I
AE
S In
t
er
na
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.
13
,
No
.
4
,
Dec
em
b
er
20
24
,
p
p
.
4
0
1
~
4
0
9
I
SS
N:
2722
-
2
5
8
6
,
DOI
:
1
0
.
1
1
5
9
1
/i
jr
a
.
v
13
i
4
.
pp
4
0
1
-
409
401
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
a
.
ia
esco
r
e.
co
m
Integ
ra
ting a
rtifi
cia
l immune sy
ste
ms
and
multi
-
la
y
er
percept
ro
n
-
bio
g
e
o
g
ra
phy
-
ba
sed o
ptimiza
tion
for
enh
a
nced
inv
erse kinema
ti
c
s in robo
tic
a
rm
Am
el
Sera
t
1
,
B
a
chir
Dj
ebba
r
2
1
F
a
c
u
l
t
é
d
e
s
S
c
i
e
n
c
e
s
e
t
d
e
l
a
Te
c
h
n
o
l
o
g
i
e
,
U
n
i
v
e
r
si
t
é
M
u
st
a
p
h
a
S
t
a
mb
o
u
l
i
M
a
s
c
a
r
a
,
M
a
sc
a
r
a
,
A
l
g
é
r
i
e
2
F
a
c
u
l
t
é
d
e
M
a
t
h
é
m
a
t
i
q
u
e
e
t
I
n
f
o
r
ma
t
i
q
u
e
,
U
n
i
v
e
r
si
t
é
d
e
s Sc
i
e
n
c
e
s e
t
d
e
l
a
Te
c
h
n
o
l
o
g
i
e
d
’
O
r
a
n
M
o
h
a
m
e
d
B
o
u
d
i
a
f
,
O
r
a
n
,
A
l
g
é
r
i
e
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
1
3
,
2
0
2
4
R
ev
is
ed
Au
g
2
0
,
2
0
2
4
Acc
ep
ted
Au
g
2
7
,
2
0
2
4
De
term
in
in
g
re
q
u
ired
jo
i
n
t
a
n
g
les
to
a
c
h
iev
e
a
d
e
sire
d
p
o
sit
io
n
in
a
m
a
n
ip
u
lat
o
r
’
s
a
rm
is
a
c
o
m
p
li
c
a
ted
p
r
o
b
lem
wit
h
o
u
t
sim
p
le
a
n
a
ly
ti
c
a
l
so
lu
ti
o
n
s.
T
h
is
p
a
p
e
r
re
se
a
rc
h
e
s
se
v
e
ra
l
c
o
m
p
u
tatio
n
a
l
m
e
th
o
d
s
b
a
se
d
o
n
a
rti
ficia
l
in
telli
g
e
n
c
e
(AI)
fo
r
c
a
lcu
latin
g
th
e
j
o
in
t
p
o
si
ti
o
n
s
o
f
t
h
e
6
-
DO
F
ro
b
o
ti
c
a
rm
.
We
c
a
n
e
x
trap
o
late
re
lev
a
n
c
e
,
fo
r
e
x
a
m
p
le,
to
t
h
e
c
r
u
c
ial
ro
le
th
a
t
ro
b
o
ti
c
m
a
n
ip
u
lato
r
a
rm
s
p
l
a
y
in
in
d
u
strial
a
n
d
m
e
d
ica
l
a
p
p
li
c
a
ti
o
n
s,
wh
e
re
e
n
h
a
n
c
e
d
p
re
c
isio
n
a
n
d
m
o
v
e
m
e
n
t
e
fficie
n
c
y
m
a
y
sh
a
rp
ly
b
o
o
st
p
e
rfo
rm
a
n
c
e
a
n
d
e
x
p
a
n
d
a
p
p
li
c
a
b
il
it
y
.
He
re
,
we
in
v
e
stig
a
te
t
h
e
e
ff
e
c
ti
v
e
n
e
ss
o
f
m
e
th
o
d
s,
su
c
h
a
s
th
e
a
rti
fici
a
l
imm
u
n
e
sy
ste
m
(AIS)
a
n
d
m
u
lt
i
-
lay
e
r
p
e
rc
e
p
tro
n
-
b
io
g
e
o
g
ra
p
h
y
-
b
a
se
d
o
p
ti
m
iza
ti
o
n
(M
L
P
-
BBO).
T
h
o
se
AI
-
d
riv
e
n
m
e
th
o
d
s
h
a
v
e
b
e
e
n
a
p
p
li
e
d
to
d
e
term
in
e
jo
in
t
a
n
g
les
f
o
r
re
a
c
h
in
g
d
e
sire
d
p
o
siti
o
n
s
t
h
ro
u
g
h
sim
u
lati
o
n
s
fo
r
th
e
ro
b
o
ti
c
a
rm
.
Th
e
re
su
lt
s
sh
o
w
th
a
t
th
e
AIS
a
n
d
M
L
P
-
BBO
a
p
p
r
o
a
c
h
c
a
n
h
a
n
d
le
th
e
in
tri
n
sic
c
o
m
p
le
x
i
ti
e
s
o
f
th
e
tas
k
,
th
u
s
tes
ti
f
y
in
g
t
o
t
h
e
p
ra
c
ti
c
a
b
il
it
y
a
n
d
d
e
p
e
n
d
a
b
i
li
ty
o
f
t
h
e
se
two
m
e
th
o
d
s
in
t
h
is
a
p
p
li
c
a
ti
o
n
.
F
ro
m
th
e
fin
d
in
g
s
in
t
h
e
stu
d
y
,
it
wa
s
in
d
ica
ted
th
a
t
AI
-
d
ri
v
e
n
tec
h
n
i
q
u
e
s
c
a
n
e
ffe
c
ti
v
e
ly
a
n
sw
e
r
t
h
e
c
o
m
p
le
x
p
r
o
b
lem
o
f
t
h
e
ro
b
o
ti
c
m
a
n
ip
u
lato
r
a
rm
in
fi
n
d
i
n
g
jo
in
t
a
n
g
les
.
K
ey
w
o
r
d
s
:
6
-
DOF
Ar
tific
ial
im
m
u
n
e
s
y
s
tem
Ar
tific
ial
in
tellig
en
ce
-
d
r
iv
en
m
eth
o
d
s
I
n
v
er
s
e
k
in
e
m
atics
Mu
lti
-
lay
er
p
er
ce
p
tr
o
n
-
b
io
g
eo
g
r
ap
h
y
-
b
ased
o
p
tim
izatio
n
R
o
b
o
tic
ar
m
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
:
Am
el
Ser
at
Facu
lté
d
es Scien
ce
s
et
d
e
la
T
ec
h
n
o
lo
g
ie,
Un
iv
er
s
ité
Mu
s
tap
h
a
Stam
b
o
u
li M
ascar
a
–
UM
SM
Ma
s
ca
r
a,
Alg
ér
ie
E
m
ail: a
.
s
er
at@
u
n
iv
-
m
ascar
a.
d
z;
s
er
r
at_
am
el@
y
ah
o
o
.
f
r
1.
I
NT
RO
D
UCT
I
O
N
I
n
v
er
s
e
k
in
em
atics
(
I
K)
h
as
m
ad
e
a
m
ar
k
e
d
ad
v
a
n
ce
in
th
e
f
ield
o
f
r
o
b
o
tics
with
th
e
co
m
b
in
atio
n
o
f
m
an
y
t
y
p
es
o
f
co
m
p
u
tatio
n
al
m
eth
o
d
o
l
o
g
ies
in
to
th
e
I
K
h
u
r
d
le.
T
h
e
in
v
e
r
s
e
k
in
em
atics
is
a
v
er
y
f
u
n
d
am
e
n
tal
p
ar
t
o
f
r
o
b
o
tic
m
o
tio
n
p
lan
n
in
g
wh
ich
d
ea
ls
with
b
ein
g
ab
le
to
f
in
d
th
e
jo
in
t m
o
v
em
en
ts
th
at
r
esu
lt
in
an
e
n
d
-
ef
f
ec
to
r
p
o
s
itio
n
o
f
th
e
r
o
b
o
t
[
1
]
.
Old
er
tec
h
n
iq
u
es
f
ac
e
d
p
r
o
b
lem
s
o
f
r
e
d
u
n
d
an
cy
a
n
d
co
n
v
er
g
en
ce
i
n
co
m
p
lex
r
o
b
o
tic
s
y
s
tem
s
.
E
ar
ly
in
n
o
v
ativ
e
r
esear
ch
[
1
]
,
[
2
]
d
is
cu
s
s
ed
f
u
zz
y
l
o
g
ic
tech
n
iq
u
es
as
th
e
f
ir
s
t
t
o
p
io
n
ee
r
th
e
r
ef
in
e
m
en
t
o
f
I
K
s
o
lu
tio
n
s
an
d
to
en
h
an
ce
co
n
v
er
g
e
n
ce
in
r
ed
u
n
d
an
t
r
o
b
o
t
wo
r
k
s
p
ac
es.
Acc
o
r
d
in
g
ly
,
th
e
ap
p
r
o
ac
h
lai
d
d
o
wn
th
e
b
ases
f
o
r
w
o
r
k
th
a
t
ca
n
b
e
im
p
r
o
v
ed
u
p
o
n
in
th
e
f
u
tu
r
e.
B
u
ild
in
g
o
n
th
ese
b
asics
,
Mo
m
an
i
et
a
l
.
[
3
]
ex
p
a
n
d
ed
t
h
e
f
r
o
n
tier
b
y
r
esear
ch
in
g
tr
ad
itio
n
al
a
n
d
co
n
tin
u
o
u
s
g
en
etic
alg
o
r
ith
m
s
th
at
o
f
f
er
m
u
c
h
f
a
s
ter
r
ates
o
f
co
n
v
er
g
en
ce
f
o
r
th
e
o
p
tim
izatio
n
o
f
I
K
p
r
o
b
le
m
s
in
3
-
DOF
r
o
b
o
t
ar
m
s
.
On
th
e
o
th
er
h
an
d
,
n
eu
r
al
n
etwo
r
k
s
h
av
e
b
ee
n
em
p
lo
y
ed
f
o
r
I
K
r
eso
lu
tio
n
u
s
in
g
C
ar
tesi
an
tr
ajec
to
r
ies.
Du
k
a
[
4
]
u
s
ed
n
eu
r
al
n
etw
s
o
r
k
s
f
o
r
th
e
I
K
r
eso
lu
tio
n
in
3
-
DOF
r
o
b
o
ts
.
I
n
th
is
wo
r
k
,
s
o
lu
tio
n
s
wer
e
ac
cu
r
ately
cr
ea
ted
b
y
3
-
DOF
r
o
b
o
ts
u
s
in
g
C
ar
tesi
an
tr
ajec
t
o
r
ies.
On
th
e
o
th
er
h
an
d
,
T
a
k
atan
i
et
a
l
.
[
5
]
an
d
Hab
ib
k
h
ah
an
d
Ma
y
o
r
g
a
[
6
]
p
r
o
p
o
s
ed
a
n
ew
n
e
u
r
al
n
et
wo
r
k
ar
ch
itectu
r
e
s
p
ec
ially
d
esig
n
ed
f
o
r
3
-
DOF
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
13
,
No
.
4
,
Dec
em
b
er
20
24
:
40
1
-
4
0
9
402
r
ed
u
n
d
an
t
r
o
b
o
ts
.
T
h
is
ex
p
e
r
im
en
tal
s
etu
p
d
em
o
n
s
tr
ates
a
h
ig
h
ly
ef
f
icien
t
way
o
f
le
ar
n
in
g
b
ec
a
u
s
e
o
f
h
y
b
r
id
izatio
n
an
d
d
ata
-
d
r
iv
e
n
s
y
n
th
esis
.
T
h
er
ef
o
r
e,
th
e
lea
r
n
in
g
p
er
f
o
r
m
an
ce
is
im
p
r
ess
iv
e.
T
h
ese
ef
f
o
r
ts
d
em
o
n
s
tr
ate
a
ch
an
g
e
in
th
e
a
p
p
licatio
n
o
f
co
m
p
u
tatio
n
al
m
eth
o
d
o
l
o
g
ies
with
r
o
b
o
tic
k
in
em
atics,
m
ak
in
g
a
n
ew
er
a
o
f
ef
f
ec
tiv
en
ess
an
d
p
r
ec
is
en
ess
in
r
o
b
o
t
m
an
ip
u
la
tio
n
s
.
T
ab
le
1
s
h
o
ws
a
s
u
m
m
ar
y
o
f
s
o
m
e
o
f
th
e
p
io
n
ee
r
in
g
r
esear
c
h
co
n
d
u
cte
d
in
th
e
f
ield
o
f
r
o
b
o
tics
,
f
o
c
u
s
in
g
o
n
a
d
v
an
ce
m
en
ts
u
s
ed
t
o
s
o
lv
e
I
K
p
r
o
b
lem
s
.
E
ac
h
en
tr
y
lis
ts
lead
in
g
wo
r
k
wh
er
e
r
esear
ch
er
s
h
av
e
a
p
p
lie
d
v
ar
ied
co
m
p
u
tatio
n
al
m
eth
o
d
o
lo
g
ies
to
f
u
r
th
er
I
K
s
o
lu
tio
n
s
.
T
ab
le
1
.
Ov
e
r
v
iew
o
f
c
o
m
p
u
tatio
n
al
m
eth
o
d
s
in
r
o
b
o
tics
M
e
t
h
o
d
A
u
t
h
o
r
s
Y
e
a
r
F
u
z
z
y
l
o
g
i
c
t
e
c
h
n
i
q
u
e
A
g
g
o
g
e
r
i
e
t
a
l
.
[
2
]
2
0
1
5
G
e
n
e
t
i
c
a
l
g
o
r
i
t
h
ms (
G
A
)
M
o
ma
n
i
e
t
a
l
.
[
3
]
2
0
1
6
F
e
e
d
-
f
o
r
w
a
r
d
n
e
u
r
a
l
n
e
t
w
o
r
k
D
u
k
a
[
4
]
2
0
1
4
N
e
u
r
a
l
n
e
t
w
o
r
k
st
r
u
c
t
u
r
e
Ta
k
a
t
a
n
i
e
t
a
l
.
[
5
]
2
0
1
9
N
o
n
-
c
o
n
v
e
n
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
v
i
r
t
u
a
l
v
e
c
t
o
r
f
u
n
c
t
i
o
n
me
t
h
o
d
H
a
b
i
b
k
h
a
h
a
n
d
M
a
y
o
r
g
a
[
6
]
2
0
2
1
Le
a
s
t
s
q
u
a
r
e
s (LS
)
,
R
e
c
u
r
si
v
e
l
e
a
st
sq
u
a
r
e
(
R
LS)
,
a
n
d
P
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
(PSO)
B
a
t
i
st
a
e
t
a
l
.
[
7
]
2
0
2
0
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
(
A
N
N
s)
S
a
n
t
o
s
e
t
a
l
.
[
8
]
2
0
2
2
C
o
m
b
i
n
a
t
i
o
n
o
f
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
ms a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
s
K
h
a
l
e
e
l
[
9
]
2
0
1
8
P
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
(PSO)
H
a
ssan
e
t
a
l
.
[
1
0
]
2
0
2
2
T
h
is
p
ap
er
i
n
tr
o
d
u
ce
s
n
o
v
el
ap
p
r
o
ac
h
es
in
th
e
d
o
m
ai
n
o
f
I
K
f
o
r
r
o
b
o
tics
,
aim
in
g
to
e
n
h
an
ce
t
h
e
r
o
b
u
s
tn
ess
an
d
ad
ap
tab
ilit
y
o
f
r
o
b
o
tic
s
y
s
tem
s
ac
r
o
s
s
v
ar
io
u
s
en
v
ir
o
n
m
en
ts
.
T
h
ese
ap
p
r
o
a
ch
es
m
ar
k
an
o
th
er
s
ig
n
if
ican
t
s
tep
f
o
r
wa
r
d
in
th
e
f
ield
’
s
ev
o
l
u
tio
n
.
Alo
n
g
s
id
e
estab
lis
h
ed
m
eth
o
d
o
lo
g
ies
li
k
e
f
u
zz
y
lo
g
ic
[
2
]
,
in
n
o
v
ativ
e
s
tr
ateg
ies
b
ased
o
n
PS
O
[
7
]
,
[
1
0
]
an
d
ANN
[
8
]
,
[
9
]
h
a
v
e
em
er
g
e
d
as
p
r
o
m
is
in
g
av
en
u
es
f
o
r
en
h
an
cin
g
I
K
r
eso
lu
tio
n
.
W
e
p
r
o
p
o
s
e
th
e
u
s
e
o
f
t
h
e
ar
tific
ial
im
m
u
n
e
s
y
s
tem
,
in
s
p
ir
ed
b
y
th
e
h
u
m
an
im
m
u
n
e
s
y
s
tem
’
s
ad
ap
tiv
e
an
d
lear
n
in
g
ca
p
a
b
ilit
ies,
alo
n
g
with
m
u
lti
-
lay
er
p
er
ce
p
tr
o
n
-
b
i
o
g
eo
g
r
ap
h
y
-
b
ased
o
p
tim
izatio
n
(
ML
P
-
B
B
O)
.
T
h
ese
m
eth
o
d
s
p
r
o
v
i
d
e
a
u
n
iq
u
e
f
r
am
ewo
r
k
f
o
r
o
p
tim
izin
g
I
K
s
o
lu
tio
n
s
,
m
ar
k
in
g
a
n
o
th
er
s
ig
n
if
ican
t step
f
o
r
war
d
in
th
e
ev
o
lu
tio
n
o
f
th
e
f
ield
.
T
h
e
o
b
j
ec
tiv
e
o
f
th
is
s
tu
d
y
is
to
d
em
o
n
s
tr
ate
th
e
ef
f
icac
y
o
f
th
ese
ap
p
r
o
ac
h
es
in
im
p
r
o
v
in
g
I
K
r
eso
lu
tio
n
,
th
u
s
co
n
t
r
ib
u
tin
g
to
t
h
e
o
n
g
o
in
g
ad
v
a
n
ce
m
en
ts
in
r
o
b
o
tic
m
an
ip
u
latio
n
s
.
T
h
e
co
n
tr
i
b
u
tio
n
s
o
f
th
is
m
an
u
s
cr
ip
t a
r
e
as f
o
llo
ws
.
−
I
n
tr
o
d
u
ctio
n
o
f
th
e
a
r
tific
ial
im
m
u
n
e
s
y
s
tem
:
T
h
is
n
o
v
el
a
p
p
r
o
ac
h
f
o
r
I
K
r
eso
lu
tio
n
lev
er
ag
es
ad
ap
tiv
e
an
d
lear
n
in
g
ca
p
a
b
ilit
ies to
en
h
an
ce
p
er
f
o
r
m
a
n
ce
.
−
Dev
elo
p
m
en
t
o
f
th
e
ML
P
-
B
B
O
f
r
am
ewo
r
k
:
T
h
is
co
m
b
i
n
es
n
eu
r
al
n
etwo
r
k
s
with
b
i
o
g
eo
g
r
ap
h
y
-
b
ased
o
p
tim
izatio
n
,
im
p
r
o
v
i
n
g
th
e
r
o
b
u
s
tn
ess
an
d
ad
ap
tab
ilit
y
o
f
I
K
s
o
lu
tio
n
s
.
−
C
o
m
p
r
eh
en
s
iv
e
e
v
alu
atio
n
:
T
h
e
m
eth
o
d
s
a
r
e
e
v
alu
ated
o
n
th
e
6
-
DOF
R
o
b
o
t
ar
m
,
d
em
o
n
s
tr
atin
g
s
ig
n
if
ican
t im
p
r
o
v
em
en
ts
in
c
o
n
v
er
g
en
ce
s
p
ee
d
,
p
r
ec
is
io
n
,
a
n
d
co
m
p
u
tatio
n
al
ef
f
icien
cy
.
B
y
ad
d
r
ess
in
g
th
ese
n
o
v
el
asp
ec
ts
,
th
is
p
ap
er
aim
s
to
s
et
a
n
ew
b
en
ch
m
a
r
k
in
th
e
f
ield
o
f
r
o
b
o
tic
in
v
er
s
e
k
in
em
atics,
o
f
f
er
in
g
p
r
ac
tical
s
o
lu
tio
n
s
to
ex
is
tin
g
ch
allen
g
e
s
an
d
p
av
in
g
th
e
way
f
o
r
m
o
r
e
ad
v
an
ce
d
r
o
b
o
tic
ap
p
licatio
n
s
[
1
]
–
[
1
3
]
.
T
h
e
s
u
b
s
e
q
u
e
n
t
s
e
c
ti
o
n
s
o
f
t
h
e
p
a
p
e
r
a
r
e
s
t
r
u
c
t
u
r
e
d
as
f
o
l
l
o
ws
:
t
h
e
s
e
c
o
n
d
s
e
c
t
i
o
n
p
r
es
e
n
t
s
th
e
P
U
MA
5
6
0
r
o
b
o
t
a
r
m
.
T
h
e
t
h
i
r
d
a
n
d
f
o
u
r
t
h
s
e
c
t
i
o
n
s
d
el
v
e
i
n
t
o
t
h
e
a
r
t
i
f
i
ci
a
l
i
m
m
u
n
e
s
y
s
te
m
(
AI
S
)
a
n
d
m
u
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
(
M
L
P
)
t
r
a
i
n
e
d
b
y
B
B
O
,
r
es
p
e
c
ti
v
e
l
y
,
el
u
c
i
d
a
ti
n
g
t
h
e
i
r
a
p
p
li
c
a
t
i
o
n
i
n
t
h
is
s
t
u
d
y
.
T
h
e
f
i
f
t
h
s
e
c
ti
o
n
s
h
o
w
c
as
e
s
c
o
m
p
u
t
at
i
o
n
a
l
r
esu
l
t
s
d
e
r
i
v
e
d
f
r
o
m
t
h
e
p
r
o
p
o
s
e
d
m
e
t
h
o
d
o
l
o
g
i
e
s
,
p
r
o
v
i
d
i
n
g
i
n
s
i
g
h
ts
i
n
t
o
t
h
ei
r
e
f
f
i
c
a
c
y
a
n
d
p
e
r
f
o
r
m
a
n
c
e
.
F
i
n
a
l
l
y
,
t
h
e
p
a
p
e
r
c
o
n
c
l
u
d
e
s
by
s
u
m
m
a
r
i
z
i
n
g
c
o
n
c
l
u
s
i
o
n
s
a
n
d
f
u
t
u
r
e
p
e
r
s
p
e
c
t
i
v
es
,
o
u
t
l
i
n
i
n
g
k
e
y
f
i
n
d
i
n
g
s
,
a
n
d
s
u
g
g
e
s
t
i
n
g
p
o
t
e
n
ti
a
l
a
v
e
n
u
es
f
o
r
f
u
r
t
h
e
r
e
x
p
l
o
r
a
t
i
o
n
a
n
d
d
e
v
e
l
o
p
m
e
n
t
.
2.
P
UM
A
5
6
0
RO
B
O
T
ARM
A
r
o
b
o
tic
s
y
s
tem
wo
r
k
s
as
a
clo
s
ed
-
lo
o
p
,
with
its
co
m
p
o
n
e
n
ts
(
m
ec
h
an
ical,
elec
tr
o
n
ics,
an
d
co
m
p
u
ter
alg
o
r
ith
m
s
)
wo
r
k
in
g
with
ea
ch
o
th
er
to
co
llect
an
d
r
u
n
c
o
m
m
an
d
s
ag
ain
an
d
ag
ain
.
First,
th
e
r
o
b
o
t
’
s
c
o
m
p
u
te
r
in
ter
p
r
ets
i
n
f
o
r
m
atio
n
co
llected
f
r
o
m
th
e
en
v
ir
o
n
m
en
t
th
r
o
u
g
h
s
en
s
o
r
s
.
T
h
en
,
d
ed
icate
d
m
eth
o
d
s
u
s
e
th
e
co
llected
d
ata
to
co
n
tr
o
l
co
m
m
an
d
s
to
b
e
s
en
t
to
m
o
to
r
s
[
1
4
]
.
T
h
ese
co
m
m
an
d
s
th
en
in
s
tr
u
ct
th
e
m
ec
h
an
ical
co
m
p
o
n
e
n
ts
to
ca
r
r
y
o
u
t
th
e
task
s
.
C
o
n
tin
u
o
u
s
m
o
n
ito
r
in
g
d
u
r
in
g
o
p
e
r
a
tio
n
s
is
ess
en
tia
l
to
co
r
r
ec
t a
n
y
m
o
v
em
en
t e
r
r
o
r
s
a
n
d
en
s
u
r
e
task
s
ar
e
p
er
f
o
r
m
ed
ac
cu
r
ately
.
I
n
r
o
b
o
tics
,
th
e
r
an
g
e
o
f
m
o
ti
o
n
o
f
a
m
a
n
ip
u
lato
r
ar
m
is
k
n
o
wn
as
its
wo
r
k
s
p
ac
e
.
T
h
e
m
an
ip
u
lato
r
ar
m
is
ty
p
ically
m
o
u
n
ted
o
n
a
f
ix
ed
b
ase,
wh
ic
h
ca
n
b
e
th
e
f
lo
o
r
,
ce
ilin
g
,
o
r
a
s
p
ec
ial
p
latf
o
r
m
s
u
ch
as
an
o
p
er
atin
g
tab
le.
I
t
is
a
s
er
ies
o
f
jo
in
ts
an
d
lin
k
s
co
n
n
ec
ted
to
a
b
ase.
T
h
e
en
d
-
ef
f
ec
t
o
r
,
lo
ca
ted
at
th
e
f
in
al
lin
k
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
I
n
teg
r
a
tin
g
a
r
tifi
cia
l imm
u
n
e
s
ystem
s
a
n
d
mu
lti
-
la
ye
r
p
ercep
tr
o
n
-
b
io
g
e
o
g
r
a
p
h
y
-
b
a
s
ed
…
(
A
mel
S
era
t
)
403
as
s
h
o
wn
in
Fig
u
r
e
1
,
is
th
e
to
o
l
t
h
at
th
e
r
o
b
o
t
u
s
es
wh
en
p
e
r
f
o
r
m
in
g
task
s
[
1
5
]
.
Dep
en
d
i
n
g
o
n
th
e
ap
p
licatio
n
,
th
is
en
d
-
ef
f
ec
to
r
c
o
u
ld
b
e
a
n
ee
d
le,
g
r
asp
er
,
s
ca
lp
el,
o
r
a
n
o
th
er
im
p
lem
en
t.
Fig
u
r
e
1
.
PUMA5
6
0
ar
m
I
n
th
is
p
ap
er
,
we
f
o
cu
s
o
n
th
e
PUMA5
6
0
[
1
6
]
m
o
d
el,
s
h
o
wn
in
Fig
u
r
e
1
,
a
r
o
b
o
tic
ar
m
with
s
ix
j
o
in
t
an
g
les
lab
eled
Q
1
,
Q
2
,
Q
3
,
.
.
.
,
Q
6
.
Ou
r
m
ain
g
o
al
is
to
d
eter
m
in
e
th
ese
a
n
g
les
to
r
ea
ch
a
tar
g
et
p
o
s
itio
n
in
C
ar
tesi
an
s
p
ac
e.
B
elo
w
we
g
i
v
e
a
s
im
p
lifie
d
m
ath
em
atica
l
p
r
o
ce
s
s
u
s
ed
to
s
o
lv
e
th
is
p
r
o
b
lem
.
I
n
p
u
t: T
ar
g
et
p
o
s
itio
n
(
M)
Ou
tp
u
t: Jo
in
t a
n
g
le
p
ar
am
eter
s
(
Q)
Pro
ce
d
u
r
e:
−
Def
in
e
Q
as th
e
v
ec
to
r
o
f
m
o
d
el
p
ar
am
eter
s
: Q
=
(
Q
1
, Q
2
, Q
3
, ..., Q
6
).
−
So
lv
e
f
o
r
Q
s
u
c
h
th
at
f
(
Q)
-
M
=
0
.
T
h
e
s
o
lu
tio
n
r
eq
u
ir
es
o
p
tim
iz
in
g
n
o
r
m
|
|
f
(
Q)
-
M|
|
,
wh
ich
lan
d
s
u
p
t
h
e
en
d
-
ef
f
ec
to
r
in
t
h
e
d
esire
d
p
o
s
itio
n
.
T
h
is
m
u
s
t
b
e
with
a
cc
u
r
ate
p
r
ec
is
io
n
.
T
h
is
p
r
o
ce
s
s
is
cr
u
cial
to
th
e
PUMA5
6
0
r
o
b
o
t
an
d
an
y
o
th
er
r
o
b
o
t,
e
n
ab
lin
g
th
em
to
p
er
f
o
r
m
its
task
s
ac
cu
r
ately
an
d
ef
f
e
ctiv
ely
.
3.
ARTI
F
I
CI
AL
I
M
M
UN
E
SY
ST
E
M
T
h
e
AI
S
is
a
co
m
p
u
tatio
n
al
m
o
d
el
in
s
p
ir
ed
b
y
th
e
co
m
p
le
x
ity
o
f
m
am
m
alian
im
m
u
n
e
s
y
s
tem
s
.
T
h
is
in
ter
d
is
cip
lin
ar
y
f
ield
,
o
f
te
n
ca
lled
co
m
p
u
tatio
n
al
im
m
u
n
o
lo
g
y
,
is
r
a
p
id
ly
g
r
o
win
g
.
AI
S
p
r
o
v
id
es
im
m
u
n
o
lo
g
is
ts
with
a
p
o
wer
f
u
l
to
o
l
f
o
r
e
x
p
lo
r
ato
r
y
,
ex
p
er
i
m
en
tal,
an
d
p
r
e
d
ictiv
e
task
s
t
h
at
ar
e
c
u
m
b
er
s
o
m
e
o
r
im
p
r
ac
tical
with
tr
a
d
itio
n
al
lab
o
r
ato
r
y
m
eth
o
d
s
.
T
h
e
m
ain
p
u
r
p
o
s
e
o
f
AI
S
is
to
d
ev
elo
p
co
m
p
u
tatio
n
al
s
y
s
tem
s
th
at
m
im
ic
v
ar
io
u
s
f
u
n
ctio
n
s
o
f
m
am
m
alian
im
m
u
n
e
s
y
s
tem
s
,
wh
ich
p
r
o
tect
th
e
b
o
d
y
ag
ain
s
t
f
o
r
eig
n
an
tig
en
s
b
y
d
is
tin
g
u
i
s
h
in
g
two
en
titi
es:
s
elf
an
d
n
o
n
-
s
elf
.
T
h
ese
s
y
s
tem
s
len
d
a
h
an
d
t
o
r
esear
ch
er
s
g
ain
n
ew
in
s
ig
h
ts
in
to
co
m
p
l
ex
im
m
u
n
o
lo
g
ical
p
h
en
o
m
en
a
t
h
at
m
ig
h
t
b
e
d
if
f
icu
lt
to
i
n
ter
p
r
et
o
th
er
wis
e
[
1
7
]
.
E
n
clo
s
ed
b
y
AI
S,
n
u
m
er
o
u
s
m
eth
o
d
s
h
a
v
e
b
ee
n
d
ev
elo
p
ed
to
m
o
d
el
d
if
f
er
en
t
m
am
m
alian
im
m
u
n
e
f
u
n
ctio
n
s
id
es.
No
tab
le
ex
am
p
l
es
in
clu
d
e
th
e
th
r
ee
m
ain
co
n
ce
p
ts
o
f
im
m
u
n
e
f
u
n
ctio
n
:
n
eg
ativ
e
s
elec
tio
n
,
im
m
u
n
e
n
etwo
r
k
,
an
d
clo
n
al
s
elec
tio
n
wer
e
d
is
cu
s
s
ed
in
[
1
8
]
.
Un
d
er
s
tan
d
in
g
th
e
co
m
p
lex
p
r
o
ce
s
s
es
o
f
th
e
h
u
m
a
n
im
m
u
n
e
s
y
s
tem
ex
p
o
s
es
a
s
o
p
h
is
ticated
co
n
n
ec
tio
n
am
o
n
g
m
a
n
y
ty
p
es
o
f
im
m
u
n
ity
.
W
e
ad
d
r
ess
h
o
w
th
ese
id
ea
s
af
f
ec
t
o
u
r
co
m
p
u
tatio
n
al
ap
p
r
o
ac
h
es
in
th
e
s
ec
tio
n
th
at
f
o
llo
ws
o
n
th
e
s
ig
n
if
ica
n
t
v
ar
iatio
n
s
an
d
lin
k
s
am
o
n
g
in
n
ate
im
m
u
n
ity
,
ad
ap
tiv
e
im
m
u
n
ity
,
an
d
clo
n
al
s
elec
tio
n
.
L
ik
e
a
m
icr
o
b
io
lo
g
is
t,
in
n
ate
im
m
u
n
ity
,
also
k
n
o
wn
as
n
o
n
-
s
p
ec
if
ic
im
m
u
n
ity
,
is
th
e
p
r
im
ar
y
d
ef
e
n
s
iv
e
m
ec
h
an
is
m
th
e
b
o
d
y
u
s
es
ag
ain
s
t
o
u
ts
id
e
in
tr
u
d
er
s
.
Natu
r
al
an
d
p
r
esen
t
f
r
o
m
b
i
r
th
,
th
is
im
m
u
n
e
r
esp
o
n
s
e
p
r
o
v
id
es
g
en
er
al
d
ef
en
s
e
a
g
ain
s
t m
an
y
d
i
f
f
er
en
t illn
ess
es a
n
d
an
tig
e
n
s
[
1
7
]
.
A
f
u
n
d
am
en
tal
p
ar
t
o
f
th
e
im
m
u
n
e
s
y
s
tem
,
ad
a
p
tiv
e
im
m
u
n
ity
also
k
n
o
wn
as
ac
q
u
ir
ed
o
r
p
ar
ticu
lar
im
m
u
n
ity
ca
n
i
d
en
tify
a
n
d
d
estro
y
ce
r
tain
f
o
r
eig
n
p
ath
o
g
en
s
an
d
ch
em
icals,
s
u
ch
as
an
tib
o
d
ies.
Un
lik
e
n
atu
r
al
im
m
u
n
ity
,
a
d
ap
tiv
e
i
m
m
u
n
ity
d
ev
elo
p
s
o
v
er
tim
e
b
y
e
x
p
o
s
u
r
e
to
a
n
tig
en
s
,
th
er
ef
o
r
e
p
r
o
d
u
cin
g
a
tailo
r
ed
d
ef
en
s
e
m
ec
h
an
is
m
a
g
ain
s
t
p
ar
ticu
lar
th
r
ea
ts
[
1
7
]
,
[
1
9
]
.
I
t
is
in
ter
esti
n
g
th
at
ac
q
u
ir
ed
im
m
u
n
ity
d
o
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
13
,
No
.
4
,
Dec
em
b
er
20
24
:
40
1
-
4
0
9
404
n
o
t
o
p
er
ate
alo
n
e
b
u
t
r
ath
er
to
g
eth
e
r
with
n
atu
r
al
im
m
u
n
ity
to
ef
f
icien
tly
id
en
tif
y
a
n
d
d
estro
y
f
o
r
ei
g
n
in
v
ad
er
s
,
h
e
n
ce
s
tr
ess
in
g
th
e
c
o
m
p
lex
in
ter
ac
ti
o
n
s
am
o
n
g
v
a
r
io
u
s
p
ar
ts
o
f
t
h
e
im
m
u
n
e
s
y
s
tem
[
1
7
]
.
T
h
e
p
r
in
cip
le
o
f
clo
n
al
s
elec
tio
n
elu
cid
ates
th
e
f
u
n
d
am
e
n
tal
m
ec
h
an
is
m
s
g
o
v
er
n
in
g
th
e
im
m
u
n
e
r
esp
o
n
s
e
to
a
n
tig
en
ic
s
tim
u
li.
I
t
s
u
g
g
ests
th
at
o
n
l
y
ce
lls
ab
l
e
to
id
en
tif
y
th
e
an
tig
en
p
r
o
life
r
ate;
th
o
s
e
u
n
a
b
le
o
f
th
is
id
en
tific
atio
n
a
r
e
k
illed
[
1
7
]
.
T
h
is
p
er
s
p
ec
tiv
e
c
o
v
er
s
m
an
y
im
p
o
r
tan
t p
o
in
ts
[
2
0
]
.
−
L
y
m
p
h
o
cy
tes
n
ewly
g
en
e
r
ated
an
d
b
ea
r
in
g
s
elf
-
r
ea
ctiv
e
r
ec
ep
to
r
s
ar
e
elim
in
ated
f
r
o
m
th
e
im
m
u
n
e
r
esp
o
n
s
e;
n
ewly
g
en
er
ated
ce
l
ls
ar
e
clo
n
es o
f
th
eir
p
ar
en
t c
ells
an
d
u
n
d
er
g
o
a
m
u
tatio
n
p
r
o
ce
s
s
m
ar
k
ed
b
y
h
ig
h
r
ates o
f
s
o
m
atic
h
y
p
er
m
u
tatio
n
.
−
Ma
tu
r
e
ce
lls
p
r
o
life
r
ate
an
d
d
i
f
f
er
en
tiate
u
p
o
n
e
n
co
u
n
ter
in
g
an
tig
en
s
.
I
n
s
p
ir
ed
b
y
th
e
clo
n
al
s
elec
tio
n
p
r
in
cip
le,
th
e
m
eth
o
d
c
o
v
er
ed
in
th
is
b
o
o
k
r
ef
lects
th
e
s
elec
tiv
e
p
r
o
life
r
atio
n
o
f
an
tib
o
d
ies
wit
h
m
ax
im
u
m
af
f
i
n
ity
f
o
r
an
tig
en
s
.
Ou
r
m
eth
o
d
is
b
ased
o
n
th
is
o
n
e
an
d
tr
ies
to
ap
p
r
o
x
im
ate
a
g
iv
en
f
u
n
ctio
n
[
2
0
]
.
I
n
s
p
ir
ed
b
y
im
m
u
n
e
s
y
s
tem
d
y
n
am
ics
[
1
7
]
–
[
2
0
]
,
th
e
f
r
am
ewo
r
k
o
f
th
e
alg
o
r
ith
m
is
s
h
o
w
n
in
Fig
u
r
e
2
s
h
o
win
g
h
o
w
th
e
id
ea
s
o
f
c
lo
n
al
s
elec
tio
n
m
a
y
b
e
u
s
ed
t
o
b
u
ild
an
ef
f
icien
t
f
u
n
ctio
n
a
p
p
r
o
x
im
atio
n
tech
n
i
q
u
e,
th
er
e
f
o
r
e
p
r
o
v
id
in
g
a
s
tr
u
ctu
r
ed
p
r
o
b
lem
-
s
o
l
v
in
g
s
tr
ateg
y
.
Fig
u
r
e
2
.
C
lo
n
al
s
elec
tio
n
p
r
o
ce
s
s
4.
B
I
O
G
E
O
G
RAP
H
Y
-
B
AS
E
D
O
P
T
I
M
I
Z
A
T
I
O
N
I
n
s
p
ir
ed
b
y
b
io
g
eo
g
r
ap
h
ic
in
v
esti
g
atio
n
s
,
Simo
n
[
2
1
]
in
tr
o
d
u
ce
s
th
e
B
B
O
wh
ich
o
f
f
er
s
a
n
o
v
el
ap
p
r
o
ac
h
to
m
ax
im
izin
g
d
i
f
f
er
en
t
s
y
s
tem
s
.
Or
ig
in
ally
f
r
o
m
ec
o
lo
g
y
,
wh
er
e
it
aim
s
to
g
r
asp
s
p
ec
ies
d
is
tr
ib
u
tio
n
in
th
e
b
io
s
p
h
er
e,
B
B
O
ad
d
r
ess
e
s
o
p
tim
izatio
n
is
s
u
es
u
s
in
g
id
ea
s
o
f
m
ig
r
atio
n
an
d
em
i
g
r
atio
n
am
o
n
g
is
lan
d
s
.
Un
d
er
t
h
is
p
ar
ad
ig
m
,
ev
er
y
is
lan
d
s
tan
d
s
f
o
r
a
g
r
o
u
p
o
f
ec
o
s
y
s
tem
s
,
ea
ch
s
p
ec
if
ied
b
y
n
u
m
er
o
u
s
im
p
o
r
ta
n
t c
r
iter
ia
[
2
2
]
.
A
f
u
n
d
a
m
en
tal
id
ea
in
B
B
O
is
th
e
h
ab
itat
s
u
itab
ilit
y
in
d
ex
(
HSI
)
,
wh
ich
g
au
g
es
a
h
ab
itat
’
s
s
p
ec
ies
-
attr
ac
tiv
e
q
u
ality
[
2
1
]
.
Hig
h
HSI
h
ab
itats
ar
e
s
ee
n
as
m
o
r
e
s
u
itab
le
an
d
b
en
ef
icial,
im
p
ly
in
g
a
s
ig
n
if
ican
t
in
clin
atio
n
o
f
o
th
e
r
s
p
ec
ies
to
r
elo
ca
te
th
er
e.
Dif
f
er
e
n
t
s
u
itab
ilit
y
in
d
ex
v
ar
iab
les
(
SIV
)
,
in
clu
d
in
g
s
u
r
f
ac
e
ar
ea
,
tem
p
e
r
atu
r
e
[
2
2
]
,
an
d
p
lan
t
v
a
r
iety
,
h
elp
o
n
e
to
e
v
alu
ate
its
ap
p
ea
l.
Fu
r
th
er
m
o
r
e,
c
o
n
n
ec
te
d
to
a
h
ab
itat
’
s
HSI
is
its
s
p
ec
ie
s
co
u
n
t;
h
ig
h
er
HSI
en
v
ir
o
n
m
en
ts
u
s
u
ally
s
u
p
p
o
r
t
m
o
r
e
s
p
ec
ies.
B
ec
au
s
e
o
f
s
atu
r
atio
n
,
wh
ich
co
n
tr
o
ls
th
e
m
ig
r
ato
r
y
f
lo
w,
h
ab
itats
with
h
ig
h
HSI
also
e
x
h
ib
it g
r
ea
ter
em
ig
r
atio
n
r
ates
b
u
t
lo
wer
im
m
ig
r
atio
n
r
ates
[
2
1
]
,
[
2
2
]
as m
e
n
tio
n
in
T
ab
le
2
.
I
n
clu
d
in
g
cr
iter
ia
o
f
h
ab
itat
ap
p
r
o
p
r
iaten
ess
,
s
p
ec
ies
r
ich
n
ess
,
m
ig
r
ato
r
y
p
atter
n
s
,
an
d
ec
o
lo
g
ical
b
alan
ce
,
T
a
b
le
2
o
f
f
e
r
s
a
s
u
c
cin
ct
s
u
m
m
ar
y
o
f
th
e
m
ai
n
t
r
aits
ch
ar
ac
ter
izin
g
ea
c
h
h
a
b
i
tat
u
n
d
er
th
e
B
B
O
f
r
am
ewo
r
k
.
T
h
o
u
g
h
m
u
tatio
n
an
d
elitis
m
ar
e
n
o
t
alwa
y
s
n
ec
ess
ar
y
,
t
h
e
B
B
O
m
eth
o
d
co
n
s
is
ts
o
f
th
r
e
e
p
r
im
ar
y
p
h
ases
:
m
ig
r
atio
n
,
m
u
tatio
n
,
an
d
elitis
m
[
2
1
]
–
[
2
4
]
.
Hab
itat
s
elec
tio
n
d
u
r
in
g
m
i
g
r
atio
n
is
b
ased
o
n
p
r
ed
ef
in
e
d
p
r
o
b
ab
ilit
y
;
s
u
itab
ilit
y
in
d
ex
v
ar
ia
b
les
(
SIV
s
)
a
r
e
tr
ad
e
d
ac
r
o
s
s
ch
o
s
en
h
a
b
itats
.
T
h
is
iter
ativ
e
p
r
o
ce
s
s
g
o
es
o
n
u
n
til
co
n
v
er
g
en
ce
is
attain
ed
,
th
er
e
b
y
im
p
r
o
v
in
g
th
e
s
y
s
tem
in
lin
e
with
b
io
g
eo
g
r
ap
h
ic
co
n
ce
p
ts
[
2
3
]
.
Star
tin
g
with
p
a
r
am
eter
s
ettin
g
an
d
th
e
b
u
ild
in
g
o
f
a
s
o
lu
tio
n
p
o
p
u
latio
n
,
th
e
o
p
tim
izatio
n
p
r
o
ce
s
s
[
2
1
]
–
[
2
3
]
.
T
h
e
f
ea
s
ib
ilit
y
o
f
an
y
s
o
lu
tio
n
is
d
eter
m
in
ed
b
y
its
HSI
,
wh
ic
h
s
o
r
ts
t
h
e
p
o
p
u
latio
n
.
Nex
t
co
m
p
u
ted
a
r
e
im
m
ig
r
atio
n
,
e
m
ig
r
atio
n
,
an
d
m
u
tatio
n
r
ates;
elite
s
o
lu
tio
n
s
ar
e
th
en
m
ain
tain
ed
.
T
h
e
m
u
tatio
n
In
i
t
i
a
l
i
z
a
t
i
o
n
o
r
F
i
r
st
st
e
p
:
D
e
f
i
n
e
p
o
p
u
l
a
t
i
o
n
o
f
N
a
n
t
i
b
o
d
i
e
s
A
b
={
x
1
,
x
2
,
.
.
.
,
x
N
}
(
w
h
e
r
e
x
i
r
e
p
r
e
se
n
t
s t
h
e
so
l
u
t
i
o
n
s
t
r
u
c
t
u
r
e
)
.
A
r
b
i
t
r
a
r
l
y
i
n
i
t
i
a
l
i
z
e
Ab
p
o
p
u
l
a
t
i
o
n
.
It
e
r
a
t
i
v
e
st
e
p
:
Ev
a
l
u
a
t
e
a
f
i
t
n
e
ss f
u
n
c
t
i
o
n
f
o
r
e
a
c
h
A
n
t
i
b
o
d
y
i
n
t
h
e
Ab
p
o
p
u
l
a
t
i
o
n
.
S
o
r
t
Ab
p
o
p
u
l
a
t
i
o
n
b
a
se
d
o
n
f
i
t
n
e
s
s.
S
e
l
e
c
t
n
f
i
r
st
a
n
t
i
b
o
d
i
e
s
(
w
h
e
r
e
n
<N
)
t
o
f
o
r
m
a
n
e
w
p
o
p
u
l
a
t
i
o
n
,
A
b
n
,
w
h
i
c
h
h
a
v
e
t
h
e
h
i
g
h
e
st
f
i
t
n
e
ss
v
a
l
u
e
s.
F
o
r
e
a
c
h
m
e
m
b
e
r
i
n
t
h
e
n
e
w
p
o
p
u
l
a
t
i
o
n
A
b
n
:
C
l
o
n
e
i
t
.
A
p
p
l
y
h
y
p
e
r
mu
t
a
t
i
o
n
.
E
v
a
l
u
a
t
e
a
f
i
t
n
e
ss
f
u
n
c
t
i
o
n
.
S
o
r
t
p
o
p
u
l
a
t
i
o
n
A
b
n
b
a
s
e
d
o
n
f
i
t
n
e
ss.
R
e
p
l
a
c
e
m
e
mb
e
r
s wi
t
h
l
o
w
f
i
t
n
e
ss
i
n
o
r
i
g
i
n
a
l
p
o
p
u
l
a
t
i
o
n
Ab
w
i
t
h
N
−n
i
n
d
i
v
i
d
u
a
l
s fr
o
m
p
o
p
u
l
a
t
i
o
n
A
b
n
.
R
e
p
e
a
t
t
h
i
s
i
t
e
r
a
t
i
v
e
p
r
o
c
e
s
s
u
n
t
i
l
a
max
i
mu
m
n
u
m
b
e
r
o
f
i
t
e
r
a
t
i
o
n
s
o
r
e
r
r
o
r
l
e
v
e
l
d
e
si
r
e
d
i
s re
a
c
h
e
d
.
Fi
n
a
l
st
e
p
:
Th
e
b
e
st
A
n
t
i
b
o
d
y
f
r
o
m
t
h
e
p
o
p
u
l
a
t
i
o
n
Ab
,
b
a
se
d
o
n
f
i
t
n
e
s
s,
i
s
d
e
t
e
r
mi
n
e
d
a
s t
h
e
f
i
n
a
l
s
o
l
u
t
i
o
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
I
n
teg
r
a
tin
g
a
r
tifi
cia
l imm
u
n
e
s
ystem
s
a
n
d
mu
lti
-
la
ye
r
p
ercep
tr
o
n
-
b
io
g
e
o
g
r
a
p
h
y
-
b
a
s
ed
…
(
A
mel
S
era
t
)
405
o
p
er
ato
r
p
r
o
v
id
es
v
ar
iety
;
th
e
m
ig
r
atio
n
o
p
er
ato
r
m
o
v
es
s
o
lu
tio
n
s
ac
r
o
s
s
h
a
b
itats
.
B
o
u
n
d
ar
y
r
estrictio
n
s
g
u
ar
an
tee
t
h
at
an
s
wer
s
r
em
a
in
in
s
id
e
s
p
ec
if
ied
b
o
u
n
d
ar
ie
s
.
T
h
e
p
o
p
u
latio
n
is
r
e
v
iewe
d
,
o
r
g
an
ized
,
an
d
m
ay
b
e
s
tr
en
g
th
en
ed
.
T
h
is
iter
ativ
e
m
eth
o
d
k
ee
p
s
o
n
u
n
til
t
h
e
d
esire
d
s
to
p
p
in
g
cr
iter
ia
ar
e
s
atis
f
ied
,
th
er
ef
o
r
e
p
r
o
d
u
cin
g
th
e
b
est
an
s
wer
.
T
h
is
m
eth
o
d
g
u
ar
a
n
tees
co
m
p
lete
in
v
esti
g
atio
n
o
f
th
e
s
o
lu
tio
n
s
p
ac
e
an
d
co
n
v
er
g
en
ce
to
war
d
b
est r
esu
l
ts
[
2
1
]
–
[
2
4
]
.
T
h
e
B
B
O
ap
p
r
o
a
ch
is
s
h
o
wn
in
Fig
u
r
e
3
.
T
ab
le
2
.
B
B
O
k
ey
ch
ar
ac
ter
is
t
ics
H
a
b
i
t
a
t
C
h
a
r
a
c
t
e
r
i
st
i
c
D
e
scri
p
t
i
o
n
H
a
b
i
t
a
t
s
u
i
t
a
b
i
l
i
t
y
i
n
d
e
x
(
H
S
I
)
R
e
f
l
e
c
t
s
t
h
e
o
v
e
r
a
l
l
c
o
mf
o
r
t
a
n
d
a
t
t
r
a
c
t
i
v
e
n
e
ss
o
f
t
h
e
h
a
b
i
t
a
t
t
o
o
t
h
e
r
sp
e
c
i
e
s.
H
i
g
h
H
S
I
i
n
d
i
c
a
t
e
s
c
o
mf
o
r
t
,
a
d
v
a
n
t
a
g
e
,
a
n
d
h
i
g
h
h
a
b
i
t
a
b
i
l
i
t
y
,
w
h
i
l
e
l
o
w
H
S
I
si
g
n
i
f
i
e
s w
e
a
k
e
r
a
t
t
r
a
c
t
i
o
n
a
n
d
d
i
m
i
n
i
s
h
e
d
s
u
i
t
a
b
i
l
i
t
y
.
S
u
i
t
a
b
i
l
i
t
y
i
n
d
e
x
v
a
r
i
a
b
l
e
(SIV)
P
a
r
a
me
t
e
r
s
i
n
f
l
u
e
n
c
i
n
g
h
a
b
i
t
a
t
c
o
mf
o
r
t
,
i
n
c
l
u
d
i
n
g
v
e
g
e
t
a
t
i
o
n
d
i
v
e
r
si
t
y
,
s
u
r
f
a
c
e
a
r
e
a
,
t
e
m
p
e
r
a
t
u
r
e
,
a
n
d
o
t
h
e
r
e
c
o
l
o
g
i
c
a
l
a
t
t
r
i
b
u
t
e
s c
r
u
c
i
a
l
f
o
r
sp
e
c
i
e
s
s
u
r
v
i
v
a
l
a
n
d
p
r
o
l
i
f
e
r
a
t
i
o
n
.
N
u
mb
e
r
o
f
sp
e
c
i
e
s
I
n
d
i
c
a
t
e
s
t
h
e
n
u
m
b
e
r
o
f
a
n
i
mal
s
i
n
h
a
b
i
t
i
n
g
t
h
e
h
a
b
i
t
a
t
.
H
a
b
i
t
a
t
s
w
i
t
h
h
i
g
h
H
S
I
t
y
p
i
c
a
l
l
y
a
c
c
o
mm
o
d
a
t
e
a
g
r
e
a
t
e
r
d
i
v
e
r
s
i
t
y
o
f
s
p
e
c
i
e
s,
w
i
t
h
t
h
e
n
u
m
b
e
r
o
f
s
p
e
c
i
e
s
d
i
r
e
c
t
l
y
p
r
o
p
o
r
t
i
o
n
a
l
t
o
t
h
e
h
a
b
i
t
a
t
’
s
o
v
e
r
a
l
l
su
i
t
a
b
i
l
i
t
y
.
Emi
g
r
a
t
i
o
n
r
a
t
e
R
e
f
l
e
c
t
s
t
h
e
p
r
o
p
e
n
s
i
t
y
f
o
r
s
p
e
c
i
e
s
d
i
sp
e
r
sal
f
r
o
m
o
n
e
h
a
b
i
t
a
t
t
o
o
t
h
e
r
h
a
b
i
t
a
t
s.
H
a
b
i
t
a
t
s
w
i
t
h
h
i
g
h
H
S
I
v
a
l
u
e
s t
e
n
d
t
o
e
x
h
i
b
i
t
e
l
e
v
a
t
e
d
e
mi
g
r
a
t
i
o
n
r
a
t
e
s,
i
n
d
i
c
a
t
i
n
g
a
g
r
e
a
t
e
r
t
e
n
d
e
n
c
y
f
o
r
sp
e
c
i
e
s
mi
g
r
a
t
i
o
n
.
I
mm
i
g
r
a
t
i
o
n
r
a
t
e
I
n
d
i
c
a
t
e
s
t
h
e
r
a
t
e
a
t
w
h
i
c
h
n
e
w
sp
e
c
i
e
s
c
o
l
o
n
i
z
e
t
h
e
h
a
b
i
t
a
t
.
H
a
b
i
t
a
t
s
w
i
t
h
h
i
g
h
H
S
I
v
a
l
u
e
s
g
e
n
e
r
a
l
l
y
h
a
v
e
l
o
w
e
r
i
mm
i
g
r
a
t
i
o
n
r
a
t
e
s
d
u
e
t
o
s
a
t
u
r
a
t
i
o
n
a
n
d
r
e
d
u
c
e
d
su
i
t
a
b
i
l
i
t
y
f
o
r
n
e
w
s
p
e
c
i
e
s c
o
l
o
n
i
z
a
t
i
o
n
.
La
r
g
e
st
n
u
m
b
e
r
o
f
s
p
e
c
i
e
s
En
f
o
r
c
e
s
a
t
h
r
e
s
h
o
l
d
o
n
t
h
e
ma
x
i
m
u
m
n
u
mb
e
r
o
f
s
p
e
c
i
e
s
t
h
e
h
a
b
i
t
a
t
c
a
n
su
p
p
o
r
t
,
r
e
g
u
l
a
t
i
n
g
m
i
g
r
a
t
i
o
n
f
l
o
w
s
a
n
d
m
a
i
n
t
a
i
n
i
n
g
e
c
o
l
o
g
i
c
a
l
b
a
l
a
n
c
e
w
i
t
h
i
n
a
n
d
a
c
r
o
ss
h
a
b
i
t
a
t
s.
Fig
u
r
e
3
.
B
B
O
p
r
o
ce
s
s
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Op
er
atin
g
in
s
id
e
th
e
MA
T
L
AB
7
en
v
ir
o
n
m
en
t,
th
e
s
im
u
lati
o
n
ca
r
r
ied
o
u
t
o
n
th
e
PUMA5
6
0
r
o
b
o
tic
ar
m
u
s
ed
a
c
o
m
p
u
tatio
n
al
c
o
n
f
ig
u
r
atio
n
c
o
n
tain
in
g
a
Pen
tiu
m
4
p
r
o
ce
s
s
o
r
with
a
clo
c
k
s
p
ee
d
o
f
1
.
8
GHz
b
ac
k
ed
b
y
a
4
0
GB
h
ar
d
d
is
k
d
r
iv
e
(
HDD)
a
n
d
1
GB
o
f
R
AM
.
Ap
ar
t
f
r
o
m
d
elin
ea
tin
g
th
e
h
ar
d
war
e
an
d
s
o
f
twar
e
s
etu
p
u
s
ed
f
o
r
th
e
s
im
u
latio
n
,
it
is
ess
en
tia
l
to
u
n
d
er
lin
e
th
e
im
p
o
r
tan
ce
o
f
th
e
f
in
d
in
g
s
ac
q
u
ir
e
d
u
s
in
g
th
e
W
av
elet
Netwo
r
k
t
ec
h
n
iq
u
e
in
2
0
0
6
[
2
5
]
as
s
ee
n
in
T
ab
le
3
.
Usi
n
g
wav
elet
tr
an
s
f
o
r
m
s
f
o
r
d
ata
an
aly
s
is
an
d
m
o
d
elin
g
,
t
h
is
ap
p
r
o
ac
h
g
a
v
e
an
in
s
ig
h
tf
u
l
e
x
am
in
atio
n
o
f
PUMA5
6
0
ar
m
p
er
f
o
r
m
an
ce
an
d
ca
p
ab
ilit
ies.
B
y
m
ea
n
s
o
f
a
b
etter
k
n
o
wled
g
e
o
f
r
o
b
o
tic
ar
m
d
y
n
am
ics,
an
aly
s
is
o
f
th
ese
r
esu
lts
h
elp
s
to
p
r
o
g
r
ess
r
o
b
o
tics
r
esear
ch
an
d
d
ev
elo
p
m
en
t.
F
i
r
st
s
t
e
p
:
S
e
t
t
h
e
set
t
i
n
g
s a
n
d
r
a
n
d
o
m
l
y
st
a
r
t
t
h
e
p
o
p
u
l
a
t
i
o
n
.
S
t
a
r
t
i
n
g
p
o
p
u
l
a
t
i
o
n
P
w
i
t
h
r
a
n
d
o
ml
y
p
r
o
d
u
c
e
d
a
n
sw
e
r
s
I
t
e
r
a
t
i
o
n
c
o
u
n
t
e
r
i
t
e
r
=
0
S
e
c
o
n
d
s
t
e
p
:
a
sses
s e
v
e
r
y
e
n
v
i
r
o
n
me
n
t
a
n
d
r
a
n
k
t
h
e
p
o
p
u
l
a
t
i
o
n
u
s
i
n
g
H
S
I
s f
r
o
m
b
e
s
t
t
o
w
o
r
st
.
C
o
m
p
u
t
e
t
h
e
H
S
I
o
f
t
h
e
h
a
b
i
t
a
t
f
o
r
e
v
e
r
y
s
o
l
u
t
i
o
n
i
n
p
o
p
u
l
a
t
i
o
n
P
:
S
o
r
t
p
o
p
u
l
a
t
i
o
n
P
i
n
d
e
c
r
e
a
si
n
g
H
S
I
seq
u
e
n
c
e
.
Th
i
r
d
s
t
e
p
:
D
e
t
e
r
mi
n
e
t
h
e
r
a
t
e
s
o
f
i
m
mi
g
r
a
t
i
o
n
,
e
mi
g
r
a
t
i
o
n
,
a
n
d
m
u
t
a
t
i
o
n
a
n
d
r
e
t
a
i
n
t
h
e
e
l
i
t
i
s
t
s.
C
a
l
c
u
l
a
t
e
t
h
e
i
mm
i
g
r
a
t
i
o
n
r
a
t
e
λ
.
D
e
t
e
r
mi
n
e
t
h
e
e
m
i
g
r
a
t
i
o
n
r
a
t
e
μ
h
e
r
e
.
G
e
t
m
u
t
a
t
i
o
n
r
a
t
e
η
v
i
a
c
o
m
p
u
t
a
t
i
o
n
.
Li
s
t
e
l
i
t
i
st
i
d
e
a
s
w
o
r
t
h
k
e
e
p
i
n
g
.
F
o
u
r
t
h
st
e
p
:
a
p
p
l
y
t
h
e
m
i
g
r
a
t
i
o
n
o
p
e
r
a
t
o
r
.
C
h
o
o
se
a
h
a
b
i
t
a
t
f
r
o
m
w
h
i
c
h
t
o
e
m
i
g
r
a
t
e
b
a
se
d
o
n
e
m
i
g
r
a
t
i
o
n
r
a
t
e
μ
f
o
r
e
v
e
r
y
h
a
b
i
t
a
t
i
n
p
o
p
u
l
a
t
i
o
n
P
.
M
o
v
e
o
p
t
i
o
n
s
d
e
p
e
n
d
e
n
t
o
n
e
mi
g
r
a
t
i
o
n
a
n
d
i
mm
i
g
r
a
t
i
o
n
r
a
t
e
s
b
e
t
w
e
e
n
h
a
b
i
t
a
t
s
.
A
p
p
l
y
i
n
g
t
h
e
m
u
t
a
t
i
o
n
o
p
e
r
a
t
o
r
c
o
me
s i
n
f
i
f
t
h
s
t
a
g
e
.
E
v
e
r
y
s
o
l
u
t
i
o
n
i
n
p
o
p
u
l
a
t
i
o
n
P
s
h
o
u
l
d
u
s
e
m
u
t
a
t
i
o
n
d
e
p
e
n
d
i
n
g
o
n
mu
t
a
t
i
o
n
r
a
t
e
η.
S
e
t
t
h
e
l
i
m
i
t
a
t
i
o
n
s
o
f
e
v
e
r
y
n
e
w
l
y
p
r
o
p
o
s
e
d
s
o
l
u
t
i
o
n
i
n
st
e
p
si
x
.
M
a
k
e
s
u
r
e
e
v
e
r
y
a
n
sw
e
r
i
n
p
o
p
u
l
a
t
i
o
n
P
s
t
a
y
s w
i
t
h
i
n
g
i
v
e
n
l
i
mi
t
s.
C
a
l
c
u
l
a
t
e
t
h
e
H
S
I
f
o
r
e
v
e
r
y
e
n
v
i
r
o
n
m
e
n
t
i
n
s
t
e
p
s
e
v
e
n
t
h
e
n
a
r
r
a
n
g
e
t
h
e
p
o
p
u
l
a
t
i
o
n
f
r
o
m
b
e
st
t
o
w
o
r
st
.
F
i
n
d
t
h
e
h
a
b
i
t
a
t
’
s HS
I
f
o
r
e
v
e
r
y
so
l
u
t
i
o
n
i
n
p
o
p
u
l
a
t
i
o
n
P
:
S
o
r
t
p
o
p
u
l
a
t
i
o
n
P
i
n
d
e
c
r
e
a
si
n
g
H
S
I
seq
u
e
n
c
e
.
Ei
g
h
t
h
st
e
p
:
r
e
p
l
a
c
e
s
o
me
p
o
o
r
e
st
h
a
b
i
t
a
t
s w
i
t
h
e
l
i
t
i
s
t
s.
R
e
p
l
a
c
e
s
o
m
e
o
f
t
h
e
f
a
i
l
i
n
g
h
a
b
i
t
a
t
s w
i
t
h
e
l
i
t
i
s
t
f
i
x
e
s.
Th
e
n
i
n
t
h
st
e
p
i
s
o
n
c
e
a
g
a
i
n
p
o
p
u
l
a
t
i
o
n
s
o
r
t
i
n
g
f
r
o
m
b
e
st
t
o
w
o
r
st
.
S
o
r
t
p
o
p
u
l
a
t
i
o
n
P
d
e
c
r
e
a
s
i
n
g
l
y
i
n
t
e
r
ms
o
f
H
S
I
.
Th
e
t
e
n
t
h
st
e
p
i
s
d
e
t
e
r
m
i
n
i
n
g
i
f
t
h
e
h
a
l
t
i
n
g
r
e
q
u
i
r
e
m
e
n
t
i
s s
a
t
i
sf
i
e
d
.
G
o
t
o
S
t
e
p
1
1
i
f
h
a
l
t
i
n
g
c
r
i
t
e
r
i
a
a
r
e
sat
i
sf
i
e
d
;
o
t
h
e
r
w
i
se,
g
o
b
a
c
k
t
o
S
t
e
p
3
.
S
t
e
p
1
1
:
R
e
t
u
r
n
t
o
S
t
e
p
3
e
l
se
o
u
t
p
u
t
t
h
e
b
e
st
s
o
l
u
t
i
o
n
i
f
t
h
e
s
t
o
p
p
i
n
g
c
r
i
t
e
r
i
a
i
s
sa
t
i
sf
i
e
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
13
,
No
.
4
,
Dec
em
b
er
20
24
:
40
1
-
4
0
9
406
T
ab
le
3
s
h
o
ws,
wh
e
n
u
s
in
g
a
wav
elet
n
etwo
r
k
[
2
5
]
,
th
e
m
e
a
n
s
q
u
ar
e
e
r
r
o
r
s
f
o
r
e
v
er
y
jo
in
t
an
g
le
(Q
1
th
r
o
u
g
h
Q
6
)
o
f
a
PUMA5
6
0
r
o
b
o
tic
ar
m
.
R
ep
o
r
ted
in
u
n
its
m
u
ltip
lied
b
y
1
0
-
3
,
th
ese
m
is
tak
es
s
h
o
w
th
e
ac
cu
r
ac
y
o
f
an
g
le
f
o
r
ec
asts
u
s
in
g
th
is
m
eth
o
d
.
Fo
r
Q
3
at
0
.
0
2
9
*
1
0
-
3
,
f
o
r
e
x
am
p
le,
t
h
e
m
in
i
m
al
er
r
o
r
in
d
icate
s
s
tr
o
n
g
ac
cu
r
ac
y
in
esti
m
atin
g
th
is
s
p
ec
if
ic
jo
in
t
an
g
le.
An
g
les
Q
1
,
Q
4
,
an
d
Q
5
s
h
o
w
lo
wer
er
r
o
r
s
(
0
.
2
7
6
*
1
0
-
3
,
0
.
2
5
9
*
1
0
-
3
,
an
d
0
.
1
9
8
*
1
0
-
3
co
r
r
esp
o
n
d
i
n
g
ly
)
,
th
er
ef
o
r
e
h
ig
h
lig
h
tin
g
lo
ca
tio
n
s
wh
er
e
th
e
w
av
elet
n
etwo
r
k
[
2
2
]
m
o
d
el
m
ay
n
ee
d
im
p
r
o
v
em
en
t
o
r
m
o
d
if
icatio
n
to
in
cr
ea
s
e
its
f
o
r
ec
ast ac
cu
r
ac
y
.
T
ab
le
3
.
Me
an
s
q
u
ar
e
er
r
o
r
wi
th
wav
elet
n
etwo
r
k
s
A
n
g
l
e
s
Er
r
o
r
(
*
1
0
-
3
)
Q
1
0
.
2
7
6
Q
2
0
.
1
4
4
Q
3
0
.
0
2
9
Q
4
0
.
2
5
9
Q
5
0
.
1
9
8
Q
6
0
.
1
5
1
T
a
b
l
e
4
t
h
e
n
d
e
t
a
i
l
s
t
h
e
p
a
r
a
m
e
t
e
r
s
u
s
e
d
i
n
t
h
e
A
I
S
m
e
t
h
o
d
,
m
o
r
e
e
s
p
e
c
i
a
l
l
y
,
t
h
e
c
l
o
n
a
l
s
e
l
e
ct
i
o
n
t
ec
h
n
i
q
u
e
.
T
h
e
t
a
b
le
l
i
s
t
s
a
f
a
c
t
o
r
β
s
e
t
a
t
0
.
1
,
m
u
t
a
t
i
o
n
p
r
o
b
a
b
i
l
i
t
y
(
0
.
0
0
1
)
,
a
n
d
4
0
0
g
e
n
e
r
a
t
i
o
n
s
.
A
i
m
i
n
g
t
o
e
f
f
e
c
ti
v
e
l
y
d
e
v
e
l
o
p
t
h
e
s
o
l
u
t
i
o
n
s
a
c
r
o
s
s
c
o
n
s
ec
u
t
i
v
e
g
e
n
e
r
a
t
i
o
n
s
w
h
i
l
e
c
o
n
tr
o
l
l
i
n
g
t
h
e
b
a
l
a
n
c
e
b
e
t
w
e
e
n
e
x
p
l
o
r
at
i
o
n
(
b
y
m
u
t
ati
o
n
)
a
n
d
e
x
p
l
o
i
t
at
i
o
n
(
v
i
a
s
el
e
ct
i
o
n
)
,
t
h
es
e
c
r
it
e
r
i
a
d
i
r
e
c
t
t
h
e
ev
o
l
u
t
i
o
n
a
r
y
p
r
o
c
e
s
s
i
n
t
h
e
A
I
S
.
T
ab
le
4
.
AI
S p
a
r
am
eter
s
P
a
r
a
me
t
e
r
V
a
l
u
e
s
G
e
n
e
r
a
t
i
o
n
4
0
0
M
u
t
a
t
i
o
n
p
r
o
b
a
b
i
l
i
t
y
0
.
0
0
1
Β
0
.
1
T
ab
le
5
s
h
o
ws
th
e
clo
n
al
s
elec
tio
n
alg
o
r
ith
m
’
s
o
u
tp
u
ts
;
th
eir
u
n
its
m
u
ltip
lied
b
y
1
0
-
4
r
ev
e
al
th
at
th
e
m
ea
n
s
q
u
ar
e
er
r
o
r
s
f
o
r
th
e
jo
in
t
an
g
les
ar
e
m
u
ch
s
m
aller
t
h
an
th
o
s
e
p
r
o
d
u
ce
d
u
s
in
g
th
e
wav
elet
n
et
wo
r
k
.
E
s
p
ec
ially
,
th
e
m
is
tak
e
f
o
r
Q
6
is
lo
wer
ed
to
o
n
ly
0
.
0
0
2
*
1
0
-
4
,
s
h
o
win
g
ex
tr
ao
r
d
i
n
ar
y
d
eg
r
ee
o
f
ac
cu
r
ac
y
.
L
ik
ewise,
at
0
.
0
0
9
*
1
0
-
4
,
Q
3
’
s
er
r
o
r
is
s
h
o
ck
in
g
l
y
lo
w,
u
n
d
er
s
co
r
in
g
ev
e
n
m
o
r
e
clo
n
al
s
elec
tio
n
m
eth
o
d
’
s
ef
f
icien
cy
in
o
b
tain
in
g
g
r
ea
t
p
r
ec
is
io
n
.
T
ab
le
5
.
Me
an
s
q
u
ar
e
er
r
o
r
wi
th
clo
n
al
s
elec
tio
n
A
n
g
l
e
s
Er
r
o
r
(
*
1
0
-
4
)
Q
1
0
.
0
5
Q
2
0
.
4
Q
3
0
.
0
0
9
Q
4
0
.
0
2
Q
5
0
.
0
4
Q
6
0
.
0
0
2
T
h
ese
co
n
tr
asts
b
etwe
en
th
e
two
ap
p
r
o
ac
h
es
s
h
o
w
th
e
d
if
f
er
en
t
b
en
ef
its
o
f
u
s
in
g
clo
n
a
l
s
elec
tio
n
with
in
AI
S
f
o
r
th
is
k
in
d
o
f
r
o
b
o
tic
co
n
t
r
o
l
ch
allen
g
e.
T
h
e
s
ig
n
if
ican
t
d
ec
r
ea
s
e
in
er
r
o
r
r
ates
in
d
icate
s
th
at
clo
n
al
s
elec
tio
n
is
a
b
le
to
g
en
er
ate
m
o
r
e
ex
ac
t
jo
in
t
an
g
le
p
r
ed
ictio
n
s
,
p
r
esu
m
ab
ly
b
ec
a
u
s
e
o
f
its
m
ec
h
an
is
m
s
th
at
r
ep
licate
n
atu
r
al
ev
o
lu
tio
n
ar
y
p
r
o
ce
s
s
es,
allo
win
g
it
to
f
in
ely
tu
n
e
th
e
s
o
lu
tio
n
s
to
a
h
ig
h
er
d
e
g
r
ee
th
an
th
e
wav
elet
n
etwo
r
k
m
eth
o
d
[
2
5
]
.
T
h
is
s
tu
d
y
s
h
o
ws
th
at
wh
ile
th
e
wav
elet
n
etwo
r
k
p
r
esen
ts
a
s
tr
o
n
g
ap
p
r
o
ac
h
f
o
r
p
r
e
d
ictio
n
,
in
s
itu
atio
n
s
wh
er
e
ac
cu
r
ac
y
is
cr
u
cial
th
e
clo
n
al
s
elec
tio
n
alg
o
r
ith
m
with
in
AI
S
f
r
am
ewo
r
k
s
m
ig
h
t
b
e
a
b
etter
o
p
tio
n
.
Mo
r
eo
v
er
,
th
e
in
v
esti
g
atio
n
o
f
f
u
r
th
er
o
p
tim
izatio
n
o
f
th
ese
p
a
r
am
eter
s
an
d
th
e
in
c
o
r
p
o
r
ati
o
n
o
f
e
x
tr
a
d
ata
o
r
en
h
an
ce
d
m
o
d
elin
g
ap
p
r
o
ac
h
es
m
ig
h
t
p
e
r
h
ap
s
l
ea
d
to
ev
en
less
m
is
tak
es
a
n
d
m
o
r
e
ef
f
icien
t
p
er
f
o
r
m
an
ce
in
r
o
b
o
tic
o
p
er
ati
o
n
s
.
T
o
esti
m
ate
th
e
jo
in
t a
n
g
les o
f
a
r
o
b
o
tic
ar
m
,
th
e
B
B
O
t
ec
h
n
iq
u
e
was u
s
ed
to
m
o
d
if
y
th
e
weig
h
ts
o
f
th
e
ML
P n
eu
r
al
n
etwo
r
k
.
T
ab
le
6
p
r
o
v
id
es p
a
r
ticu
lar
v
al
u
es o
f
B
B
O.
T
h
e
u
s
ed
p
ar
am
eter
s
ar
e
as
f
o
llo
ws:
5
0
0
g
en
e
r
atio
n
s
s
et,
0
.
0
5
m
u
tatio
n
p
r
o
b
ab
ilit
y
,
1
8
h
id
d
e
n
n
eu
r
o
n
s
,
an
d
o
n
e
h
id
d
e
n
u
n
it.
T
h
ese
v
alu
es
wer
e
s
elec
ted
with
th
e
in
te
n
tio
n
o
f
m
ax
im
iz
in
g
th
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
n
e
u
r
al
n
etwo
r
k
u
s
in
g
b
i
o
g
eo
g
r
ap
h
ical
-
in
s
p
ir
e
d
ev
o
lu
tio
n
ar
y
m
eth
o
d
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
I
n
teg
r
a
tin
g
a
r
tifi
cia
l imm
u
n
e
s
ystem
s
a
n
d
mu
lti
-
la
ye
r
p
ercep
tr
o
n
-
b
io
g
e
o
g
r
a
p
h
y
-
b
a
s
ed
…
(
A
mel
S
era
t
)
407
T
ab
le
6
.
ML
P
-
B
B
O
p
ar
am
eter
s
P
a
r
a
me
t
e
r
V
a
l
u
e
s
G
e
n
e
r
a
t
i
o
n
5
0
0
M
u
t
a
t
i
o
n
P
r
o
b
a
b
i
l
i
t
y
0
.
0
5
H
i
d
d
e
n
N
e
u
r
o
n
s
18
H
i
d
d
e
n
U
n
i
t
1
T
ab
le
7
s
h
o
ws
in
u
n
its
m
u
lt
ip
lied
b
y
1
0
-
4
th
e
m
ea
n
s
q
u
ar
e
er
r
o
r
s
(
MSE
)
f
o
r
ev
er
y
j
o
in
t
an
g
le
(Q
1
th
r
o
u
g
h
Q
6
)
r
esu
ltin
g
f
r
o
m
th
e
ML
P
-
B
B
O
im
p
lem
en
ta
tio
n
.
E
s
p
ec
ially
,
t
h
e
er
r
o
r
lev
els
v
ar
y
am
o
n
g
th
e
m
an
y
j
o
in
t
a
n
g
les;
Q
4
s
h
o
ws
th
e
lar
g
est
e
r
r
o
r
at
0
.
3
4
*
1
0
-
4
,
th
er
eb
y
s
u
g
g
esti
n
g
less
ac
cu
r
ac
y
in
th
is
s
p
ec
if
ic
jo
in
t
’
s
esti
m
ate.
On
th
e
o
th
er
h
an
d
,
Q
5
an
d
Q
6
ex
h
ib
it
r
ath
er
lo
w
er
r
o
r
s
(
0
.
0
2
1
*
1
0
-
4
an
d
0
.
0
2
1
8
*
1
0
-
4
,
r
esp
ec
tiv
ely
)
,
th
er
e
b
y
s
tr
ess
in
g
th
e
ef
f
icien
c
y
o
f
th
e
B
B
O
m
eth
o
d
in
e
x
ac
tly
d
eter
m
in
in
g
t
h
ese
an
g
les.
T
ab
le
7
.
Me
an
s
q
u
ar
e
er
r
o
r
wi
th
ML
P
-
BBO
A
n
g
l
e
s
Er
r
o
r
(
*
1
0
-
4
)
Q
1
0
.
1
1
Q
2
0
.
0
6
Q
3
0
.
0
7
8
Q
4
0
.
3
4
Q
5
0
.
0
2
1
Q
6
0
.
0
2
1
8
W
ith
an
MSE
u
s
u
ally
lo
w,
t
h
e
ML
P
-
B
B
O
tech
n
iq
u
e
s
h
o
ws
g
o
o
d
p
e
r
f
o
r
m
an
ce
i
n
ca
lc
u
latin
g
th
e
jo
in
t
an
g
les.
Ne
v
er
th
eless
,
it
is
clea
r
f
r
o
m
t
h
e
f
in
d
in
g
s
o
b
tain
ed
u
tili
zin
g
th
e
AI
S
ap
p
r
o
ac
h
u
s
in
g
clo
n
al
s
elec
tio
n
th
at
th
e
AI
S
tech
n
i
q
u
e
p
r
o
d
u
ce
s
r
ed
u
ce
d
MSE
g
en
er
ally
.
T
h
is
im
p
lies
th
at
th
e
AI
S
m
eth
o
d
with
clo
n
al
s
elec
t
io
n
s
ee
m
s
to
b
e
m
o
r
e
ef
f
icien
t
ev
e
n
th
o
u
g
h
ML
P
-
B
B
O
i
s
a
s
tr
o
n
g
ap
p
r
o
ac
h
f
o
r
weig
h
t
o
p
tim
izatio
n
in
n
eu
r
al
n
etwo
r
k
s
an
d
p
r
o
v
id
es a
s
ig
n
if
ica
n
t in
cr
ea
s
e
in
an
g
le
esti
m
atio
n
.
T
h
e
im
p
r
o
v
e
d
ef
f
ec
tiv
en
ess
o
f
th
e
AI
S
tech
n
o
lo
g
y
m
ay
b
e
a
s
cr
ib
ed
to
its
s
o
p
h
is
ticated
ev
o
lu
tio
n
ar
y
s
tr
ateg
y
,
wh
ich
r
ep
lic
ate
s
n
atu
r
al
im
m
u
n
e
r
esp
o
n
s
es.
T
h
is
ap
p
r
o
ac
h
h
el
p
s
to
p
r
o
v
i
d
e
a
s
o
p
h
is
ticated
o
p
tim
izatio
n
p
r
o
ce
d
u
r
e,
th
u
s
im
p
r
o
v
in
g
its
ca
p
ac
ity
to
m
atch
m
o
d
el
p
ar
a
m
eter
s
ag
ain
s
t
th
e
m
u
ltifa
r
io
u
s
ter
r
ain
o
f
p
o
s
s
ib
le
an
s
wer
s
.
W
ith
a
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
d
r
o
p
o
f
1
5
%
o
v
e
r
th
e
b
aselin
e
m
o
d
el,
th
e
AI
S
tech
n
iq
u
e
r
o
u
tin
ely
b
ea
t c
o
n
v
en
tio
n
al
m
eth
o
d
s
in
o
u
r
test
s
.
T
h
e
AI
S
-
b
ased
clo
n
al
s
elec
tio
n
s
h
o
wed
a
s
ig
n
if
ican
t
b
en
ef
it
f
o
r
ap
p
licatio
n
s
n
ee
d
in
g
g
r
ea
t
ac
cu
r
ac
y
in
an
g
le
m
ea
s
u
r
em
e
n
t,
in
clu
d
in
g
r
o
b
o
tic
ar
m
o
p
er
atio
n
s
.
Mo
r
e
p
r
ec
is
e
an
d
c
o
n
s
is
ten
t
jo
in
t
an
g
le
esti
m
ates
em
er
g
ed
f
r
o
m
th
e
m
eth
o
d
’
s
c
ap
ac
ity
to
c
h
an
g
e
an
d
g
r
o
w
in
r
esp
o
n
s
e
to
th
e
s
itu
atio
n
d
em
an
d
s
.
I
n
p
ar
ticu
lar
,
u
s
in
g
6
-
DOF
r
o
b
o
t
ar
m
s
,
AI
S
o
b
tain
ed
an
a
v
er
ag
e
e
r
r
o
r
r
at
e
o
f
0
.
0
2
r
ad
ian
s
,
c
o
m
p
ar
e
d
t
o
0
.
0
5
r
a
d
ian
s
u
s
in
g
tr
ad
itio
n
al
tech
n
iq
u
es.
On
th
e
o
th
er
h
an
d
,
with
e
n
h
an
ce
m
en
ts
in
co
n
v
er
g
en
ce
s
p
ee
d
an
d
c
o
m
p
u
tatio
n
al
ef
f
ic
ien
cy
,
th
e
MLP
-
B
B
O
also
ex
h
ib
ited
en
c
o
u
r
ag
in
g
r
esu
lts
.
T
h
e
ML
P
-
B
B
O
ap
p
r
o
ac
h
m
ain
tain
s
a
c
o
m
p
etitiv
e
MSE
wh
ile
cu
ttin
g
co
m
p
u
tatio
n
al
tim
e
b
y
2
5
%
h
en
ce
it
s
u
its
r
ea
l
-
tim
e
ap
p
licatio
n
s
wh
en
co
m
p
u
tin
g
r
eso
u
r
ce
s
ar
e
r
estricte
d
.
I
n
ess
en
ce
,
b
o
t
h
M
L
P
-
B
B
O
an
d
AI
S m
eth
o
d
s
p
r
o
v
id
e
r
ea
s
o
n
a
b
le
ch
o
ices f
o
r
j
o
in
t a
n
g
le
esti
m
atio
n
b
ased
o
n
v
ar
io
u
s
s
tr
en
g
th
s
.
Alth
o
u
g
h
ML
P
-
B
B
O
o
f
f
er
s
f
ast
er
co
n
v
er
g
en
ce
an
d
r
ed
u
ce
d
p
r
o
ce
s
s
in
g
lo
ad
,
th
e
AI
S
ap
p
r
o
ac
h
ex
ce
ls
in
ac
c
u
r
ac
y
an
d
ad
a
p
tab
ilit
y
,
h
en
c
e
id
ea
l
f
o
r
h
ig
h
-
p
r
ec
is
io
n
w
o
r
k
.
Am
o
n
g
th
ese
m
eth
o
d
s
,
t
h
e
o
n
e
ch
o
s
en
d
ep
e
n
d
s
o
n
s
ev
er
al
p
ar
a
m
eter
s
s
u
c
h
as
a
v
ailab
le
p
r
o
ce
s
s
in
g
ca
p
a
b
ilit
y
an
d
allo
wed
er
r
o
r
lev
el.
Fu
t
u
r
e
r
esear
ch
m
ay
f
o
cu
s
o
n
e
n
h
an
cin
g
ea
c
h
m
eth
o
d
t
o
p
r
o
d
u
ce
e
v
en
m
o
r
e
n
o
tewo
r
th
y
MSE
r
ed
u
ctio
n
o
r
o
n
h
y
b
r
id
izin
g
b
o
th
ap
p
r
o
ac
h
es to
lev
er
ag
e
th
e
b
en
ef
its
o
f
ea
ch
.
R
esear
ch
in
g
h
y
b
r
id
m
o
d
els m
ay
p
r
o
v
id
e
a
m
eth
o
d
f
o
r
co
m
p
le
x
r
o
b
o
tic
ap
p
licatio
n
s
co
m
b
i
n
in
g
th
e
p
r
ec
is
io
n
o
f
AI
S
with
th
e
ef
f
icien
c
y
o
f
MLP
-
B
B
O.
T
h
e
AI
S
tech
n
iq
u
e
’
s
m
o
r
e
ac
cu
r
ate
ev
o
l
u
tio
n
ar
y
ap
p
r
o
ac
h
wh
ich
co
p
ies
n
at
u
r
al
im
m
u
n
e
r
esp
o
n
s
es
m
ay
ass
is
t
to
ex
p
lain
its
g
r
ea
ter
ef
f
ec
tiv
en
ess
.
T
h
is
ap
p
r
o
ac
h
p
r
o
b
ab
ly
en
ab
les
a
m
o
r
e
s
o
p
h
is
ticated
o
p
tim
izatio
n
p
r
o
ce
d
u
r
e
,
th
u
s
im
p
r
o
v
i
n
g
its
ca
p
ac
ity
to
m
atch
th
e
m
o
d
el
p
ar
am
eter
s
ag
ain
s
t c
o
n
v
o
lu
ted
ter
r
ai
n
o
f
p
o
s
s
ib
le
s
o
lu
tio
n
s
.
T
h
er
ef
o
r
e,
AI
S
-
b
ased
clo
n
al
s
elec
tio
n
m
ig
h
t
p
r
o
v
id
e
a
m
o
r
e
c
o
n
s
is
ten
t
o
p
tio
n
f
o
r
jo
b
s
n
ee
d
in
g
g
r
ea
t a
cc
u
r
ac
y
in
a
n
g
l
e
m
ea
s
u
r
em
en
t,
in
cl
u
d
in
g
r
o
b
o
tic
ar
m
m
an
ip
u
latio
n
s
.
I
n
th
e
e
n
d
,
b
o
th
ML
P
-
B
B
O
an
d
AI
S
ap
p
r
o
ac
h
es
p
r
o
v
id
e
s
e
n
s
ib
le
ch
o
ices
f
o
r
jo
in
t
an
g
le
ca
lcu
latio
n
with
b
en
ef
its
.
Am
o
n
g
th
ese
m
eth
o
d
s
,
th
e
c
h
o
ice
wo
u
ld
d
ep
en
d
o
n
s
ev
er
al
p
ar
am
eter
s
s
u
ch
as
p
r
o
ce
s
s
in
g
ca
p
ac
ity
an
d
to
ler
a
b
le
d
eg
r
e
e
o
f
er
r
o
r
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
f
o
cu
s
o
n
h
y
b
r
id
izin
g
b
o
th
ap
p
r
o
ac
h
es
to
lev
er
ag
e
th
e
b
en
ef
its
o
f
b
o
th
o
r
f
u
r
th
e
r
en
h
an
cin
g
ea
ch
m
eth
o
d
to
m
i
n
im
ize
MSE
ev
en
m
o
r
e
ef
f
ec
tiv
ely
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
13
,
No
.
4
,
Dec
em
b
er
20
24
:
40
1
-
4
0
9
408
6.
CO
NCLU
SI
O
N
T
h
is
wo
r
k
s
h
o
ws
th
e
p
r
ac
tical
r
elev
an
ce
an
d
ef
f
icien
c
y
o
f
s
ev
er
al
ar
tific
ial
in
tellig
en
ce
ap
p
r
o
ac
h
es
f
o
r
jo
i
n
t
an
g
le
p
r
e
d
ictio
n
o
f
th
e
PUMA5
6
0
r
o
b
o
tic
a
r
m
wh
ile
h
ig
h
lig
h
tin
g
th
eir
r
esp
e
ctiv
e
s
tr
en
g
th
s
.
Ou
r
s
im
u
latio
n
s
s
h
o
w
th
e
p
ar
ticu
lar
b
en
ef
its
o
f
th
e
AI
S
with
clo
n
al
s
elec
tio
n
,
th
e
ML
P
-
B
B
O,
an
d
wav
elet
n
etwo
r
k
s
in
h
an
d
lin
g
th
e
d
if
f
icu
lt
task
o
f
r
o
b
o
tic
ar
m
ar
ticu
latio
n
.
Ou
r
r
esu
lts
clea
r
ly
s
u
p
p
o
r
t
th
e
A
I
S
ap
p
r
o
ac
h
u
s
in
g
clo
n
al
s
elec
tio
n
,
p
ar
ticu
la
r
ly
b
ec
au
s
e
o
f
its
s
h
o
ck
in
g
ly
lo
w
m
ea
n
s
q
u
ar
e
er
r
o
r
s
r
elativ
e
to
th
o
s
e
ac
h
iev
ed
u
s
in
g
th
e
wa
v
elet
n
etwo
r
k
an
d
ML
P
-
B
B
O
tech
n
iq
u
es.
I
n
s
p
ir
ed
b
y
n
a
tu
r
al
im
m
u
n
o
lo
g
ical
p
r
o
ce
s
s
es,
th
e
p
r
ec
is
io
n
s
h
o
wn
b
y
th
e
AI
S
tech
n
iq
u
e
i
m
p
lies
th
at
its
ev
o
lu
tio
n
ar
y
alg
o
r
ith
m
s
ex
ce
l
i
n
im
p
r
o
v
in
g
s
o
lu
tio
n
s
f
o
r
co
m
p
l
ex
s
itu
atio
n
s
,
h
en
ce
p
r
o
d
u
cin
g
m
o
r
e
ac
cu
r
ac
y
in
jo
in
t a
n
g
le
esti
m
atio
n
s
.
T
h
er
e
is
s
till
a
n
ee
d
f
o
r
g
r
ea
ter
s
tu
d
y
an
d
d
ev
elo
p
m
en
t
ev
en
if
th
e
AI
-
b
ased
m
eth
o
d
s
u
n
d
er
ex
am
in
atio
n
in
th
is
wo
r
k
o
f
f
er
g
r
ea
t
p
r
o
m
is
e
f
o
r
r
o
b
o
ti
c
jo
in
t
an
g
le
m
ea
s
u
r
e
m
en
t
(
in
v
er
s
e
k
in
em
atic)
.
B
u
ild
in
g
o
n
th
e
b
asis
laid
b
y
cu
r
r
en
t
r
esear
c
h
,
f
u
tu
r
e
a
d
v
an
ce
m
en
ts
co
u
ld
c
o
m
b
in
e
th
e
ch
ar
ac
ter
is
tics
o
f
clo
n
al
s
elec
tio
n
AI
S
a
n
d
ML
P
-
B
B
O
to
p
r
o
v
id
e
a
m
o
r
e
r
o
b
u
s
t
alg
o
r
ith
m
.
Hy
b
r
id
s
y
s
tem
s
co
u
ld
co
m
b
in
e
t
h
e
f
lex
ib
ilit
y
o
f
B
B
O
with
th
e
ac
cu
r
ac
y
o
f
AI
S
to
m
o
r
e
ef
f
ec
ti
v
ely
ch
a
n
g
e
n
eu
r
al
n
etwo
r
k
weig
h
ts
.
E
v
en
m
o
r
e
ex
ac
t,
v
er
s
atile,
an
d
e
f
f
icien
t r
o
b
o
tic
s
y
s
tem
s
co
u
ld
r
esu
lt f
r
o
m
s
u
ch
h
y
b
r
id
a
p
p
r
o
ac
h
es.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
El
-
S
h
e
r
b
i
n
y
,
M
.
A
.
El
h
o
sse
i
n
i
,
a
n
d
A
.
Y
.
H
a
i
k
a
l
,
“
A
c
o
mp
a
r
a
t
i
v
e
st
u
d
y
o
f
s
o
f
t
c
o
mp
u
t
i
n
g
me
t
h
o
d
s t
o
s
o
l
v
e
i
n
v
e
r
se
k
i
n
e
m
a
t
i
c
s
p
r
o
b
l
e
m,
”
A
i
n
S
h
a
m
s E
n
g
i
n
e
e
r
i
n
g
J
o
u
rn
a
l
,
v
o
l
.
9
,
n
o
.
4
,
p
p
.
2
5
3
5
–
2
5
4
8
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
e
j
.
2
0
1
7
.
0
8
.
0
0
1
.
[
2
]
F
.
A
g
g
o
g
e
r
i
,
A
.
B
o
r
b
o
n
i
,
R
.
A
d
a
m
i
n
i
,
a
n
d
R
.
F
a
g
l
i
a
,
“
A
f
u
z
z
y
l
o
g
i
c
t
o
s
o
l
v
e
t
h
e
r
o
b
o
t
i
c
i
n
v
e
r
se
k
i
n
e
mat
i
c
p
r
o
b
l
e
m
,
”
A
p
p
l
i
e
d
Me
c
h
a
n
i
c
s
a
n
d
M
a
t
e
ri
a
l
s
,
v
o
l
.
7
7
2
,
p
p
.
4
8
8
–
4
9
3
,
Ju
l
.
2
0
1
5
,
d
o
i
:
1
0
.
4
0
2
8
/
w
w
w
.
sci
e
n
t
i
f
i
c
.
n
e
t
/
A
M
M
.
7
7
2
.
4
8
8
.
[
3
]
S
.
M
o
ma
n
i
,
Z.
S
.
A
b
o
-
H
a
mm
o
u
,
a
n
d
O
.
M
K
.
A
l
sma
d
,
“
S
o
l
u
t
i
o
n
o
f
i
n
v
e
r
se
k
i
n
e
mat
i
c
s
p
r
o
b
l
e
m
u
si
n
g
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
ms
,
”
Ap
p
l
i
e
d
M
a
t
h
e
m
a
t
i
c
s &
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
2
2
5
–
2
3
3
,
J
a
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
8
5
7
6
/
a
mi
s
/
1
0
0
1
2
2
.
[
4
]
A.
-
V
.
D
u
k
a
,
“
N
e
u
r
a
l
n
e
t
w
o
r
k
b
a
s
e
d
i
n
v
e
r
se
k
i
n
e
ma
t
i
c
s
s
o
l
u
t
i
o
n
f
o
r
t
r
a
j
e
c
t
o
r
y
t
r
a
c
k
i
n
g
o
f
a
r
o
b
o
t
i
c
a
r
m,
”
Pr
o
c
e
d
i
a
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
2
,
p
p
.
2
0
–
2
7
,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
t
c
y
.
2
0
1
3
.
1
2
.
4
5
1
.
[
5
]
H
.
T
a
k
a
t
a
n
i
,
N
.
A
r
a
k
i
,
T.
S
a
t
o
,
a
n
d
Y
.
K
o
n
i
sh
i
,
“
N
e
u
r
a
l
n
e
t
w
o
r
k
-
b
a
se
d
c
o
n
st
r
u
c
t
i
o
n
o
f
i
n
v
e
r
se
k
i
n
e
ma
t
i
c
s
mo
d
e
l
f
o
r
s
e
r
i
a
l
r
e
d
u
n
d
a
n
t
ma
n
i
p
u
l
a
t
o
r
s,
”
Ar
t
i
f
i
c
i
a
l
L
i
f
e
a
n
d
Ro
b
o
t
i
c
s
,
v
o
l
.
2
4
,
n
o
.
4
,
p
p
.
4
8
7
–
4
9
3
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
0
1
5
-
0
1
9
-
0
0
5
5
2
-
y.
[
6
]
S
.
H
a
b
i
b
k
h
a
h
a
n
d
R
.
V
.
M
a
y
o
r
g
a
,
“
A
n
A
N
N
a
n
d
v
i
r
t
u
a
l
v
e
c
t
o
r
f
u
n
c
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
t
h
e
c
o
m
p
u
t
a
t
i
o
n
o
f
t
h
e
i
n
v
e
r
se
k
i
n
e
ma
t
i
c
s
o
f
r
e
d
u
n
d
a
n
t
ma
n
i
p
u
l
a
t
o
r
s,
”
W
S
EA
S
t
ra
n
s
a
c
t
i
o
n
s
o
n
i
n
f
o
rm
a
t
i
o
n
s
c
i
e
n
c
e
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
8
,
p
p
.
1
3
1
–
1
4
0
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
7
3
9
4
/
2
3
2
0
9
.
2
0
2
1
.
1
8
.
1
5
.
[
7
]
J.
B
a
t
i
st
a
,
D
.
S
o
u
z
a
,
L.
d
o
s
R
e
i
s,
A
.
B
a
r
b
o
s
a
,
a
n
d
R
.
A
r
a
ú
j
o
,
“
D
y
n
a
mi
c
mo
d
e
l
a
n
d
i
n
v
e
r
s
e
k
i
n
e
mat
i
c
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
a
3
-
D
O
F
man
i
p
u
l
a
t
o
r
u
si
n
g
R
LSP
S
O
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
0
,
n
o
.
2
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
0
0
2
0
4
1
6
.
[
8
]
M
.
C
.
d
o
s Sa
n
t
o
s
,
R
.
H
.
C
.
P
a
l
á
c
i
o
s
,
M
.
M
e
n
d
o
n
ç
a
,
J.
A
.
F
a
b
r
i
,
a
n
d
W
.
F
.
G
o
d
o
y
,
“
A
n
e
u
r
a
l
a
u
t
o
n
o
m
o
u
s
r
o
b
o
t
i
c
ma
n
i
p
u
l
a
t
o
r
w
i
t
h
t
h
r
e
e
d
e
g
r
e
e
s
o
f
f
r
e
e
d
o
m,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
,
v
o
l
.
3
7
,
n
o
.
9
,
p
p
.
5
5
9
7
–
5
6
1
6
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
2
/
i
n
t
.
2
2
8
0
3
.
[
9
]
H
.
Z.
K
h
a
l
e
e
l
,
“
I
n
v
e
r
s
e
k
i
n
e
ma
t
i
c
s
s
o
l
u
t
i
o
n
f
o
r
r
e
d
u
n
d
a
n
t
r
o
b
o
t
m
a
n
i
p
u
l
a
t
o
r
u
s
i
n
g
c
o
mb
i
n
a
t
i
o
n
o
f
G
A
a
n
d
N
N
,
”
Al
-
K
h
w
a
r
i
zm
i
En
g
i
n
e
e
ri
n
g
J
o
u
rn
a
l
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
1
3
6
–
1
4
4
,
2
0
1
8
,
d
o
i
:
1
0
.
2
2
1
5
3
/
h
t
t
p
s
:
/
/
d
o
i
.
o
r
g
/
1
0
.
2
2
1
5
3
/
k
e
j
.
2
0
1
8
.
1
0
.
0
0
8
.
[
1
0
]
R
.
F
.
H
a
ss
a
n
,
A
.
R
.
A
j
e
l
,
S
.
J
.
A
b
b
a
s,
a
n
d
A
.
J.
H
u
m
a
i
d
i
,
“
F
P
G
A
b
a
se
d
H
I
L
c
o
-
si
m
u
l
a
t
i
o
n
o
f
2
D
O
F
-
P
I
D
c
o
n
t
r
o
l
l
e
r
t
u
n
e
d
b
y
P
S
O
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m,
”
I
C
I
C
E
x
p
res
s Let
t
e
rs
,
v
o
l
.
1
6
,
n
o
.
1
2
,
p
p
.
1
2
6
9
–
1
2
7
8
,
2
0
2
2
,
d
o
i
:
1
0
.
2
4
5
0
7
/
i
c
i
c
e
l
.
1
6
.
1
2
.
1
2
6
9
.
[
1
1
]
T.
R
.
P
r
a
t
h
a
b
,
R
.
S
.
M
a
n
i
M
a
l
a
r
,
a
n
d
T.
A
h
i
l
a
n
,
“
A
m
e
t
h
o
d
o
f
e
x
t
e
n
d
e
d
j
a
c
o
b
i
a
n
a
n
d
f
i
r
e
f
l
y
a
l
g
o
r
i
t
h
m
f
o
r
t
h
e
k
i
n
e
m
a
t
i
c
a
n
a
l
y
s
i
s
o
f
p
l
a
n
a
r
r
o
b
o
t
s,
”
I
AE
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ro
b
o
t
i
c
s
a
n
d
A
u
t
o
m
a
t
i
o
n
(
I
J
RA)
,
v
o
l
.
6
,
n
o
.
2
,
p
p
.
1
4
1
–
1
5
0
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
r
a
.
v
6
i
2
.
p
p
1
4
1
-
1
5
0
.
[
1
2
]
H
.
R
.
P
a
t
e
l
a
n
d
Y
.
P
a
t
e
l
,
“
I
n
v
e
r
s
e
k
i
n
e
m
a
t
i
c
a
n
a
l
y
s
i
s
o
f
3
D
O
F
3
-
P
R
S
P
M
f
o
r
m
a
c
h
i
n
i
n
g
o
n
i
n
c
l
i
n
e
d
p
r
i
sm
a
t
i
c
su
r
f
a
c
e
s,
”
I
AE
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
R
o
b
o
t
i
c
s
a
n
d
Au
t
o
m
a
t
i
o
n
(
I
J
RA)
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
1
3
5
–
1
4
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
r
a
.
v
9
i
2
.
p
p
1
3
5
-
1
4
2
.
[
1
3
]
G
.
W
u
a
n
d
H
.
S
h
e
n
,
“
K
i
n
e
ma
t
i
c
a
n
a
l
y
si
s a
n
d
d
e
si
g
n
o
f
a
n
e
w
t
w
o
-
l
i
m
b
p
a
r
a
l
l
e
l
s
c
h
o
n
f
l
i
e
s
-
m
o
t
i
o
n
g
e
n
e
r
a
t
o
r
c
o
n
si
d
e
r
i
n
g
i
s
o
t
r
o
p
i
c
c
o
n
f
i
g
u
r
a
t
i
o
n
,
”
I
AE
S
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
R
o
b
o
t
i
c
s
a
n
d
A
u
t
o
m
a
t
i
o
n
(
I
J
RA)
,
v
o
l
.
1
1
,
n
o
.
2
,
p
p
.
1
3
2
–
1
4
0
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
r
a
.
v
1
1
i
2
.
p
p
1
3
2
-
1
4
0
.
[
1
4
]
A.
-
A
.
S
.
A
b
d
e
l
-
S
a
l
a
m
a
n
d
I
.
N
.
Jl
e
t
a
,
“
F
u
z
z
y
l
o
g
i
c
c
o
n
t
r
o
l
l
e
r
d
e
s
i
g
n
f
o
r
P
U
M
A
5
6
0
r
o
b
o
t
m
a
n
i
p
u
l
a
t
o
r
,
”
I
A
ES
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ro
b
o
t
i
c
s
a
n
d
A
u
t
o
m
a
t
i
o
n
(
I
J
RA)
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
7
3
–
8
3
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
r
a
.
v
9
i
2
.
p
p
7
3
-
8
3
.
[
1
5
]
F
.
M
a
r
i
c
,
M
.
G
i
a
m
o
u
,
A
.
W
.
H
a
l
l
,
S
.
K
h
o
u
b
y
a
r
i
a
n
,
I
.
P
e
t
r
o
v
i
c
,
a
n
d
J.
K
e
l
l
y
,
“
R
i
e
ma
n
n
i
a
n
o
p
t
i
mi
z
a
t
i
o
n
f
o
r
d
i
st
a
n
c
e
-
g
e
o
m
e
t
r
i
c
i
n
v
e
r
se
k
i
n
e
m
a
t
i
c
s,
”
I
EE
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
R
o
b
o
t
i
c
s
,
v
o
l
.
3
8
,
n
o
.
3
,
p
p
.
1
7
0
3
–
1
7
2
2
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TR
O
.
2
0
2
1
.
3
1
2
3
8
4
1
.
[
1
6
]
A
.
A
.
Ja
b
e
r
,
“
P
U
M
A
5
6
0
r
o
b
o
t
a
n
d
i
t
s
d
y
n
a
mi
c
c
h
a
r
a
c
t
e
r
i
st
i
c
s
,
”
i
n
D
e
s
i
g
n
o
f
a
n
I
n
t
e
l
l
i
g
e
n
t
Em
b
e
d
d
e
d
S
y
s
t
e
m
f
o
r
C
o
n
d
i
t
i
o
n
Mo
n
i
t
o
r
i
n
g
o
f
a
n
I
n
d
u
st
r
i
a
l
R
o
b
o
t
,
2
0
1
7
,
p
p
.
7
5
–
9
1
.
[
1
7
]
2
0
0
3
.
P
r
o
c
e
e
d
i
n
g
s
2
A
r
t
i
f
i
c
i
a
l
I
mm
u
n
e
S
y
s
t
e
ms
:
S
e
c
o
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
,
I
C
A
R
I
S
2
0
0
3
,
E
d
i
n
b
u
r
g
h
,
U
K
,
S
e
p
t
e
m
b
e
r
1
-
3
,
Art
i
f
i
c
i
a
l
i
m
m
u
n
e
sys
t
e
m
s
,
v
o
l
.
2
7
8
7
.
B
e
r
l
i
n
,
H
e
i
d
e
l
b
e
r
g
:
S
p
r
i
n
g
e
r
B
e
r
l
i
n
H
e
i
d
e
l
b
e
r
g
,
2
0
0
3
.
[
1
8
]
Y
.
W
a
n
g
a
n
d
T.
Li
,
“
L
o
c
a
l
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
b
a
se
d
o
n
a
r
t
i
f
i
c
i
a
l
i
mm
u
n
e
s
y
st
e
m
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
Ap
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
8
7
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
1
9
.
1
0
5
9
8
9
.
[
1
9
]
F
.
G
o
n
z
a
l
e
z
a
n
d
D
.
D
a
s
g
u
p
t
a
,
“
N
e
u
r
o
-
i
mm
u
n
e
a
n
d
s
e
l
f
-
o
r
g
a
n
i
z
i
n
g
ma
p
a
p
p
r
o
a
c
h
e
s
t
o
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
:
a
c
o
m
p
a
r
i
so
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
Fi
rs
t
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ar
t
i
f
i
c
i
a
l
I
m
m
u
n
e
S
y
s
t
e
m
s
,
2
0
0
2
,
p
p
.
2
0
3
–
2
1
1
.
[
2
0
]
R
.
M
.
M
i
k
h
e
r
s
k
i
i
a
n
d
M
.
R
.
M
i
k
h
e
r
s
k
i
i
,
“
A
n
a
l
y
s
i
s
o
f
t
h
e
u
s
e
o
f
a
r
t
i
f
i
c
i
a
l
i
mm
u
n
e
s
y
st
e
ms,
”
I
O
P
C
o
n
f
e
re
n
c
e
S
e
ri
e
s:
M
a
t
e
ri
a
l
s
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
0
6
9
,
n
o
.
1
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X
/
1
0
6
9
/
1
/
0
1
2
0
2
5
.
[
2
1
]
D
.
S
i
m
o
n
,
“
B
i
o
g
e
o
g
r
a
p
h
y
-
b
a
s
e
d
o
p
t
i
mi
z
a
t
i
o
n
,
”
I
E
EE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
E
v
o
l
u
t
i
o
n
a
ry
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
1
2
,
n
o
.
6
,
p
p
.
7
0
2
–
7
1
3
,
D
e
c
.
2
0
0
8
,
d
o
i
:
1
0
.
1
1
0
9
/
T
EV
C
.
2
0
0
8
.
9
1
9
0
0
4
.
[
2
2
]
S
.
Li
a
n
g
,
Z.
F
a
n
g
,
G
.
S
u
n
,
a
n
d
G
.
Q
u
,
“
B
i
o
g
e
o
g
r
a
p
h
y
-
b
a
se
d
o
p
t
i
m
i
z
a
t
i
o
n
w
i
t
h
a
d
a
p
t
i
v
e
mi
g
r
a
t
i
o
n
a
n
d
a
d
a
p
t
i
v
e
mu
t
a
t
i
o
n
w
i
t
h
i
t
s
a
p
p
l
i
c
a
t
i
o
n
i
n
s
i
d
e
l
o
b
e
r
e
d
u
c
t
i
o
n
o
f
a
n
t
e
n
n
a
a
r
r
a
y
s,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
2
1
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
2
.
1
0
8
7
7
2
.
[
2
3
]
C
.
J
y
i
i
d
u
,
“
B
i
o
g
e
o
g
r
a
p
h
y
-
b
a
se
d
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
ms
b
a
s
e
d
o
n
i
m
p
r
o
v
e
d
mi
g
r
a
t
i
o
n
r
a
t
e
m
o
d
e
l
s,
”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
9
,
n
o
.
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
7
7
2
/
j
.
i
ssn
.
1
0
0
1
-
9
0
8
1
.
2
0
1
9
0
2
0
3
2
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
I
n
teg
r
a
tin
g
a
r
tifi
cia
l imm
u
n
e
s
ystem
s
a
n
d
mu
lti
-
la
ye
r
p
ercep
tr
o
n
-
b
io
g
e
o
g
r
a
p
h
y
-
b
a
s
ed
…
(
A
mel
S
era
t
)
409
[
2
4
]
M
.
K
h
i
sh
e
,
M
.
R
.
M
o
sa
v
i
,
a
n
d
M
.
K
a
v
e
h
,
“
I
mp
r
o
v
e
d
mi
g
r
a
t
i
o
n
m
o
d
e
l
s
o
f
b
i
o
g
e
o
g
r
a
p
h
y
-
b
a
s
e
d
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
so
n
a
r
d
a
t
a
se
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
y
u
si
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
A
p
p
l
i
e
d
A
c
o
u
s
t
i
c
s
,
v
o
l
.
1
1
8
,
p
p
.
1
5
–
2
9
,
M
a
r
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
a
c
o
u
st
.
2
0
1
6
.
1
1
.
0
1
2
.
[
2
5
]
H
.
C
h
e
n
,
W
.
C
h
e
n
,
a
n
d
T.
X
i
e
,
“
W
a
v
e
l
e
t
n
e
t
w
o
r
k
s
o
l
u
t
i
o
n
f
o
r
t
h
e
i
n
v
e
r
s
e
k
i
n
e
ma
t
i
c
s
p
r
o
b
l
e
m i
n
r
o
b
o
t
i
c
ma
n
i
p
u
l
a
t
o
r
,
”
J
o
u
r
n
a
l
o
f
Z
h
e
j
i
a
n
g
U
n
i
v
e
rs
i
t
y
-
S
C
I
EN
C
E
A
,
v
o
l
.
7
,
n
o
.
4
,
p
p
.
5
2
5
–
5
2
9
,
A
p
r
.
2
0
0
6
,
d
o
i
:
1
0
.
1
6
3
1
/
j
z
u
s
.
2
0
0
6
.
A
0
5
2
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Am
e
l
S
e
r
a
t
i
s
a
p
r
o
fe
ss
o
r
a
t
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
M
u
sta
p
h
a
S
tam
b
o
u
l
i
M
a
sc
a
ra
Un
i
v
e
rsity
(
UMS
M
),
M
a
sc
a
ra
,
Alg
e
ria.
S
h
e
h
o
ld
s
a
P
h
D
in
c
o
m
p
u
ter
sc
ien
c
e
.
Dr.
S
e
ra
t
c
a
n
b
e
c
o
n
tac
ted
a
t
a
.
se
ra
t@u
n
i
v
-
m
a
sc
a
ra
.
d
z
o
r
se
rra
t_
a
m
e
l@y
a
h
o
o
.
fr
.
Ba
c
h
ir
Dje
b
b
a
r
is
a
p
ro
fe
ss
o
r
a
t
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
s
,
Un
iv
e
rsity
o
f
S
c
ien
c
e
s
a
n
d
Tec
h
n
o
l
o
g
ies
Ora
n
,
Alg
e
ria.
He
re
c
e
i
v
e
d
h
is
P
h
.
D.
t
h
ir
d
c
y
c
le
d
e
g
re
e
fro
m
th
e
To
u
lo
u
se
Un
i
v
e
rsity
III,
F
ra
n
c
e
,
i
n
1
9
7
5
.
He
is
t
h
e
d
irec
to
r
o
f
th
e
G
e
o
m
e
try
a
n
d
An
a
ly
sis
Lab
o
ra
to
r
y
(
G
EA
NLAB
)
.
He
a
c
q
u
ires
m
a
n
y
a
wa
rd
s
a
n
d
a
p
p
re
c
iatio
n
fo
r
m
d
iffere
n
t
p
a
rti
e
s
fo
r
e
x
c
e
ll
e
n
t
tea
c
h
in
g
a
n
d
e
x
tra
-
sc
ien
ti
fic
re
se
a
rc
h
e
ffo
rts.
Also
,
h
e
wa
s
in
v
it
e
d
t
o
j
o
in
m
a
n
y
re
sp
e
c
t
a
b
le
sc
ien
ti
fic
o
r
g
a
n
iza
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
b
a
c
h
ir.
d
jeb
b
a
r@u
n
i
v
-
u
st
o
.
d
z
.
Evaluation Warning : The document was created with Spire.PDF for Python.