
g
e
n
er
at
e
a
c
y
l
in
d
r
ical
g
r
ip
o
n
th
e
ele
m
en
t,
as
a
co
m
p
le
m
en
tar
y
s
u
p
p
o
r
t
o
f
s
tate
o
f
ar
t
i
n
h
u
m
an
-
r
o
b
o
t
in
ter
ac
tio
n
s
.
As
a
co
m
p
le
m
e
n
t
o
f
p
r
ev
io
u
s
w
o
r
k
s
r
elate
s
i
n
th
e
s
tate
o
f
ar
t lik
e
[
1
4
,
1
5
]
.
T
h
e
d
ev
elo
p
m
e
n
t
o
f
th
is
ap
p
l
icatio
n
is
f
u
n
d
a
m
e
n
tal
f
o
r
th
e
p
r
o
g
r
am
m
i
n
g
o
f
a
n
as
s
is
tiv
e
r
o
b
o
t,
f
o
r
ex
a
m
p
le,
in
t
h
e
m
ed
ical
ar
ea
,
w
h
er
e
it
o
p
er
ates
a
s
a
n
in
s
tr
u
m
e
n
tal
is
t
w
it
h
t
h
e
ab
ilit
y
to
p
r
o
v
id
e
th
e
s
u
r
g
ical
in
s
tr
u
m
en
t
s
to
th
e
d
o
cto
r
[
1
6
]
,
d
eliv
er
in
g
th
e
m
i
n
t
h
e
h
a
n
d
w
it
h
t
h
e
ap
p
r
o
p
r
iate
o
r
ien
tatio
n
f
o
r
its
s
u
p
p
o
r
t.
I
n
p
r
ev
io
u
s
w
o
r
k
s
,
th
e
r
ec
o
g
n
i
tio
n
an
d
cla
s
s
i
f
ica
tio
n
p
ar
t o
f
s
u
r
g
ical
i
n
s
tr
u
m
en
ta
tio
n
h
as
b
ee
n
s
o
l
v
ed
to
allo
w
th
e
m
a
n
ip
u
la
to
r
to
f
in
d
th
e
to
o
l
r
eq
u
ested
b
y
t
h
e
u
s
er
,
h
o
l
d
it
a
n
d
tak
e
it
to
a
ce
r
tai
n
p
o
in
t,
i
n
ad
d
itio
n
to
tr
ain
i
n
g
a
C
NN
f
o
r
th
e
cla
s
s
i
f
icatio
n
o
f
h
an
d
g
est
u
r
es
(
s
u
c
h
as
o
p
en
o
r
clo
s
ed
)
,
as
s
h
o
w
n
i
n
[
1
7
]
.
I
n
s
u
c
h
a
w
a
y
t
h
at
t
h
e
n
e
x
t
s
tep
is
b
as
ed
o
n
th
e
d
eli
v
er
y
o
f
t
h
e
i
n
s
tr
u
m
e
n
t
in
th
e
p
al
m
o
f
t
h
e
u
s
er
,
w
h
ic
h
is
ex
p
o
s
ed
b
elo
w
,
as a
co
n
tr
ib
u
tio
n
to
th
e
s
tate
o
f
th
e
ar
t.
T
h
e
in
teg
r
atio
n
o
f
a
r
o
b
o
tic
a
g
en
t
w
i
th
ar
ti
f
icial
i
n
tell
ig
e
n
c
e
s
y
s
te
m
s
is
co
m
m
o
n
[
1
8
]
,
w
h
er
e
C
NN
s
allo
w
th
i
s
i
n
te
g
r
atio
n
at
d
if
f
er
en
t
s
ca
les
s
u
c
h
a
s
r
o
b
o
tic
co
n
tr
o
l
[
1
9
]
,
clea
n
in
g
r
o
b
o
ts
[
2
0
]
o
r
r
ec
y
cler
s
[
2
1
]
.
T
h
is
tech
n
iq
u
e
h
a
s
d
e
m
o
n
s
tr
a
ted
its
v
er
s
ati
lit
y
[
2
2
]
an
d
ar
ticu
latio
n
ca
p
ac
it
y
w
it
h
o
th
er
t
ec
h
n
iq
u
es
[
2
3
,
2
4
]
,
ev
en
i
n
v
ir
tu
al
r
o
b
o
tic
w
o
r
k
e
n
v
ir
o
n
m
e
n
t
s
[
2
5
]
,
w
h
ic
h
is
w
h
y
t
h
e
y
ar
e
t
h
e
tec
h
n
iq
u
e
u
s
ed
i
n
t
h
i
s
d
ev
elo
p
m
en
t.
T
h
e
p
ap
er
is
d
i
v
id
ed
in
to
3
m
a
in
s
ec
tio
n
s
,
wh
er
e
t
h
e
f
ir
s
t
ex
p
lai
n
s
i
n
d
eta
il
t
h
e
m
et
h
o
d
o
lo
g
y
d
ev
elo
p
ed
f
o
r
th
e
ex
ec
u
tio
n
o
f
th
e
h
a
n
d
tr
ac
k
i
n
g
a
lg
o
r
i
th
m
b
y
t
h
e
m
an
ip
u
lato
r
,
an
d
th
e
ad
j
u
s
t
m
en
t
o
f
th
e
d
eli
v
er
y
s
tat
u
s
o
f
t
h
e
to
o
l.
T
h
e
f
o
llo
w
i
n
g
p
r
esen
ts
th
e
r
esu
l
ts
a
n
d
a
n
al
y
ze
s
ac
h
ie
v
e
d
,
an
d
i
n
t
h
e
la
s
t
s
ec
tio
n
t
h
e
co
n
cl
u
s
io
n
s
o
b
tain
ed
f
r
o
m
t
h
e
ap
p
licatio
n
ar
e
p
r
esen
ted
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
A
r
o
b
o
tic
ass
is
ta
n
ce
al
g
o
r
ith
m
w
a
s
d
ev
elo
p
ed
w
h
o
s
e
o
b
j
ec
tiv
e
i
s
to
p
r
o
v
id
e
to
o
ls
to
a
u
s
er
b
y
co
n
s
ta
n
tl
y
m
o
n
ito
r
in
g
h
i
s
h
a
n
d
w
i
th
i
n
a
li
m
ited
w
o
r
k
ar
ea
,
an
d
f
in
al
izin
g
t
h
e
d
eliv
er
y
p
r
o
ce
s
s
w
i
th
a
n
ad
j
u
s
t
m
e
n
t
o
f
th
e
o
r
ien
tatio
n
o
f
th
e
to
o
l,
r
o
tatin
g
it
u
n
til
it
is
ar
r
an
g
ed
in
s
u
ch
a
w
a
y
t
h
a
t
a
c
y
l
in
d
r
ical
g
r
ip
ca
n
b
e
g
en
er
ated
o
n
it,
as
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
A
C
NN
w
as
tr
ai
n
ed
,
an
d
s
eg
m
en
tatio
n
al
g
o
r
ith
m
s
w
er
e
u
s
ed
f
o
r
h
an
d
r
ec
o
g
n
itio
n
d
u
r
i
n
g
a
v
id
eo
s
eq
u
en
ce
an
d
d
ata
a
u
g
m
e
n
tat
i
o
n
tech
n
iq
u
es
[
2
6
]
.
Su
b
s
eq
u
en
tl
y
,
t
h
e
i
n
v
er
s
e
k
in
e
m
atic
s
o
f
t
h
e
m
an
ip
u
lato
r
w
a
s
ca
lc
u
lated
to
ex
ec
u
te
it
s
d
is
p
lace
m
e
n
t,
an
d
g
eo
m
etr
ic
an
al
y
s
is
w
as
u
s
ed
to
ad
j
u
s
t
t
h
e
d
eliv
er
y
s
tat
u
s
o
f
th
e
to
o
l
w
ith
r
esp
ec
t
to
t
h
e
p
o
s
itio
n
o
f
t
h
e
u
s
er
'
s
h
an
d
,
at
t
h
e
m
o
m
en
t
w
h
e
n
t
h
e
r
o
b
o
t
s
to
p
s
o
n
th
e
p
al
m
o
f
th
e
h
a
n
d
.
Fi
g
u
r
e
2
s
h
o
w
s
t
h
e
s
eq
u
en
ce
o
f
b
asic
o
p
er
atio
n
o
f
th
e
al
g
o
r
ith
m
,
i
n
w
h
ich
a
to
tal
o
f
5
s
tep
s
ar
e
d
em
ar
ca
ted
,
w
h
er
e
t
h
e
f
ir
s
t
ta
k
es
t
h
e
m
a
n
ip
u
lato
r
to
th
e
in
i
t
ial
p
o
s
itio
n
s
h
o
w
n
in
Fi
g
u
r
e
7
a,
w
it
h
th
e
to
o
l
h
eld
b
y
th
e
g
r
ip
p
er
,
an
d
t
h
e
f
o
l
lo
w
i
n
g
t
h
r
ee
ar
e
r
esp
o
n
s
ib
l
e
f
o
r
ex
ec
u
ti
n
g
t
h
e
tr
ac
k
in
g
o
f
th
e
h
a
n
d
an
d
th
e
ad
j
u
s
t
m
e
n
t
o
f
t
h
e
d
eli
v
er
y
o
f
t
h
e
to
o
l,
r
ep
ea
tin
g
i
n
a
c
y
c
le
th
at
o
n
l
y
e
n
d
s
w
h
e
n
t
h
e
g
r
i
p
p
er
is
o
n
t
h
e
h
an
d
an
d
th
e
to
o
l
h
a
s
alr
ea
d
y
b
ee
n
ac
co
m
m
o
d
ated
f
o
r
th
e
g
r
ip
,
th
en
it
i
s
p
ass
ed
to
th
e
f
i
f
t
h
s
tep
an
d
th
e
al
g
o
r
ith
m
is
f
i
n
i
s
h
ed
.
Fig
u
r
e
1
.
C
y
li
n
d
r
ical
g
r
ip
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
.
6
,
Decem
b
er
2020
:
6
3
0
0
-
6
3
0
8
6302
Fig
u
r
e
2
.
A
l
g
o
r
ith
m
f
lo
w
ch
ar
t
2
.
1
.
M
a
nip
ula
t
o
r
t
ra
j
ec
t
o
r
y
An
al
g
o
r
ith
m
w
as
d
ev
elo
p
ed
th
at
allo
w
s
to
s
e
t
a
c
u
r
v
ed
p
ath
b
et
w
ee
n
t
h
e
h
an
d
o
f
th
e
u
s
er
an
d
th
e
m
an
ip
u
lato
r
,
an
d
r
ec
alcu
l
ate
it
ea
ch
ti
m
e
t
h
e
p
o
s
itio
n
o
f
th
e
h
a
n
d
v
ar
ies
s
ig
n
i
f
ica
n
tl
y
.
T
h
e
tr
aj
ec
to
r
y
is
ca
lcu
lated
i
n
s
u
c
h
a
w
a
y
th
at
th
e
s
p
ee
d
o
f
d
is
p
lace
m
e
n
t
o
f
th
e
e
n
d
e
f
f
ec
to
r
is
co
n
tr
o
lled
,
en
s
u
r
in
g
a
li
n
ea
r
v
elo
cit
y
eq
u
al
to
ze
r
o
at
t
h
e
b
eg
in
n
i
n
g
a
n
d
en
d
o
f
t
h
e
tr
aj
ec
to
r
y
,
d
e
s
cr
ib
in
g
a
p
ar
ab
o
lic
b
eh
av
io
r
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
3
,
w
h
er
e
th
e
m
a
x
i
m
u
m
v
elo
cit
y
i
n
t
h
e
m
id
d
le
o
f
th
e
p
ath
is
r
ea
ch
ed
.
Fo
r
th
e
d
is
p
la
ce
m
en
t
o
f
t
h
e
en
d
ef
f
ec
to
r
,
a
tr
a
j
ec
to
r
y
w
i
th
c
u
b
ic
b
eh
av
io
r
is
u
s
ed
f
o
r
th
e
X
ax
is
,
th
e
Y
a
x
is
a
n
d
t
h
e
Z
ax
is
,
as
s
h
o
w
n
i
n
Fig
u
r
e
4
,
w
h
er
e
t
h
e
r
o
b
o
t
g
en
er
ates
s
m
al
l
d
i
s
p
lace
m
e
n
ts
at
th
e
en
d
s
o
f
t
h
e
tr
aj
ec
to
r
y
an
d
g
r
ea
t
ad
v
an
ce
s
i
n
th
e
m
id
d
le
o
f
it,
th
u
s
allo
w
i
n
g
to
en
s
u
r
e
t
h
e
d
esire
d
s
p
ee
d
.
Fig
u
r
e
3
.
E
n
d
ef
f
ec
to
r
v
e
lo
cit
y
Fig
u
r
e
4
.
Dis
p
lace
m
e
n
t o
f
t
h
e
en
d
ef
f
ec
to
r
T
o
ca
lcu
late
ea
ch
o
f
th
e
p
o
in
ts
o
f
th
e
tr
aj
ec
to
r
y
in
th
e
t
h
r
ee
co
o
r
d
in
ate
ax
es,
(
1
)
w
as
u
s
ed
,
w
h
ic
h
d
escr
ib
es
th
e
cu
b
ic
b
eh
a
v
io
r
s
h
o
w
n
i
n
Fi
g
u
r
e
4
,
w
h
er
e
x
(
t)
is
th
e
p
o
s
itio
n
f
u
n
ctio
n
f
o
r
an
y
o
f
t
h
e
co
o
r
d
in
ate
ax
es,
a,
b
,
c,
d
ar
e
co
n
s
tan
ts
,
an
d
t
is
th
e
ti
m
e,
w
h
ic
h
is
b
et
w
e
en
0
,
f
o
r
th
e
in
i
tial
p
o
s
itio
n
,
a
n
d
th
e
to
tal
ti
m
e
o
f
th
e
ex
ec
u
tio
n
o
f
t
h
e
m
o
v
e
m
e
n
t
(
T
t)
,
d
ef
in
ed
b
y
th
e
u
s
er
.
F
o
r
th
e
ca
lcu
latio
n
o
f
ea
c
h
o
f
t
h
e
co
n
s
tan
t
s
o
f
(
1
)
,
th
e
v
elo
cit
y
f
u
n
ctio
n
o
f
(
2
)
w
as
o
b
tain
ed
,
d
er
iv
i
n
g
eq
u
atio
n
(
1
)
w
it
h
r
esp
ec
t
to
ti
m
e,
a
n
d
it
w
as
e
s
tab
lis
h
ed
th
at
t
h
e
in
i
tial (
v
_
i)
an
d
f
in
al
v
elo
cit
y
(
v
_
f
)
s
h
o
u
ld
b
e
eq
u
al
to
ze
r
o
,
as p
r
ev
io
u
s
l
y
s
h
o
w
n
i
n
Fig
u
r
e
3
.
(
)
=
3
+
2
+
+
(
1
)
(
)
=
2
+
+
(
2
)
T
h
en
,
th
e
p
o
s
itio
n
an
d
v
elo
cit
y
f
u
n
ctio
n
s
w
er
e
ev
al
u
ate
d
f
o
r
a
ti
m
e
t=0
an
d
f
o
r
t=
T
t
t
o
f
in
d
th
e
co
n
s
tan
ts
a,
b
,
c,
d
.
Fin
all
y
,
th
e
co
n
s
ta
n
ts
f
o
u
n
d
i
n
(
1
)
w
er
e
r
ep
lace
d
,
an
d
t
w
as
r
ep
lace
d
b
y
d
i
f
f
er
e
n
t
eq
u
is
p
ac
ed
ti
m
e
i
n
s
ta
n
ts
to
g
en
er
ate
t
h
e
co
m
p
lete
tr
aj
ec
to
r
y
as
a
s
et
o
f
5
0
in
ter
m
ed
iate
p
o
in
ts
b
et
w
ee
n
th
e
in
i
tial
(
x
(
0
)
)
an
d
f
in
al
(
x
(
T
t)
)
p
o
s
itio
n
o
f
th
e
tr
aj
ec
to
r
y
,
an
d
th
e
m
a
n
ip
u
lato
r
an
d
th
e
in
v
er
s
e
k
i
n
e
m
atic
s
p
r
esen
ted
in
[
1
4
]
w
er
e
u
s
ed
to
ex
ec
u
te
t
h
e
m
o
v
e
m
en
t in
t
h
e
ap
p
licatio
n
.
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:
2088
-
8708
To
o
l d
elive
r
y
r
o
b
o
t u
s
in
g
c
o
n
v
o
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
(
Ja
vier P
in
z
o
n
-
A
r
en
a
s
)
6303
2
.
2
.
CNN
f
o
r
t
he
det
ec
t
io
n a
nd
o
rient
a
t
io
n o
f
t
he
ha
nd
T
h
e
C
NN
tr
ai
n
ed
in
[
1
3
]
w
a
s
u
s
ed
f
o
r
th
e
r
ec
o
g
n
it
io
n
a
n
d
c
lass
if
icatio
n
o
f
t
h
e
h
an
d
s
,
an
d
a
s
eg
m
e
n
tatio
n
al
g
o
r
ith
m
w
a
s
d
ev
elo
p
ed
in
w
h
ic
h
a
n
i
m
a
g
e
o
f
th
e
w
o
r
k
i
n
g
b
ac
k
g
r
o
u
n
d
is
ca
p
tu
r
ed
an
d
th
e
a
v
er
ag
e
o
f
t
h
e
to
n
es
o
f
th
e
w
h
o
le
i
m
ag
e
is
o
b
tain
ed
,
i
n
s
u
ch
a
w
a
y
th
a
t
t
h
e
o
b
j
ec
t
th
at
is
lo
ca
ted
u
n
d
er
th
e
ca
m
er
a
a
n
d
th
a
t
h
a
s
a
d
i
f
f
er
en
t
co
lo
r
to
th
e
b
ac
k
g
r
o
u
n
d
w
il
l
b
e
r
ec
o
g
n
ized
as
t
h
e
u
s
er
's
h
a
n
d
,
an
d
w
ill
b
e
cr
o
p
p
e
d
f
r
o
m
t
h
e
o
r
ig
i
n
al
i
m
ag
e
to
b
e
s
en
t
to
t
h
e
C
NN.
Data
au
g
m
e
n
tat
io
n
tec
h
n
iq
u
e
s
h
a
v
e
b
ee
n
u
s
ed
i
n
tr
ain
i
n
g
to
i
m
p
r
o
v
e
t
h
e
d
atab
ase
u
s
ed
[
2
7
]
.
On
ce
t
h
at
i
m
ag
e
i
s
e
n
ter
ed
in
th
e
C
NN,
th
e
f
ir
s
t
ac
ti
v
atio
n
o
f
t
h
e
n
et
w
o
r
k
is
e
x
tr
ac
ted
,
i.e
.
th
e
r
es
u
lt
o
f
p
ass
i
n
g
th
e
i
m
ag
e
th
r
o
u
g
h
th
e
f
ir
s
t
R
e
L
U
(
R
ec
ti
f
ied
L
i
n
ea
r
Un
it)
la
y
er
o
f
t
h
e
n
e
t
wo
r
k
,
an
d
th
e
n
it
is
b
in
ar
ized
in
o
r
d
er
to
o
b
tain
th
e
o
v
er
all
s
h
ap
e
o
f
t
h
e
h
a
n
d
,
as
s
h
o
w
n
i
n
Fi
g
u
r
e
5
.
T
h
is
f
o
r
m
allo
w
s
k
n
o
w
i
n
g
th
e
o
r
ien
tatio
n
o
f
t
h
e
h
a
n
d
,
g
e
n
er
atin
g
a
n
ellip
s
e
o
n
t
h
e
lar
g
est n
u
m
b
er
o
f
w
h
ite
p
i
x
els o
f
t
h
e
b
in
ar
ized
i
m
a
g
e,
an
d
tak
i
n
g
th
e
a
n
g
le
o
f
i
n
cli
n
atio
n
b
et
w
ee
n
t
h
e
h
o
r
izo
n
ta
l
o
f
th
e
i
m
a
g
e
a
n
d
th
e
m
aj
o
r
ax
is
o
f
th
e
e
l
lip
s
e
θ
m
s
h
o
w
n
i
n
Fi
g
u
r
e
5
.
A
d
d
iti
o
n
all
y
,
t
h
e
f
i
n
al
p
o
s
itio
n
o
f
t
h
e
h
an
d
i
s
o
b
tain
ed
w
h
en
ex
tr
ac
tin
g
t
h
e
ce
n
ter
o
f
th
e
b
o
x
th
at
co
v
er
s
it,
as
s
h
o
wn
i
n
F
ig
u
r
e
6
(
"
+"
s
ig
n
)
.
I
n
th
i
s
w
a
y
,
t
h
e
m
an
ip
u
lato
r
s
ee
k
s
t
o
b
r
in
g
t
h
e
to
o
l
to
th
e
"
+"
s
y
m
b
o
l,
an
d
w
h
e
n
p
la
ce
d
o
n
it,
ad
j
u
s
ts
th
e
o
r
ien
tat
i
o
n
o
f
t
h
e
to
o
l,
a
n
d
m
ak
e
s
s
u
r
e
th
at
w
h
en
f
in
is
h
ed
,
it h
as
n
o
t c
h
a
n
g
ed
n
eit
h
er
th
e
l
o
ca
tio
n
o
f
th
e
h
an
d
n
o
r
its
o
r
ien
tatio
n
to
f
i
n
all
y
d
eli
v
er
th
e
to
o
l
.
Fig
u
r
e
5
.
Or
ien
tatio
n
o
f
th
e
h
a
n
d
Fig
u
r
e
6
.
T
r
ac
k
in
g
th
e
h
an
d
i
n
a
r
ea
l e
n
v
ir
o
n
m
en
t
2
.
3
.
H
a
nd
t
ra
ck
ing
a
lg
o
rit
h
m
On
ce
t
h
e
m
an
ip
u
lato
r
h
as
g
r
as
p
ed
th
e
d
esire
d
to
o
l a
n
d
m
o
v
e
d
it to
th
e
p
o
s
it
io
n
s
h
o
w
n
i
n
Fi
g
u
r
e
7
(
a
)
,
it
is
p
r
o
ce
ed
ed
to
ca
lcu
late
t
h
e
f
ir
s
t
tr
ac
k
in
g
p
at
h
o
f
t
h
e
h
an
d
,
g
en
er
ati
n
g
5
0
p
o
in
ts
b
et
w
ee
n
t
h
e
c
u
r
r
en
t
p
o
s
itio
n
o
f
t
h
e
f
in
al
e
f
f
ec
to
r
(
in
itial
p
o
s
it
io
n
x
(
0
)
)
an
d
th
e
c
u
r
r
en
t
p
o
s
itio
n
o
f
t
h
e
h
a
n
d
(
f
i
n
al
p
o
s
itio
n
x
(
T
t)
)
,
w
h
ic
h
is
o
b
tain
ed
b
y
m
ea
n
s
o
f
th
e
s
eg
m
e
n
tatio
n
alg
o
r
it
h
m
,
w
h
ic
h
ex
tr
ac
ts
t
h
e
co
o
r
d
in
ates
o
f
t
h
is
o
n
e
f
r
o
m
a
n
i
m
a
g
e
o
f
t
h
e
w
o
r
k
s
p
ac
e,
lik
e
t
h
e
o
n
e
s
h
o
w
n
i
n
Fi
g
u
r
e
7
(
b
)
.
Fig
u
r
e
7
.
(
a)
I
n
itial
p
o
s
itio
n
f
o
r
h
an
d
tr
ac
k
i
n
g
a
n
d
(
b
)
ex
a
m
p
le
o
f
w
o
r
k
s
p
ac
e
ca
p
tu
r
e
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
.
6
,
Decem
b
er
2020
:
6
3
0
0
-
6
3
0
8
6304
On
ce
t
h
e
tr
aj
ec
to
r
y
is
g
e
n
er
at
ed
,
th
e
m
an
ip
u
lato
r
m
o
v
es
p
o
in
t
b
y
p
o
in
t
u
s
in
g
t
h
e
i
n
v
er
s
e
k
in
e
m
atics,
an
d
in
ea
ch
s
tep
a
p
h
o
to
o
f
t
h
e
w
o
r
k
s
p
ac
e
is
ca
p
tu
r
ed
ag
ai
n
to
s
ea
r
ch
t
h
e
h
a
n
d
ag
ai
n
a
n
d
th
u
s
d
etec
t
c
h
a
n
g
e
s
o
f
its
p
o
s
itio
n
,
i
n
a
co
n
s
tan
t
wa
y
.
Dep
en
d
in
g
o
n
h
o
w
f
ar
t
h
e
n
e
w
p
o
s
itio
n
o
f
t
h
e
h
an
d
is
l
o
ca
ted
w
ith
r
e
s
p
ec
t
to
th
e
f
ir
s
t
d
etec
ted
p
o
s
itio
n
,
s
to
r
ed
as
x
(
T
t
)
,
th
e
alg
o
r
ith
m
i
s
p
ass
ed
to
a
s
er
ies
o
f
co
n
d
itio
n
als
t
h
at
ch
a
n
g
e
th
e
tr
aj
ec
to
r
y
o
f
th
e
m
a
n
ip
u
la
to
r
to
b
r
in
g
it
to
a
n
e
w
f
i
n
al
p
o
s
itio
n
.
Fi
g
u
r
e
8
s
h
o
w
s
t
h
e
tr
aj
ec
to
r
y
ch
a
n
g
e
s
g
en
er
ated
b
y
th
e
v
ar
iatio
n
i
n
th
e
lo
ca
tio
n
o
f
t
h
e
h
an
d
d
u
r
in
g
t
h
e
tr
ac
k
in
g
p
r
o
ce
s
s
,
w
h
er
e
x
(
ta)
is
t
h
e
c
u
r
r
en
t
p
o
s
itio
n
o
f
t
h
e
h
a
n
d
,
u
1
,
u
2
,
u
3
ar
e
th
e
d
is
ta
n
ce
t
h
r
es
h
o
ld
s
th
at
d
eter
m
i
n
e
h
o
w
clo
s
e
o
r
f
ar
th
e
h
a
n
d
i
s
f
r
o
m
th
e
p
o
s
itio
n
x
(
T
t)
,
P1
%,P
2
%,P
3
%
ar
e
p
er
ce
n
tag
es
w
h
er
e
P
1
%>P2
%>P
3
%,
P
a
r
e
p
r
esen
ts
h
o
w
m
u
c
h
p
er
ce
n
tag
e
o
f
t
h
e
tr
aj
ec
to
r
y
h
a
s
tr
av
eled
t
h
e
m
a
n
ip
u
lato
r
s
o
f
ar
,
an
d
P
is
eq
u
al
to
th
e
p
er
ce
n
tag
e
P
1
%,
P
2
% o
r
P
3
% o
f
th
e
co
n
d
itio
n
al
to
w
h
i
ch
th
e
p
r
o
g
r
a
m
h
as e
n
ter
ed
.
Fig
u
r
e
8
.
Han
d
tr
ac
k
in
g
co
n
d
i
tio
n
als
I
n
th
e
f
ir
s
t
in
s
ta
n
ce
,
it
is
e
v
a
lu
ated
i
f
th
e
d
i
f
f
er
en
ce
b
et
wee
n
x
(
T
t)
an
d
x
(
ta)
is
le
s
s
t
h
an
u
1
,
i.e
.
if
t
h
e
h
a
n
d
is
clo
s
e
e
n
o
u
g
h
to
its
p
r
ev
io
u
s
p
o
s
i
tio
n
to
co
n
s
id
er
th
at
it
h
as
n
o
t
m
o
v
ed
,
o
th
er
w
i
s
e
it
is
ev
a
lu
ated
h
o
w
f
ar
it
i
s
f
r
o
m
i
ts
f
ir
s
t
p
o
s
itio
n
.
Fo
r
a
d
is
tan
ce
b
et
w
ee
n
u
1
an
d
u
2
,
it
is
s
a
id
th
at
t
h
e
h
an
d
is
n
o
t
v
er
y
f
ar
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:
2088
-
8708
To
o
l d
elive
r
y
r
o
b
o
t u
s
in
g
c
o
n
v
o
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
(
Ja
vier P
in
z
o
n
-
A
r
en
a
s
)
6305
f
r
o
m
x
(
T
t)
,
s
o
a
p
er
ce
n
tag
e
P
1
%
clo
s
e
to
1
0
0
%
is
estab
lis
h
ed
s
o
th
at
t
h
e
r
o
b
o
t
alm
o
s
t
en
d
s
its
tr
aj
ec
to
r
y
b
ef
o
r
e
co
r
r
ec
tin
g
its
d
ir
ec
tio
n
in
s
ea
r
c
h
o
f
th
e
h
a
n
d
.
Fo
r
a
d
i
s
tan
ce
b
et
w
ee
n
u
2
an
d
u
3
is
s
aid
th
at
th
e
h
an
d
i
s
f
air
l
y
f
ar
a
w
a
y
,
s
o
a
P
2
%
p
er
ce
n
tag
e
clo
s
e
to
5
0
%
is
s
et
to
a
v
o
id
th
e
en
d
e
f
f
ec
to
r
m
o
v
i
n
g
to
a
p
o
in
t
n
o
t
v
er
y
clo
s
e
to
its
f
in
a
l
o
b
j
ec
tiv
e.
F
o
r
a
d
is
tan
ce
g
r
ea
ter
t
h
a
n
u
3
,
it
i
s
s
aid
th
at
t
h
e
h
an
d
i
s
v
e
r
y
f
ar
f
r
o
m
it
s
f
ir
s
t
p
o
s
itio
n
,
s
o
a
P
3
% c
lo
s
e
to
0
% is
s
et
to
r
ec
alcu
la
te
th
e
tr
aj
ec
to
r
y
q
u
ick
l
y
a
n
d
co
r
r
ec
t th
e
d
ir
ec
tio
n
o
f
ad
v
a
n
ce
.
T
h
en
,
it
is
e
v
al
u
ated
w
h
a
t
p
er
ce
n
tag
e
o
f
t
h
e
tr
aj
ec
to
r
y
t
h
e
m
an
ip
u
lato
r
h
a
s
m
o
v
ed
(
P
a)
,
an
d
if
it
is
g
r
ea
ter
th
a
n
P
,
th
e
tr
aj
ec
to
r
y
i
s
i
m
m
ed
iatel
y
s
to
p
p
ed
an
d
th
e
n
ex
t
o
n
e
i
s
r
ec
a
lcu
lated
w
it
h
t
h
e
n
e
w
v
a
lu
e
s
o
f
x
(
0
)
an
d
x
(
T
t
)
,
o
th
er
w
i
s
e,
it
is
ex
p
ec
ted
th
at
t
h
e
m
a
n
ip
u
la
to
r
r
ea
ch
es
th
e
p
er
ce
n
tag
e
P
o
f
ad
v
an
ce
b
ef
o
r
e
s
to
p
p
in
g
t
h
e
tr
aj
ec
to
r
y
a
n
d
ca
l
cu
lati
n
g
th
e
n
e
x
t o
n
e.
I
n
ca
s
e
t
h
e
d
if
f
er
en
ce
b
et
w
ee
n
x
(
T
t)
a
n
d
x
(
ta)
is
le
s
s
t
h
a
n
u
1
,
th
e
estab
li
s
h
ed
tr
aj
ec
to
r
y
is
co
m
p
leted
,
t
h
e
d
eli
v
er
y
s
tat
u
s
o
f
t
h
e
to
o
l
i
s
ad
j
u
s
ted
,
t
h
e
cu
r
r
en
t
p
o
s
it
io
n
o
f
th
e
h
a
n
d
is
ag
ai
n
co
m
p
ar
ed
w
i
th
x
(
T
t)
,
an
d
if
it
is
s
till
les
s
th
an
u
1
,
th
e
to
o
l
is
d
eliv
er
ed
an
d
th
e
m
o
n
ito
r
i
n
g
i
s
co
m
p
leted
,
o
th
er
w
i
s
e
a
n
e
w
tr
aj
ec
to
r
y
is
r
ec
alcu
lated
w
it
h
t
h
e
n
e
w
v
al
u
es o
f
x
(
0
)
an
d
x
(
T
t)
.
2
.
4
.
Deliv
er
y
s
t
a
t
us
a
djust
m
ent
E
ac
h
ti
m
e
th
e
m
a
n
ip
u
lato
r
c
o
m
p
lete
s
1
0
0
%
o
f
its
tr
aj
ec
to
r
y
,
t
h
e
d
e
g
r
ee
o
f
r
o
tatio
n
r
eq
u
ir
ed
b
y
th
e
g
r
ip
p
er
is
ca
lcu
lated
to
eq
u
alize
its
o
r
ien
ta
tio
n
to
th
at
o
f
th
e
h
an
d
an
d
t
h
u
s
ad
j
u
s
t
th
e
t
o
o
l
to
a
cy
li
n
d
r
ical
g
r
ip
.
T
h
e
p
r
o
g
r
am
is
r
esp
o
n
s
ib
le
f
o
r
eq
u
alin
g
t
h
e
an
g
le
o
f
r
o
tatio
n
o
f
th
e
g
r
ip
p
er
θ
P
t
o
th
e
o
r
ien
tatio
n
o
f
th
e
h
an
d
θ
m
,
f
o
r
w
h
ic
h
(
3
)
to
(
6
)
ar
e
ap
p
lied
,
w
h
er
e
(
3
)
ca
lcu
lates
th
e
a
n
g
le
o
f
r
o
tatio
n
θ
R
b
et
w
ee
n
t
h
e
p
o
in
t
w
h
er
e
th
e
to
o
l
is
an
d
th
e
h
o
r
izo
n
tal
ax
i
s
o
f
th
e
s
y
s
te
m
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
9
,
in
(
4
)
ca
l
cu
lates
t
h
e
cu
r
r
en
t
o
r
ien
tatio
n
o
f
th
e
g
r
ip
p
er
θ
P
ad
d
in
g
t
h
e
p
r
ev
io
u
s
r
o
tatio
n
s
θ
i
to
its
i
n
itial
o
r
ien
tatio
n
t
h
at
is
at
-
9
0
°
f
r
o
m
θ
R
.
B
y
(
5
)
,
th
e
d
if
f
er
e
n
ce
b
et
w
ee
n
th
e
cu
r
r
en
t
r
o
tatio
n
o
f
t
h
e
h
a
n
d
θ
m
an
d
t
h
e
cu
r
r
en
t
o
r
ien
tat
i
o
n
o
f
th
e
g
r
ip
p
er
is
ca
lcu
lated
,
in
o
r
d
er
to
ad
d
th
is
d
if
f
er
e
n
ce
to
θ
P
to
e
q
u
al
it
to
th
e
o
r
ien
tatio
n
o
f
th
e
h
a
n
d
,
lead
in
g
b
y
d
ef
au
lt
th
e
to
o
l
to
b
e
lo
ca
ted
p
er
p
en
d
icu
lar
to
th
e
s
ag
ittal
p
lan
e
o
f
th
e
h
a
n
d
to
allo
w
t
h
e
c
y
li
n
d
r
ical
g
r
ip
.
I
n
(
6
)
u
p
d
ates θ
i
,
ad
d
in
g
t
h
e
n
e
w
r
o
t
atio
n
ap
p
lied
θ
Rot
to
th
e
p
r
ev
io
u
s
r
o
tatio
n
s
.
=
180°
−
ta
n
−
1
−
−
(
3
)
=
−
90°
+
(
4
)
=
−
(
5
)
=
+
(
6
)
W
h
er
e
W
an
d
H
ar
e
th
e
w
id
th
an
d
h
ei
g
h
t
o
f
th
e
i
m
a
g
e
ca
p
t
u
r
ed
b
y
t
h
e
ca
m
er
a,
r
esp
ec
tiv
el
y
,
an
d
X,
Y
ar
e
th
e
cu
r
r
en
t
co
o
r
d
in
ates
o
f
th
e
en
d
ef
f
ec
to
r
at
th
e
en
d
o
f
1
0
0
%
o
f
a
tr
a
j
ec
to
r
y
.
Fig
u
r
e
9
s
h
o
w
s
t
h
e
an
g
les
an
d
d
i
m
e
n
s
io
n
s
u
s
ed
f
o
r
t
h
e
ad
j
u
s
t
m
e
n
t
o
f
th
e
d
eliv
er
y
s
t
atu
s
,
a
s
w
ell
as
a
n
e
x
a
m
p
le
o
f
a
f
ir
s
t
o
r
ien
tatio
n
alr
ea
d
y
m
ad
e
a
n
d
t
h
e
n
e
w
a
n
g
les
to
b
e
ca
lcu
lated
,
to
g
e
n
er
ate
th
e
ad
j
u
s
t
m
e
n
t
o
f
t
h
e
to
o
l
to
a
n
e
w
p
o
s
itio
n
o
f
th
e
h
an
d
.
T
h
is
al
g
o
r
ith
m
allo
w
s
ad
j
u
s
ti
n
g
t
h
e
d
eli
v
er
y
s
tat
u
s
o
f
t
h
e
to
o
l
f
r
o
m
a
n
y
o
r
ien
tat
io
n
o
f
t
h
e
g
r
ip
p
er
to
an
y
o
r
ien
ta
tio
n
o
f
t
h
e
h
a
n
d
,
u
s
e
f
u
l
f
o
r
ca
s
es
i
n
w
h
ic
h
af
t
er
h
av
i
n
g
m
ad
e
a
f
ir
s
t
ad
j
u
s
t
m
en
t,
th
e
h
a
n
d
h
as
m
o
v
ed
an
d
t
h
e
r
o
b
o
t m
u
s
t
f
o
ll
o
w
it a
g
a
in
a
n
d
m
a
k
e
a
s
ec
o
n
d
ad
j
u
s
t
m
en
t.
Fig
u
r
e
9
.
Deliv
er
y
s
tat
u
s
ad
j
u
s
t
m
e
n
t
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
.
6
,
Decem
b
er
2020
:
6
3
0
0
-
6
3
0
8
6306
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Fig
u
r
e
1
0
s
h
o
w
s
t
h
e
r
es
u
lt
o
b
tain
ed
b
y
t
h
e
al
g
o
r
ith
m
f
o
r
a
r
ea
l
w
o
r
k
en
v
ir
o
n
m
e
n
t
s
u
c
h
as
t
h
at
p
o
s
ed
in
Fi
g
u
r
e
7
(
b
)
,
w
h
o
s
e
b
eh
a
v
i
o
r
f
o
llo
w
s
t
h
e
m
o
v
e
m
en
t
s
o
f
th
e
s
i
m
u
lated
r
o
b
o
t
in
V
R
M
L
o
f
M
A
T
L
A
B
®,
p
er
f
o
r
m
in
g
t
h
e
d
eliv
er
y
o
f
t
h
e
to
o
l
in
b
o
th
e
n
v
ir
o
n
m
en
t
s
,
v
i
r
tu
al
a
n
d
i
n
r
ea
l
ti
m
e,
s
i
m
u
lta
n
eo
u
s
l
y
.
As
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
1
0
,
th
e
s
i
m
u
latio
n
s
h
o
w
s
th
e
tr
ac
k
i
n
g
p
er
f
o
r
m
ed
b
y
t
h
e
r
o
b
o
t
to
w
ar
d
s
th
e
h
a
n
d
an
d
th
e
ad
j
u
s
t
m
en
t
o
f
t
h
e
d
eliv
er
y
s
tatu
s
o
f
t
h
e
to
o
l,
s
u
ch
a
s
t
h
e
p
o
s
itio
n
an
d
o
r
ien
tat
io
n
o
f
t
h
e
h
a
n
d
in
th
e
r
ea
l
en
v
ir
o
n
m
e
n
t.
T
h
e
o
n
l
y
d
i
f
f
er
en
ce
b
et
w
ee
n
b
o
th
s
itu
a
tio
n
s
is
th
at
t
h
e
r
ea
l
r
o
b
o
t
d
o
es
n
o
t
ad
j
u
s
t
th
e
o
r
ien
tatio
n
o
f
t
h
e
to
o
l
b
ec
a
u
s
e
it
d
o
es
n
o
t
h
a
v
e
t
h
i
s
d
e
g
r
ee
o
f
f
r
ee
d
o
m
.
T
en
te
s
t
s
w
er
e
p
er
f
o
r
m
ed
to
d
eter
m
i
n
e
th
e
av
er
ag
e
ti
m
e
it
tak
e
s
f
o
r
th
e
m
a
n
ip
u
lato
r
to
d
eliv
er
th
e
to
o
l,
f
r
o
m
its
i
n
itial
p
o
s
itio
n
f
o
r
tr
ac
k
in
g
t
h
e
h
a
n
d
s
ee
Fi
g
u
r
e
7
(
a
)
to
th
e
ad
j
u
s
t
m
en
t
o
f
th
e
d
eliv
er
y
s
tatu
s
,
m
ak
in
g
5
d
i
f
f
er
en
t
p
o
s
it
io
n
c
h
an
g
es
f
o
r
ea
c
h
te
s
t.
A
d
d
itio
n
al
l
y
,
f
r
o
m
ea
ch
o
f
t
h
e
test
s
,
th
e
d
is
ta
n
c
e
b
et
w
ee
n
th
e
p
o
s
itio
n
o
f
th
e
e
n
d
ef
f
ec
to
r
an
d
th
e
h
an
d
p
o
s
itio
n
,
ex
tr
ac
ted
b
y
t
h
e
al
g
o
r
ith
m
,
w
as
m
ea
s
u
r
ed
to
o
b
tai
n
a
m
ar
g
i
n
o
f
er
r
o
r
in
t
h
e
ac
c
u
r
ac
y
o
f
th
e
d
eliv
er
y
.
T
ab
le
1
s
h
o
w
s
th
e
ti
m
e
u
s
e
d
b
y
th
e
ap
p
licatio
n
f
o
r
th
e
d
eliv
er
y
o
f
th
e
to
o
l
an
d
th
e
d
is
t
an
ce
d
if
f
er
en
c
e
b
et
w
ee
n
th
e
d
esire
d
p
o
in
t a
n
d
th
e
f
in
al
e
f
f
ec
to
r
,
tak
en
i
n
m
ill
i
m
eter
s
.
Fig
u
r
e
10
.
Deliv
er
y
o
f
t
h
e
to
o
l b
o
th
in
s
i
m
u
latio
n
a
n
d
in
a
r
e
al
en
v
ir
o
n
m
e
n
t
T
ab
le
1
.
R
esu
lts
o
b
tain
ed
T
e
st
T
i
me
(
s)
D
i
st
a
n
c
e
e
r
r
o
r
(
mm
)
1
1
5
.
1
4
1
2
1
9
.
5
7
5
3
1
0
.
2
5
17
4
1
5
.
4
5
8
5
1
3
.
7
3
3
6
1
6
.
0
4
2
7
1
5
.
0
1
1
8
1
6
.
3
0
2
9
1
6
.
7
6
3
10
1
5
.
3
2
9
A
v
e
r
a
g
e
1
5
.
3
5
7
5
.
1
T
h
e
ap
p
licatio
n
ta
k
es
ar
o
u
n
d
1
5
s
to
tr
ac
k
th
e
h
an
d
,
w
i
th
ch
an
g
e
s
i
n
p
o
s
itio
n
d
u
r
in
g
th
e
a
p
p
licatio
n
,
an
d
it
h
as
a
m
ar
g
i
n
o
f
er
r
o
r
o
f
less
th
a
n
1
0
m
m
i
n
m
o
s
t
ca
s
es
.
As
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
1
0
,
o
n
e
o
f
t
h
e
g
r
ea
tes
t
d
if
f
ic
u
lt
ies
o
f
th
e
ap
p
licatio
n
is
t
h
e
r
ec
o
g
n
itio
n
o
f
t
h
e
h
a
n
d
w
h
en
t
h
e
m
a
n
ip
u
lato
r
i
s
n
e
ar
o
r
o
n
to
p
o
f
it.
B
ec
au
s
e
th
e
o
b
j
ec
t
d
etec
tio
n
alg
o
r
ith
m
i
n
cl
u
d
es
all
th
o
s
e
w
h
o
s
e
d
if
f
er
e
n
ce
o
f
to
n
es
w
i
t
h
th
e
b
ac
k
g
r
o
u
n
d
is
h
ig
h
er
t
h
a
n
a
t
h
r
es
h
o
ld
,
th
e
al
g
o
r
ith
m
te
n
d
s
to
r
ec
o
g
n
ize
th
e
r
o
b
o
t
as
p
ar
t
o
f
t
h
e
h
a
n
d
,
wh
ich
g
e
n
er
ates
t
h
at
th
e
s
ize
o
f
t
h
e
b
o
x
th
at
co
v
er
s
it
ex
p
an
d
s
a
n
d
co
v
er
s
t
h
e
m
a
n
ip
u
lato
r
,
d
is
p
laci
n
g
t
h
e
r
ea
l
p
o
s
itio
n
o
f
t
h
e
h
an
d
,
as
s
h
o
w
n
in
Fi
g
u
r
e
1
0
.
On
t
h
e
o
th
er
h
a
n
d
,
t
h
e
p
r
esen
ce
o
f
th
e
m
a
n
ip
u
lato
r
o
n
th
e
h
a
n
d
c
au
s
e
s
d
eter
io
r
atio
n
o
r
f
ail
u
r
e
o
f
t
h
e
d
etec
tio
n
o
f
th
e
o
r
ien
tatio
n
o
f
t
h
e
h
a
n
d
,
b
ec
au
s
e
i
n
t
h
e
f
ir
s
t
ac
ti
v
ati
o
n
o
f
t
h
e
n
et
w
o
r
k
th
e
r
o
b
o
t
is
r
ec
o
g
n
ized
as
p
a
r
t
o
f
th
e
h
an
d
,
ca
u
s
in
g
th
e
el
lip
s
e
to
en
co
m
p
ass
p
ar
t
o
f
th
e
r
o
b
o
t
an
d
d
ef
lect
th
e
in
c
lin
a
tio
n
.
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:
2088
-
8708
To
o
l d
elive
r
y
r
o
b
o
t u
s
in
g
c
o
n
v
o
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
(
Ja
vier P
in
z
o
n
-
A
r
en
a
s
)
6307
4.
CO
NCLU
SI
O
N
T
h
is
alg
o
r
ith
m
is
t
h
e
id
ea
l
co
m
p
le
m
e
n
t
f
o
r
h
u
m
a
n
-
r
o
b
o
t
in
t
er
ac
tio
n
w
o
r
k
s
,
s
u
c
h
as
t
h
e
d
ev
elo
p
m
e
n
t
o
f
as
s
is
ta
n
ce
r
o
b
o
ts
,
s
i
n
ce
it
i
s
ca
p
ab
le
o
f
e
n
s
u
r
in
g
t
h
e
d
eli
v
e
r
y
o
f
th
e
o
b
j
ec
t
d
esire
d
b
y
t
h
e
u
s
er
r
eg
ar
d
less
o
f
th
e
lo
ca
tio
n
o
f
h
is
h
a
n
d
,
its
o
r
ien
tatio
n
o
r
an
y
c
h
a
n
g
e
i
n
d
eliv
er
y
co
n
d
itio
n
s
t
h
at
o
cc
u
r
s
at
a
n
y
p
o
in
t
i
n
th
e
in
ter
ac
tio
n
p
r
o
ce
s
s
.
T
h
e
d
eliv
er
y
o
f
to
o
ls
m
ad
e
b
y
t
h
e
r
o
b
o
t
allo
w
s
th
e
u
s
er
to
co
n
ce
n
tr
ate
o
n
th
e
ta
s
k
h
e
is
d
ev
e
lo
p
in
g
,
eit
h
er
a
s
u
r
g
er
y
o
r
th
e
r
ep
air
o
f
a
v
e
h
icle,
s
i
n
ce
th
e
u
s
er
d
o
n
o
t
h
a
v
e
to
s
p
e
n
d
p
ar
t
o
f
t
h
e
ti
m
e
lo
o
k
in
g
f
o
r
a
to
o
l a
m
o
n
g
a
lar
g
e
s
et
o
f
ele
m
e
n
ts
,
b
u
t o
n
l
y
a
s
k
f
o
r
it a
n
d
w
ait
f
o
r
it to
b
e
d
e
liv
er
ed
.
I
t
is
p
r
o
p
o
s
ed
to
tr
ain
a
C
NN
th
at
r
ec
o
g
n
ize
s
th
e
h
an
d
ev
e
n
w
h
e
n
it
h
as
a
n
o
b
s
tr
u
ctio
n
o
n
it,
in
o
r
d
er
to
o
b
tain
ac
tiv
atio
n
s
ca
p
ab
le
o
f
f
o
c
u
s
i
n
g
clea
r
l
y
o
n
th
e
h
a
n
d
,
an
d
n
o
t
o
n
t
h
e
r
o
b
o
t,
an
d
to
en
s
u
r
e
th
at
th
e
b
o
x
co
v
er
in
g
th
e
h
a
n
d
is
m
o
r
e
ac
cu
r
ate
an
d
d
o
es
n
o
t
co
v
er
m
o
r
e
th
an
n
ec
e
s
s
ar
y
.
A
s
a
s
ec
o
n
d
o
p
tio
n
,
a
m
o
r
e
r
o
b
u
s
t
o
b
j
ec
t
d
etec
tio
n
alg
o
r
ith
m
co
u
ld
b
e
u
s
ed
t
h
at
o
n
l
y
e
x
tr
ac
ts
t
h
e
h
an
d
f
r
o
m
t
h
e
w
o
r
k
en
v
ir
o
n
m
e
n
t
an
d
en
ter
s
i
t
i
n
to
th
e
C
N
N
alr
ea
d
y
tr
ai
n
ed
.
Desp
ite
t
h
e
d
i
f
f
icu
lties
p
r
ese
n
ted
w
h
e
n
d
etec
ti
n
g
t
h
e
p
o
s
itio
n
an
d
o
r
ien
tat
io
n
o
f
t
h
e
h
a
n
d
,
th
e
a
lg
o
r
ith
m
h
a
s
th
e
ab
ilit
y
to
f
o
l
lo
w
t
h
e
d
esire
d
en
d
p
o
in
t,
ev
en
if
it
m
o
v
e
s
an
d
ch
an
g
es
p
o
s
itio
n
co
n
s
ta
n
tl
y
,
an
d
ca
n
a
ls
o
co
r
r
ec
t
th
e
o
r
ien
tatio
n
o
f
th
e
to
o
l,
th
e
n
u
m
b
er
o
f
ti
m
e
s
it
is
n
ec
es
s
ar
y
,
u
n
til i
t d
etec
ts
th
a
t it
r
ea
ll
y
is
i
n
t
h
e
p
o
s
itio
n
an
d
o
r
ien
tatio
n
n
ec
ess
ar
y
to
ca
r
r
y
o
u
t th
e
d
eli
v
er
y
.
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
t
h
e
Militar
Nu
e
v
a
Gr
a
n
ad
a
U
n
i
v
er
s
it
y
,
w
h
ic
h
th
r
o
u
g
h
i
ts
Vice
ch
an
ce
l
lo
r
f
o
r
r
esear
ch
f
i
n
an
ce
s
t
h
e
p
r
esen
t
p
r
o
j
ec
t
w
it
h
co
d
e
I
MP
-
I
NG
-
2
2
9
0
an
d
titl
ed
"
P
r
o
to
ty
p
e
o
f
r
o
b
o
t
ass
is
tan
ce
f
o
r
s
u
r
g
er
y
"
.
L
ik
e
w
i
s
e,
ac
k
n
o
w
led
g
e
m
e
n
t
i
s
g
i
v
en
to
th
e
p
ar
ticip
atio
n
o
f
t
h
e
en
g
i
n
ee
r
Pa
u
la
Usech
e
w
h
o
,
t
h
r
o
u
g
h
t
h
e
s
er
v
ice
p
r
o
v
is
io
n
o
r
d
er
n
u
m
b
er
0
721
/2
0
1
8
,
w
as
h
ir
ed
f
o
r
t
h
e
d
ev
elo
p
m
e
n
t
o
f
th
e
ex
p
o
s
ed
alg
o
r
it
h
m
s
.
RE
F
E
R
E
NC
E
S
[1
]
A
n
n
a
He
n
sc
h
e
l,
Ru
u
d
Ho
rte
n
siu
s,
Em
il
y
S
.
Cro
ss
,
“
S
o
c
ial
Co
g
n
it
io
n
in
t
h
e
Ag
e
o
f
Hu
m
a
n
–
Ro
b
o
t
In
tera
c
ti
o
n
,
”
T
re
n
d
s i
n
Ne
u
ro
sc
ien
c
e
s,
v
o
l.
4
3
,
n
o
.
6
,
p
p
.
3
7
3
-
3
8
4
,
2
0
2
0
.
[2
]
A
n
g
e
li
k
i
Zac
h
a
ra
k
i,
Io
a
n
n
is
Ko
sta
v
e
li
s,
“
A
n
to
n
io
s
G
a
ste
ra
to
s,
Io
a
n
n
is
D
o
k
a
s,
S
a
f
e
t
y
b
o
u
n
d
s
in
h
u
m
a
n
ro
b
o
t
in
tera
c
ti
o
n
:
A
su
rv
e
y
,
”
S
a
fety
S
c
ien
c
e
,
v
o
l.
1
2
7
,
2
0
2
0
.
[3
]
Yu
e
y
u
e
L
iu
,
Zh
ij
u
n
L
i,
Hu
a
p
i
n
g
L
iu
,
Zh
e
n
Ka
n
,
“
S
k
il
l
tran
sf
e
r
le
a
rn
in
g
f
o
r
a
u
to
n
o
m
o
u
s
ro
b
o
ts
a
n
d
h
u
m
a
n
–
ro
b
o
t
c
o
o
p
e
ra
ti
o
n
:
A
su
rv
e
y
,
”
Ro
b
o
ti
c
s a
n
d
Au
to
n
o
mo
u
s S
y
ste
ms
,
v
o
l.
12
8
,
2
0
2
0
.
[4
]
S
.
Eh
sa
n
Ha
sh
e
m
i
-
P
e
tro
o
d
i,
S
imo
n
T
h
e
v
e
n
in
,
S
e
rg
e
y
Ko
v
a
le
v
,
A
l
e
x
a
n
d
re
Do
lg
u
i,
“
Op
e
ra
ti
o
n
s
m
a
n
a
g
e
m
e
n
t
issu
e
s
in
d
e
sig
n
a
n
d
c
o
n
tr
o
l
o
f
h
y
b
rid
h
u
m
a
n
-
ro
b
o
t
c
o
ll
a
b
o
ra
ti
v
e
m
a
n
u
f
a
c
tu
rin
g
s
y
ste
m
s:
a
su
rv
e
y
,
”
An
n
u
a
l
Rev
iews
in
Co
n
tro
l,
2
0
2
0
.
[5
]
Am
in
Ha
m
e
d
,
M
e
h
d
i
T
a
le
M
a
s
o
u
leh
,
A
h
m
a
d
Ka
lh
o
r,
“
De
sig
n
a
n
d
c
h
a
ra
c
teriz
a
ti
o
n
o
f
a
b
io
-
i
n
sp
ired
3
-
DO
F
T
a
c
ti
le/F
o
rc
e
se
n
so
r
a
n
d
im
p
le
m
e
n
tatio
n
o
n
a
3
-
DO
F
d
e
c
o
u
p
led
p
a
ra
ll
e
l
m
e
c
h
a
n
ism
f
o
r
h
u
m
a
n
-
r
o
b
o
t
in
tera
c
ti
o
n
p
u
r
p
o
se
s,
”
M
e
c
h
a
tro
n
ics
,
v
o
l.
6
6
,
2
0
2
0
.
[6
]
J.
T
a
y
lo
r,
L
.
Bo
rd
e
a
u
x
,
T
.
Ca
sh
m
a
n
,
B.
Co
r
ish
,
C
.
Ke
sk
in
,
S
h
a
rp
,
T
.
,
e
t
a
l,
“
Ef
f
icie
n
t
a
n
d
p
re
c
ise
i
n
tera
c
ti
v
e
h
a
n
d
trac
k
in
g
th
ro
u
g
h
jo
i
n
t,
c
o
n
t
in
u
o
u
s
o
p
ti
m
iza
ti
o
n
o
f
p
o
se
a
n
d
c
o
rre
sp
o
n
d
e
n
c
e
s,
”
ACM
T
ra
n
sa
c
ti
o
n
s
o
n
Gr
a
p
h
ics
(T
OG)
,
v
o
l.
3
5
,
n
o
.
4
,
p
p
.
1
-
1
2
,
2
0
1
6
.
[7
]
Jin
g
F
a
n
g
,
Yu
a
n
Yu
a
n
,
“
Hu
m
a
n
-
in
-
th
e
-
l
o
o
p
o
p
ti
m
iza
ti
o
n
o
f
we
a
ra
b
le
ro
b
o
ts
to
re
d
u
c
e
th
e
h
u
m
a
n
m
e
tab
o
li
c
e
n
e
rg
y
c
o
st i
n
p
h
y
sic
a
l
m
o
v
e
m
e
n
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.
1
2
7
,
2
0
2
0
.
[8
]
Yo
n
g
W
a
n
g
,
X
ian
Wei,
Ha
o
S
h
e
n
,
L
u
Din
g
,
Jiu
q
in
g
W
a
n
,
“
Ro
b
u
st
f
u
sio
n
f
o
r
R
G
B
-
D
trac
k
in
g
u
sin
g
CNN
f
e
a
tu
re
s,
”
Ap
p
li
e
d
S
o
ft
C
o
mp
u
ti
n
g
,
v
o
l.
9
2
,
2
0
2
0
.
[9
]
Di
Yu
a
n
,
W
e
i
Ka
n
g
,
Zh
e
n
y
u
He
,
“
Ro
b
u
st
v
isu
a
l
trac
k
in
g
w
it
h
c
o
r
re
latio
n
f
il
ters
a
n
d
m
e
tri
c
lea
rn
in
g
,
”
Kn
o
wled
g
e
-
Ba
se
d
S
y
ste
ms
,
v
o
l.
1
9
5
,
2
0
2
0
.
[1
0
]
Ja
v
ier
Orla
n
d
o
P
i
n
z
ó
n
-
A
re
n
a
s,
Cé
sa
r
G
io
v
a
n
y
P
a
c
h
ó
n
-
S
u
e
sc
ú
n
a
n
d
Ro
b
in
s
o
n
Jim
é
n
e
z
-
M
o
re
n
o
,
“
As
sista
n
t
ro
b
o
t
th
ro
u
g
h
d
e
e
p
lea
rn
in
g
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
1
0
,
n
o
.
1
,
p
p
.
1
0
5
3
-
1
0
6
2
,
2
0
2
0
.
[1
1
]
Jia
o
h
u
a
Qi
n
,
W
e
n
y
a
n
P
a
n
,
X
u
y
u
X
ia
n
g
,
Yu
n
T
a
n
,
G
u
im
in
Ho
u
,
“
A
b
io
lo
g
ica
l
im
a
g
e
c
las
sif
ic
a
ti
o
n
m
e
th
o
d
b
a
se
d
o
n
im
p
ro
v
e
d
CNN
,
”
Eco
l
o
g
ica
l
I
n
fo
rm
a
t
ics
,
v
o
l.
5
8
,
2
0
2
0
.
[1
2
]
M
a
y
u
r
Bh
a
rg
a
b
Bo
ra
,
Din
th
isra
n
g
Da
i
m
a
r
y
,
Kh
wa
irak
p
a
m
Am
i
tab
,
De
b
d
a
tt
a
Ka
n
d
a
r,
“
Ha
n
d
w
rit
ten
Ch
a
ra
c
ter
Re
c
o
g
n
it
io
n
f
ro
m
I
m
a
g
e
s u
sin
g
CNN
-
ECOC,
”
Pro
c
e
d
ia
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
6
7
,
p
p
.
2
4
0
3
-
2
4
0
9
,
2
0
2
0
.
[1
3
]
Da
n
ish
V
a
sa
n
,
M
a
m
o
u
n
A
laz
a
b
,
S
o
b
ia
W
a
ss
a
n
,
Ba
b
a
k
S
a
f
a
e
i,
Qin
Zh
e
n
g
,
“
Im
a
g
e
-
Ba
se
d
m
a
l
w
a
r
e
c
las
si
f
ica
ti
o
n
u
sin
g
e
n
se
m
b
le o
f
CNN
a
rc
h
it
e
c
t
u
re
s (IM
CEC),
”
Co
m
p
u
ter
s &
S
e
c
u
rity,
v
o
l.
9
2
,
2
0
2
0
.
[1
4
]
P
a
u
la
Us
e
c
h
e
,
Ro
b
in
so
n
Jim
é
n
e
z
-
M
o
re
n
o
a
n
d
Ja
v
ier
M
a
rti
n
e
z
B
a
q
u
e
ro
,
“
A
lg
o
rit
h
m
o
f
d
e
tec
ti
o
n
,
c
las
sif
ic
a
ti
o
n
a
n
d
g
rip
p
in
g
o
f
o
c
c
lu
d
e
d
o
b
jec
ts
b
y
CNN
tec
h
n
i
q
u
e
s
a
n
d
Ha
a
r
c
las
sif
iers
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
E
n
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
1
0
,
n
o
.
2
.
p
p
.
1
3
0
8
-
1
3
1
6
,
2
0
2
0
.
[1
5
]
Cé
sa
r
G
io
v
a
n
y
P
a
c
h
ó
n
-
S
u
e
sc
ú
n
,
Ca
rlo
s
J.
En
c
iso
-
A
ra
g
o
n
a
n
d
Ro
b
i
n
so
n
Jim
é
n
e
z
-
M
o
re
n
o
,
“
Ro
b
o
ti
c
n
a
v
ig
a
ti
o
n
a
lg
o
rit
h
m
w
it
h
m
a
c
h
in
e
v
isio
n
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
lec
t
ric
a
l
a
n
d
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
1
0
,
no
.
1
,
p
p
.
1
3
2
9
-
1
3
4
2
,
2
0
2
0
.
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
.
6
,
Decem
b
er
2020
:
6
3
0
0
-
6
3
0
8
6308
[1
6
]
Ra
c
h
e
ll
e
M
o
rg
e
n
ste
rn
,
Ed
w
in
P
.
S
u
,
“
T
h
e
g
rip
p
e
r
ta
b
le
m
o
u
n
ted
re
trac
ti
o
n
sy
ste
m
:
A
ti
re
les
s
su
rg
ica
l
a
ss
istan
t,
”
S
e
min
a
rs
i
n
Art
h
ro
p
la
sty
,
v
o
l
.
2
9
,
n
o
.
3
,
p
p
.
1
3
4
-
1
3
6
,
2
0
1
8
.
[1
7
]
J.
O.
P
.
A
re
n
a
s,
P
.
C
.
U.
M
u
ri
ll
o
a
n
d
R.
J.
M
o
re
n
o
,
“
Co
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
a
rc
h
it
e
c
tu
re
f
o
r
h
a
n
d
g
e
stu
re
re
c
o
g
n
it
io
n
,
”
IEE
E
XX
IV
In
ter
n
a
ti
o
n
a
l
C
o
n
fe
re
n
c
e
o
n
E
lec
tro
n
ics
,
E
lec
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ti
n
g
(
INT
ER
CON)
,
p
p
.
1
-
4
,
2
0
1
7
.
[1
8
]
T
re
sn
a
De
w
i,
S
it
i
Nu
rm
a
in
i,
P
o
la
Rism
a
,
Yu
rn
i
Ok
tarin
a
,
M
u
h
a
m
m
a
d
Ro
riz,
“
In
v
e
rse
k
in
e
m
a
ti
c
a
n
a
l
y
sis
o
f
4
DO
F
p
ick
a
n
d
p
lac
e
a
rm
ro
b
o
t
m
a
n
ip
u
lat
o
r
u
sin
g
f
u
z
z
y
lo
g
ic
c
o
n
tro
ll
e
r,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
E
n
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
1
0
,
n
o
.
2
,
p
p
.
1
3
7
6
-
1
3
8
6
,
2
0
2
0
.
[1
9
]
P
a
u
la
Ca
talin
a
Us
e
c
h
e
M
.
a
n
d
Ro
b
i
n
so
n
Jim
é
n
e
z
-
M
o
re
n
o
,
“
De
tec
ti
o
n
a
n
d
g
rip
p
i
n
g
o
f
a
n
o
c
c
lu
d
e
d
to
o
l
u
sin
g
DAG
-
CNN
,
”
AR
PN
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
A
p
p
l
ied
S
c
ie
n
c
e
s,
v
o
l.
1
5
,
n
o
.
9
,
p
p
.
1
0
6
9
-
1
0
7
8
,
20
2
0
.
[2
0
]
M
a
ry
a
m
Ko
u
z
e
h
g
a
r,
Yo
k
h
e
sh
Krish
n
a
sa
m
y
T
a
m
il
se
lv
a
m
,
M
a
n
u
e
l
V
e
g
a
He
re
d
ia,
M
o
h
a
n
Ra
jes
h
El
a
ra
,
“
S
e
lf
-
re
c
o
n
f
ig
u
ra
b
le
f
a
ç
a
d
e
-
c
lea
n
in
g
r
o
b
o
t
e
q
u
i
p
p
e
d
w
it
h
d
e
e
p
-
lea
rn
in
g
-
b
a
se
d
c
ra
c
k
d
e
tec
ti
o
n
b
a
se
d
o
n
co
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s,
”
Au
to
m
a
ti
o
n
i
n
C
o
n
stru
c
ti
o
n
,
v
o
l.
1
0
8
,
2
0
1
9
.
[2
1
]
Zeli
W
a
n
g
,
He
n
g
L
i,
X
iao
li
n
g
Z
h
a
n
g
,
“
Co
n
str
u
c
ti
o
n
w
a
ste
re
c
y
c
li
n
g
ro
b
o
t
f
o
r
n
a
il
s
a
n
d
sc
re
w
s:
C
o
m
p
u
ter
v
isio
n
tec
h
n
o
l
o
g
y
a
n
d
n
e
u
ra
l
n
e
tw
o
rk
a
p
p
ro
a
c
h
,
”
A
u
to
m
a
ti
o
n
in
C
o
n
str
u
c
ti
o
n
,
v
o
l.
9
7
,
p
p
.
2
2
0
-
2
2
8
,
2
0
1
9
.
[2
2
]
S
im
o
n
y
a
n
,
K.
a
n
d
Zi
ss
e
r
m
a
n
,
A
.
,
“
V
e
r
y
d
e
e
p
c
o
n
v
o
lu
ti
o
n
a
l
n
e
tw
o
rk
s
f
o
r
lar
g
e
-
sc
a
le
i
m
a
g
e
re
c
o
g
n
it
io
n
,
”
a
rXiv p
re
p
ri
n
t
a
rX
iv:1
4
0
9
.
1
5
5
6
,
2
0
1
4
.
[
2
3
]
E
n
c
i
s
o
-
A
r
a
g
ó
n
,
C
.
J
.
,
P
a
c
h
ó
n
-
S
u
e
s
c
ú
n
,
C
.
G
.
a
n
d
J
i
m
e
n
e
z
-
M
o
r
e
n
o
,
R
.
,
“
Q
u
a
l
i
t
y
c
o
n
t
r
o
l
s
y
s
t
e
m
b
y
m
e
a
n
s
o
f
C
N
N
a
n
d
f
u
z
z
y
s
y
s
t
e
m
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
p
p
l
i
e
d
E
n
g
i
n
e
e
r
i
n
g
R
e
s
e
a
r
c
h
,
v
o
l
.
1
3
,
n
o
.
1
6
,
p
p
.
12846
-
1
2
8
5
3
,
2
0
1
8
.
[2
4
]
F
e
n
g
y
i
Zh
a
n
g
,
Zh
iy
o
n
g
L
iu
,
F
a
n
g
z
h
o
u
X
io
n
g
,
Jia
n
h
u
a
S
u
,
Ho
n
g
Qia
o
,
“
WAG
NN
:
A
W
e
ig
h
ted
A
g
g
re
g
a
ti
o
n
G
ra
p
h
Ne
u
ra
l
Ne
tw
o
rk
f
o
r
ro
b
o
t
sk
il
l
lea
rn
in
g
,
”
R
o
b
o
ti
c
s a
n
d
Au
t
o
n
o
mo
u
s S
y
ste
ms
,
v
o
l.
1
3
0
,
2
0
2
0
.
[2
5
]
F
u
rre
r,
F
.
,
B
u
rri,
M
.
,
A
c
h
telik
,
M
.
a
n
d
S
ieg
w
a
rt,
R.
,
“
Ro
to
rS
-
A
m
o
d
u
lar
G
a
z
e
b
o
M
A
V
sim
u
lato
r
f
ra
m
e
w
o
rk
,
”
Ro
b
o
t
Op
e
ra
ti
n
g
S
y
ste
m (
ROS
),
p
p
.
5
9
5
-
6
2
5
,
2
0
1
6
.
[2
6
]
Yo
n
g
W
a
n
g
,
X
ian
W
e
i,
Xu
a
n
T
a
n
g
,
Ha
o
S
h
e
n
,
L
u
Din
g
,
“
CNN
tr
a
c
k
in
g
b
a
se
d
o
n
d
a
ta
a
u
g
m
e
n
tatio
n
,
”
Kn
o
wled
g
e
-
Ba
se
d
S
y
ste
ms
,
v
o
l.
1
9
4
,
2
0
2
0
.
[2
7
]
T
ian
h
a
o
Hu
,
T
a
n
g
T
a
n
g
,
Ro
n
g
lai
L
in
,
M
i
n
g
Ch
e
n
,
S
h
u
f
a
Ha
n
,
Jie
W
u
,
“
A
si
m
p
le
d
a
ta
a
u
g
m
e
n
tatio
n
a
lg
o
rit
h
m
a
n
d
a
se
l
f
-
a
d
a
p
ti
v
e
c
o
n
v
o
lu
ti
o
n
a
l
a
r
c
h
it
e
c
t
u
re
f
o
r
f
e
w
-
sh
o
t
f
a
u
lt
d
i
a
g
n
o
sis
u
n
d
e
r
d
if
f
e
r
e
n
t
w
o
rk
in
g
c
o
n
d
it
i
o
n
s,
”
M
e
a
su
re
me
n
t,
v
o
l.
1
5
6
,
2
0
2
0
,
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
r
n
i
n
B
o
g
o
tá,
C
o
lo
m
b
ia,
i
n
1
9
7
8
.
He
re
c
e
iv
e
d
th
e
En
g
i
n
e
e
r
d
e
g
re
e
in
El
e
c
tro
n
ics
a
t
t
h
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
l
o
m
b
ia
-
2
0
1
2
a
n
d
P
h
D
i
n
En
g
in
e
e
rin
g
a
t
th
e
F
ra
n
c
isc
o
Jo
s
é
d
e
Ca
ld
a
s
District
Un
iv
e
rsity
-
2
0
1
8
.
He
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
a
P
ro
f
e
ss
o
r
in
th
e
M
e
c
h
a
tro
n
ics
En
g
in
e
e
rin
g
P
r
o
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
-
UMN
G
.
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
C
o
n
tro
l
,
a
c
ti
n
g
m
a
in
ly
in
:
Ro
b
o
ti
c
s,
c
o
n
tro
l,
p
a
tt
e
rn
re
c
o
g
n
it
i
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
la
n
d
o
Pi
n
z
ó
n
A
r
e
n
a
s
w
a
s
b
o
rn
in
S
o
c
o
rr
o
-
S
a
n
tan
d
e
r,
Co
lo
m
b
ia,
i
n
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
En
g
in
e
e
rin
g
(Cu
m
L
a
u
d
e
)
in
2
0
1
3
,
S
p
e
c
ializa
ti
o
n
i
n
En
g
in
e
e
rin
g
P
ro
jec
t
M
a
n
a
g
e
m
e
n
t
in
2
0
1
6
,
a
n
d
M
.
S
c
.
in
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
ry
Un
iv
e
rsity
-
UMN
G
.
He
h
a
s
e
x
p
e
rien
c
e
in
t
h
e
a
re
a
s
o
f
a
u
to
m
a
ti
o
n
,
e
lec
tro
n
ic
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.
i
n
A
p
p
li
e
d
S
c
ien
c
e
s
a
n
d
w
o
rk
in
g
a
s
a
G
ra
d
u
a
te
A
s
sista
n
t
a
t
th
e
UMNG
w
it
h
e
m
p
h
a
sis
o
n
Ro
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
Evaluation Warning : The document was created with Spire.PDF for Python.