I
nte
rna
t
io
na
l J
o
urna
l o
f
Ro
bo
t
ics a
nd
Aut
o
m
a
t
io
n
(
I
J
RA
)
Vo
l.
4
,
No
.
2
,
J
u
n
e
2
0
1
5
,
p
p
.
1
0
9
~1
2
3
I
SS
N:
2089
-
4856
109
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
RA
Inv
erse K
in
e
m
a
ti
c Solutio
n of
5R
M
a
nipula
tor
U
sin
g
ANN
a
nd ANF
IS
P
a
ncha
na
nd
J
ha
,
B
.
B
.
B
is
wa
l
De
p
a
rt
m
e
n
t
o
f
In
d
u
strial
De
sig
n
,
Na
ti
o
n
a
l
I
n
stit
u
t
e
o
f
T
e
c
h
n
o
lo
g
y
Ro
u
rk
e
la
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
9
,
2
0
1
5
R
ev
i
s
ed
A
p
r
2
5
,
2
0
1
5
A
cc
ep
ted
Ma
y
1
2
,
2
0
1
5
In
v
e
rse
k
in
e
m
a
ti
c
s
o
f
m
a
n
ip
u
lat
o
r
c
o
m
p
rise
s
th
e
c
o
m
p
u
tatio
n
r
e
q
u
ired
to
f
in
d
th
e
j
o
in
t
a
n
g
les
f
o
r
a
g
iv
e
n
Ca
rtes
ian
p
o
siti
o
n
a
n
d
o
rien
tatio
n
o
f
th
e
e
n
d
e
ffe
c
to
r.
T
h
e
re
is
n
o
u
n
iq
u
e
so
lu
ti
o
n
f
o
r
t
h
e
in
v
e
rse
k
in
e
m
a
ti
c
s
th
u
s
n
e
c
e
ss
it
a
ti
n
g
a
p
p
li
c
a
ti
o
n
o
f
a
p
p
ro
p
riate
p
re
d
ictiv
e
m
o
d
e
ls
f
ro
m
th
e
so
f
t
c
o
m
p
u
ti
n
g
d
o
m
a
in
.
A
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
a
n
d
a
d
a
p
ti
v
e
n
e
u
ra
l
f
u
z
z
y
in
f
e
re
n
c
e
s
y
ste
m
t
e
c
h
n
iq
u
e
s ca
n
b
e
g
a
in
f
u
ll
y
u
se
d
to
y
ield
th
e
d
e
sire
d
re
su
lt
s.
T
h
is
p
a
p
e
r
p
ro
p
o
se
s
stru
c
tu
re
d
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
(
A
NN
)
m
o
d
e
l
a
n
d
a
d
a
p
ti
v
e
n
e
u
ra
l
f
u
z
z
y
in
f
e
r
e
n
c
e
s
y
ste
m
(
A
NFIS
)
to
f
in
d
th
e
in
v
e
rse
k
in
e
m
a
ti
c
s
so
lu
ti
o
n
o
f
ro
b
o
t
m
a
n
ip
u
lat
o
r.
T
h
e
A
NN
m
o
d
e
l
u
se
d
i
s
a
m
u
lt
i
-
la
y
e
re
d
p
e
rc
e
p
tro
n
Ne
u
ra
l
Ne
two
rk
(M
L
P
NN
).
W
h
e
re
in
,
g
ra
d
ien
t
d
e
sc
e
n
t
ty
p
e
o
f
le
a
rn
in
g
ru
les
is
a
p
p
li
e
d
.
A
n
a
tt
e
m
p
t
h
a
s
b
e
e
n
m
a
d
e
to
f
in
d
th
e
b
e
st
A
N
N
c
o
n
f
ig
u
ra
ti
o
n
f
o
r
th
e
p
ro
b
lem
.
It
is
f
o
u
n
d
th
a
t
A
NFIS
g
iv
e
s
b
e
tt
e
r
re
su
lt
a
n
d
m
in
im
u
m
e
rro
r
a
s co
m
p
a
re
d
to
A
N
N.
K
ey
w
o
r
d
:
A
N
FIS
D
-
H
P
ar
a
m
eter
s
Fo
r
w
ar
d
Kin
e
m
atic
s
I
n
v
er
s
e
Ki
n
e
m
atic
s
ML
P
Neu
r
al
Net
w
o
r
k
Co
p
y
rig
h
t
©
2
0
1
5
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
:
P
an
ch
an
a
n
d
J
h
a,
Dep
ar
te
m
en
t o
f
I
n
d
u
s
tr
ial
Des
ig
n
,
Natio
n
al
I
n
s
tit
u
te
o
f
T
ec
h
n
o
lo
g
y
,
R
o
u
r
k
e
la
,
7
6
9
0
0
8
,
Od
is
h
a,
I
n
d
ia.
E
m
ail: j
h
a_
ip
0
0
7
@
h
o
t
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
R
o
b
o
t
m
a
n
ip
u
lato
r
i
s
co
m
p
o
s
ed
o
f
a
s
er
ial
c
h
ai
n
o
f
r
i
g
id
li
n
k
s
co
n
n
ec
ted
to
ea
ch
o
th
er
b
y
r
e
v
o
lu
te
o
r
p
r
is
m
atic
j
o
in
ts
.
E
ac
h
r
o
b
o
t
j
o
in
t
lo
ca
tio
n
is
u
s
u
all
y
d
e
f
in
ed
r
elativ
e
to
th
e
n
ei
g
h
b
o
u
r
i
n
g
j
o
in
t.
T
h
e
r
elatio
n
b
et
w
ee
n
s
u
cc
es
s
iv
e
j
o
in
ts
is
d
escr
ib
ed
b
y
4
x
4
h
o
m
o
g
e
n
eo
u
s
tr
a
n
s
f
o
r
m
atio
n
m
atr
ices
t
h
at
h
a
v
e
o
r
ien
tatio
n
an
d
p
o
s
itio
n
d
ata
o
f
r
o
b
o
ts
.
T
h
e
n
u
m
b
er
o
f
th
o
s
e
tr
an
s
f
o
r
m
atio
n
m
atr
ices
d
e
ter
m
i
n
es
th
e
d
eg
r
ee
s
o
f
f
r
ee
d
o
m
o
f
r
o
b
o
ts
.
T
h
e
p
r
o
d
u
ct
o
f
s
u
ch
m
atr
ices
p
r
o
d
u
ce
s
f
i
n
al
o
r
ien
tatio
n
an
d
p
o
s
i
tio
n
d
ata
o
f
an
n
d
eg
r
ee
s
o
f
f
r
ee
d
o
m
r
o
b
o
t
m
a
n
ip
u
lato
r
.
R
o
b
o
t
co
n
tr
o
l
ac
tio
n
s
ar
e
ex
ec
u
ted
in
t
h
e
j
o
in
t
co
o
r
d
in
ates
w
h
ile
r
o
b
o
t
m
o
tio
n
s
ar
e
s
p
ec
if
ied
in
t
h
e
C
ar
tesi
a
n
co
o
r
d
in
ates.
C
o
n
v
er
s
io
n
o
f
t
h
e
p
o
s
itio
n
a
n
d
o
r
ien
tatio
n
o
f
r
o
b
o
t
m
an
ip
u
lato
r
en
d
-
e
f
f
ec
to
r
s
f
r
o
m
C
ar
te
s
ian
s
p
ac
e
to
j
o
in
t
s
p
ac
e
is
ca
l
led
as
in
v
er
s
e
k
in
e
m
at
ics
p
r
o
b
lem
.
T
h
is
is
o
f
f
u
n
d
a
m
en
ta
l
i
m
p
o
r
tan
ce
i
n
ca
lcu
lati
n
g
d
esire
d
jo
in
t
an
g
les
f
o
r
r
o
b
o
t
m
an
ip
u
lato
r
d
esig
n
an
d
co
n
tr
o
l.
I
n
m
o
s
t
r
o
b
o
tic
a
p
p
licatio
n
s
th
e
d
esir
ed
p
o
s
itio
n
s
an
d
o
r
ien
tatio
n
s
o
f
th
e
en
d
ef
f
ec
to
r
s
ar
e
s
p
ec
i
f
ied
b
y
th
e
u
s
er
in
C
ar
tesi
a
n
co
o
r
d
in
ates.
T
h
e
c
o
r
r
esp
o
n
d
in
g
j
o
in
t
v
alu
e
s
m
u
s
t
b
e
co
m
p
u
ted
at
h
i
g
h
s
p
ee
d
b
y
th
e
in
v
e
r
s
e
k
in
e
m
at
ics
tr
an
s
f
o
r
m
a
tio
n
[
1
]
.
Fo
r
a
m
a
n
ip
u
lato
r
w
it
h
n
d
e
g
r
ee
o
f
f
r
ee
d
o
m
,
a
t
a
n
y
in
s
ta
n
t
o
f
ti
m
e
th
e
j
o
in
t
v
ar
iab
le
is
d
e
n
o
ted
b
y
i
=
(
t
)
,
i
=
1
,
2
,
3
.
.
.
.
.
.
.
.
.
n
an
d
p
o
s
iti
o
n
v
ar
iab
les
b
y
x
j
=
x
(
t)
,
j
=
1
,
2
,
3
.
.
.
.
.
.
.
m
.
T
h
e
r
elatio
n
s
b
et
w
ee
n
t
h
e
e
nd
-
e
f
f
e
cto
r
s
p
o
s
itio
n
x
(
t)
an
d
j
o
in
t
an
g
le
(
t)
ca
n
b
e
r
ep
r
esen
ted
b
y
f
o
r
w
ar
d
k
i
n
e
m
atic
eq
u
atio
n
(
1
)
W
h
er
e,
f
is
a
n
o
n
li
n
ea
r
co
n
tin
u
o
u
s
a
n
d
d
if
f
er
en
tiab
le
f
u
n
ct
i
o
n
.
))
(
(
)
(
t
f
t
x
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4856
IJ
RA
Vo
l.
4
,
No
.
2
,
J
u
n
e
2
0
1
5
:
1
0
9
–
12
3
110
On
th
e
o
t
h
er
h
an
d
,
w
it
h
th
e
d
esire
d
en
d
ef
f
ec
to
r
s
p
o
s
itio
n
,
th
e
p
r
o
b
lem
o
f
f
i
n
d
in
g
th
e
v
al
u
es
o
f
t
h
e
j
o
in
t v
ar
iab
les is
i
n
v
er
s
e
k
i
n
e
m
atic
s
,
w
h
ic
h
ca
n
b
e
s
o
l
v
ed
b
y
,
(
2
)
I
n
v
er
s
e
k
i
n
e
m
atic
s
s
o
l
u
tio
n
is
n
o
t
u
n
iq
u
e
d
u
e
to
n
o
n
li
n
ea
r
,
u
n
ce
r
tai
n
a
n
d
ti
m
e
v
ar
y
in
g
n
a
tu
r
e
o
f
th
e
g
o
v
er
n
in
g
eq
u
atio
n
s
[
2
]
.
T
h
e
d
if
f
er
en
t
tech
n
iq
u
e
s
u
s
ed
f
o
r
s
o
lv
i
n
g
i
n
v
er
s
e
k
in
e
m
at
ics
c
an
b
e
clas
s
i
f
ied
a
s
alg
eb
r
aic,
g
eo
m
etr
ic
a
n
d
iter
ativ
e.
T
h
e
al
g
eb
r
aic
m
et
h
o
d
s
d
o
n
o
t
g
u
ar
an
tee
clo
s
ed
f
o
r
m
s
o
lu
tio
n
s
.
I
n
ca
s
e
o
f
g
eo
m
etr
ic
m
et
h
o
d
s
,
clo
s
ed
f
o
r
m
s
o
lu
tio
n
s
f
o
r
th
e
f
ir
s
t
th
r
ee
j
o
in
ts
o
f
th
e
m
a
n
ip
u
lato
r
m
u
s
t
ex
i
s
t
g
eo
m
etr
ic
all
y
.
T
h
e
iter
ativ
e
m
et
h
o
d
s
co
n
v
er
g
e
to
o
n
l
y
a
s
in
g
le
s
o
lu
t
io
n
d
ep
en
d
in
g
o
n
t
h
e
s
tar
ti
n
g
p
o
in
t
a
n
d
m
a
y
n
o
t
w
o
r
k
n
ea
r
s
in
g
u
lar
itie
s
[3
-
5]
.
T
h
e
f
o
r
w
ar
d
k
in
e
m
at
ic
eq
u
ati
o
n
s
al
w
a
y
s
h
a
v
e
a
u
n
iq
u
e
s
o
lu
tio
n
,
an
d
th
e
r
es
u
lti
n
g
Neu
r
al
n
et
ca
n
b
e
u
s
ed
as
a
s
tar
tin
g
p
o
in
t
f
o
r
f
u
r
th
er
r
ef
in
e
m
e
n
t
w
h
e
n
t
h
e
m
a
n
ip
u
lato
r
d
o
es
b
ec
o
m
e
a
v
ailab
l
e.
A
r
ti
f
icia
l
n
eu
r
al
n
et
w
o
r
k
e
s
p
ec
iall
y
M
L
P
(
m
u
l
ti
-
la
y
er
ed
p
er
ce
p
tr
o
n
)
is
u
s
ed
to
lear
n
t
h
e
f
o
r
w
ar
d
an
d
t
h
e
in
v
er
s
e
k
in
e
m
atic
s
eq
u
atio
n
s
o
f
f
iv
e
d
e
g
r
ee
s
f
r
ee
d
o
m
(
DO
F)
r
o
b
o
t
ar
m
[
6
-
7
]
.
T
h
is
u
n
s
u
p
er
v
is
ed
m
et
h
o
d
lear
n
s
t
h
e
f
u
n
ctio
n
a
l
r
elatio
n
s
h
ip
b
et
w
ee
n
in
p
u
t
(
C
ar
tesi
an
)
s
p
ac
e
an
d
o
u
tp
u
t
(
j
o
in
t)
s
p
ac
e
b
ased
o
n
a
lo
ca
lize
d
ad
ap
tatio
n
o
f
t
h
e
m
ap
p
in
g
,
b
y
u
s
i
n
g
t
h
e
m
a
n
ip
u
lato
r
its
el
f
u
n
d
er
j
o
in
t
co
n
tr
o
l
an
d
ad
ap
tin
g
t
h
e
s
o
lu
tio
n
b
a
s
e
d
o
n
a
co
m
p
ar
i
s
o
n
b
et
w
ee
n
t
h
e
r
es
u
lti
n
g
lo
ca
tio
n
s
o
f
th
e
m
an
ip
u
lato
r
‟
s
e
n
d
ef
f
e
cto
r
s
in
C
ar
tes
ian
s
p
ac
e
w
i
th
t
h
e
d
esire
d
lo
ca
tio
n
[
6
].
Ma
n
y
w
o
r
k
s
h
a
v
e
b
ee
n
co
m
p
leted
r
elate
d
to
th
e
n
e
u
r
al
n
et
w
o
r
k
-
b
ased
i
n
v
er
s
e
k
i
n
e
m
at
ic
s
s
o
l
u
tio
n
o
f
r
o
b
o
t
m
a
n
ip
u
la
to
r
s
[8
-
1
1
]
.
T
h
e
p
r
esen
t
w
o
r
k
p
r
o
p
o
s
es
in
v
er
s
e
k
i
n
e
m
atic
s
s
o
l
u
tio
n
s
b
ased
o
n
s
tr
u
ct
u
r
ed
ML
P
NN
th
a
t c
an
b
e
tr
ain
ed
q
u
ick
l
y
.
ML
P
n
e
u
r
al
n
et
w
o
r
k
i
s
u
s
ed
to
f
i
n
d
in
v
er
s
e
k
i
n
e
m
atics
s
o
l
u
tio
n
w
h
ich
y
ield
s
m
u
lt
ip
le
a
n
d
p
r
ec
is
e
s
o
lu
tio
n
s
w
it
h
an
ac
ce
p
tab
le
e
r
r
o
r
an
d
ar
e
s
u
i
tab
le
f
o
r
r
ea
l
-
tim
e
ad
ap
tiv
e
co
n
tr
o
l
o
f
r
o
b
o
tic
m
a
n
ip
u
lato
r
s
[
1
2
]
.
T
h
er
ef
o
r
e,
th
e
m
ai
n
ai
m
o
f
th
i
s
w
o
r
k
is
f
o
c
u
s
ed
o
n
m
i
n
i
m
izi
n
g
th
e
m
ea
n
s
q
u
ar
e
er
r
o
r
o
f
th
e
n
e
u
r
al
n
et
w
o
r
k
-
b
ased
as
w
ell
as
ANFI
S
b
as
ed
s
o
lu
tio
n
o
f
i
n
v
er
s
e
k
i
n
e
m
atics
p
r
o
b
lem
.
T
h
e
r
esu
lt
o
f
ea
ch
tech
n
iq
u
e
i
s
ev
alu
a
ted
b
y
u
s
in
g
i
n
v
er
s
e
k
i
n
e
m
a
tics
eq
u
a
tio
n
s
to
o
b
tain
in
f
o
r
m
atio
n
ab
o
u
t
t
h
eir
er
r
o
r
.
I
n
o
th
er
w
o
r
d
s
,
t
h
e
an
g
le
s
o
b
tain
ed
f
o
r
ea
ch
j
o
in
t
ar
e
u
s
ed
to
co
m
p
u
te
th
e
C
ar
te
s
ian
co
o
r
d
in
ate
f
o
r
en
d
e
f
f
ec
to
r
.
T
h
e
tr
ain
in
g
d
ata
f
o
r
A
NN
a
n
d
A
NFI
S
h
a
v
e
b
ee
n
s
e
lecte
d
v
er
y
p
r
ec
is
e
l
y
.
E
s
p
ec
iall
y
,
u
n
le
ar
n
ed
d
ata
in
ea
ch
n
eu
r
al
n
et
w
o
r
k
a
n
d
ANFI
S h
a
v
e
b
ee
n
ch
o
s
en
,
a
n
d
u
s
ed
to
o
b
tain
th
e
tr
ain
i
n
g
s
et
o
f
th
e
la
s
t
n
et
w
o
r
k
.
2.
K
I
NE
M
AT
I
C
M
O
DE
L
I
N
G
O
F
5R
M
ANIPULAT
O
R
T
h
e
Den
av
it
-
Har
te
n
b
er
g
(
D
-
H)
n
o
tatio
n
an
d
m
eth
o
d
o
lo
g
y
ar
e
u
s
ed
in
t
h
i
s
s
ec
tio
n
to
d
er
iv
e
th
e
k
in
e
m
at
ics
o
f
r
o
b
o
t
m
an
ip
u
l
ato
r
.
T
h
e
Den
av
it/
Har
ten
b
er
g
(
o
r
D
-
H)
tech
n
iq
u
e
h
as
b
e
co
m
e
t
h
e
s
ta
n
d
ar
d
m
et
h
o
d
in
r
o
b
o
tics
f
o
r
d
escr
ib
in
g
th
e
f
o
r
w
ar
d
k
in
e
m
atic
s
o
f
a
m
an
ip
u
lato
r
.
E
s
s
e
n
tiall
y
,
b
y
ca
r
ef
u
l
p
lace
m
en
t
o
f
a
s
er
ies
o
f
co
o
r
d
in
ate
f
r
a
m
es
f
i
x
ed
in
ea
c
h
li
n
k
,
th
e
D
-
H
tec
h
n
iq
u
e
r
ed
u
ce
s
th
e
f
o
r
w
ar
d
k
in
e
m
at
ics
p
r
o
b
lem
to
th
at
o
f
co
m
b
i
n
in
g
a
s
er
ies
o
f
s
tr
aig
h
t
f
o
r
w
ar
d
co
n
s
ec
u
tiv
e
li
n
k
-
to
-
li
n
k
tr
an
s
f
o
r
m
at
io
n
s
f
r
o
m
th
e
b
ase
to
th
e
e
n
d
ef
f
ec
to
r
f
r
a
m
e.
Usi
n
g
t
h
i
s
m
e
th
o
d
,
th
e
f
o
r
w
a
r
d
k
in
e
m
atics
f
o
r
an
y
m
a
n
ip
u
l
ato
r
is
s
u
m
m
ar
ized
in
a
tab
le
o
f
p
ar
am
eter
s
(
t
h
e
D
-
H
p
ar
a
m
eter
s
)
.
T
h
e
co
o
r
d
in
ate
f
r
a
m
e
as
s
i
g
n
m
e
n
t
an
d
th
e
DH
p
ar
am
eter
s
ar
e
d
ep
icted
in
Fig
u
r
e
1
an
d
lis
te
d
in
T
a
b
le
1
r
esp
ec
tiv
el
y
,
w
h
e
r
e
to
r
ep
r
esen
ts
th
e
lo
ca
l
c
o
o
r
d
in
ate
f
r
a
m
es
at
th
e
f
i
v
e
j
o
in
ts
r
esp
ec
ti
v
el
y
,
r
ep
r
es
en
ts
t
h
e
lo
ca
l
co
o
r
d
in
ate
f
r
a
m
e
at
th
e
e
n
d
-
e
f
f
ec
to
r
,
w
h
er
e
θi
r
ep
r
esen
ts
r
o
tatio
n
ab
o
u
t
th
e
Z
-
a
x
is
,
α
i
r
o
tatio
n
a
b
o
u
t
th
e
X
-
a
x
i
s
,
tr
an
s
itio
n
alo
n
g
t
h
e
Z
-
a
x
i
s
,
an
d
tr
an
s
itio
n
a
lo
n
g
t
h
e
X
-
a
x
i
s
[
1
]
,
[
3
]
.
T
ab
le
1
.
T
h
e
D
-
H
P
ar
am
eter
s
T
h
e
tr
an
s
f
o
r
m
a
tio
n
m
atr
ix
Ai
b
et
w
ee
n
t
w
o
n
ei
g
h
b
o
u
r
i
n
g
f
r
a
m
es Oi−
1
a
n
d
Oi
is
ex
p
r
es
s
ed
in
eq
u
atio
n
(
1
)
as,
))
(
(
)
(
'
t
x
f
t
F
r
a
me
i
(
d
e
g
r
e
e
)
i
d
(
mm
)
i
a
(
mm
)
i
(
d
e
g
r
e
e
)
O
0
-
O
1
θ
1
d
1
=
1
5
0
a
1
=
6
0
-
90
O
1
–
O
2
θ
2
0
a
2
=
1
4
5
0
O
2
–
O
3
-
9
0
+
θ
3
0
0
-
90
O
3
–
O
4
θ
4
d
2
=
1
2
5
0
90
O
4
–
O
5
θ
5
0
0
-
90
O
5
–
O
6
0
d
3
=
1
3
0
0
0
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
RA
I
SS
N:
2089
-
4856
I
n
ve
r
s
e
K
in
ema
tic
S
o
lu
tio
n
o
f
5
R
Ma
n
ip
u
l
a
to
r
Usi
n
g
A
N
N
a
n
d
A
N
F
I
S
(
P
a
n
c
h
a
n
a
n
d
J
h
a
)
111
Fig
u
r
e
1
.
D
-
H
f
r
a
m
es o
f
th
e
S
C
A
R
A
r
o
b
o
t.
A
i
=
1
0
0
0
c
o
s
s
i
n
0
s
i
n
s
i
n
c
o
s
c
o
s
c
o
s
s
i
n
c
o
s
s
i
n
s
i
n
c
o
s
s
i
n
c
o
s
i
i
i
i
i
i
i
i
i
i
i
i
i
i
i
i
i
d
a
a
(3
)
B
y
s
u
b
s
tit
u
ti
n
g
t
h
e
D
-
H
p
ar
a
m
eter
s
in
T
ab
le
1
in
to
eq
u
atio
n
(
3
)
,
th
e
in
d
i
v
id
u
a
l
tr
a
n
s
f
o
r
m
a
tio
n
m
atr
ices
A
1
to
A
4
ca
n
b
e
o
b
t
ain
ed
an
d
t
h
e
g
e
n
er
al
tr
an
s
f
o
r
m
atio
n
m
atr
ix
f
r
o
m
t
h
e
f
ir
s
t
j
o
in
t
to
t
h
e
la
s
t
j
o
in
t
o
f
th
e
m
an
ip
u
lato
r
ca
n
b
e
d
er
iv
ed
b
y
m
u
ltip
l
y
i
n
g
all
t
h
e
i
n
d
i
v
id
u
al
tr
a
n
s
f
o
r
m
atio
n
m
a
tr
ices
(
0
T
4
)
.
1
0
0
0
4
3
2
1
4
0
z
z
z
z
y
y
y
y
x
x
x
x
p
a
o
n
p
a
o
n
p
a
o
n
A
A
A
A
T
(4
)
W
h
er
e
)
p
,
p
,
p
(
z
y
x
r
ep
r
esen
ts
th
e
p
o
s
it
io
n
an
d
)
,
,
(
),
,
,
(
),
,
,
(
z
y
x
z
y
x
z
y
x
a
a
a
and
o
o
o
n
n
n
r
epr
es
ent
s
th
e
o
r
ien
tatio
n
o
f
th
e
en
d
-
ef
f
ec
to
r
.
T
h
e
o
r
ien
t
atio
n
a
n
d
p
o
s
itio
n
o
f
th
e
en
d
-
ef
f
ec
to
r
ca
n
b
e
ca
lcu
lated
in
ter
m
s
o
f
j
o
in
t
an
g
les
a
n
d
th
e
D
-
H
p
ar
a
m
eter
s
o
f
th
e
m
an
ip
u
lato
r
ar
e
s
h
o
w
n
in
f
o
llo
w
i
n
g
m
atr
i
x
as:
1
0
0
0
1
2
2
23
2
5
23
3
5
4
23
3
5
23
5
4
23
4
23
5
23
5
4
23
1
1
2
1
2
23
1
2
5
23
1
3
5
4
1
3
5
4
23
1
3
5
23
1
5
4
1
5
4
23
1
4
1
4
23
1
5
23
1
5
4
1
5
4
23
1
1
1
2
1
2
23
1
2
5
23
1
3
5
4
1
3
5
4
23
1
3
5
23
1
5
4
1
5
4
23
1
4
1
4
23
1
5
23
1
5
4
1
4
23
1
5
d
s
a
s
d
c
s
d
s
c
c
d
c
s
s
c
c
s
c
s
s
c
c
c
s
a
c
s
a
c
s
d
c
c
s
d
s
s
c
d
s
c
s
s
d
c
c
s
s
s
c
s
c
s
s
c
c
s
s
s
s
c
s
c
s
c
c
c
s
s
c
a
c
c
a
c
c
d
c
c
c
d
s
s
s
d
s
c
s
c
d
c
c
c
s
s
s
s
c
s
c
c
s
s
s
c
s
c
c
c
s
s
c
c
s
c
(
5
)
w
h
er
e,
)
s
i
n
(
)
c
o
s
(
),
s
i
n
(
),
c
o
s
(
3
2
23
3
2
23
s
and
c
s
c
i
i
i
i
B
y
eq
u
a
lizi
n
g
t
h
e
m
atr
ices i
n
eq
u
atio
n
(
4
)
an
d
(
5
)
,
th
e
f
o
llo
w
i
n
g
eq
u
atio
n
s
ar
e
d
er
iv
ed
1
1
2
1
2
23
1
2
5
23
1
3
5
4
1
3
5
4
23
1
3
c
a
c
c
a
c
c
d
c
c
c
d
s
s
s
d
s
c
s
c
d
p
x
(
6
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4856
IJ
RA
Vo
l.
4
,
No
.
2
,
J
u
n
e
2
0
1
5
:
1
0
9
–
12
3
112
1
1
2
1
2
23
1
2
5
23
1
3
5
4
1
3
5
4
23
1
3
s
a
c
s
a
c
s
d
c
c
s
d
s
s
c
d
s
c
s
s
d
p
y
(
7
)
1
2
2
23
2
5
23
2
5
23
3
5
4
23
3
d
s
a
s
d
c
s
d
c
s
d
s
c
c
d
p
z
(
8
)
5
23
1
5
4
1
5
4
23
1
s
c
c
c
s
s
c
c
s
c
n
x
(
9
)
5
23
1
5
4
1
5
4
23
1
y
s
c
s
c
s
c
c
c
s
s
n
(
1
0
)
5
23
5
4
23
z
s
s
c
c
c
n
(
1
1
)
4
1
4
23
1
x
c
s
s
s
c
o
(
1
2
)
4
1
4
23
1
y
c
c
s
s
s
o
(
1
3
)
4
23
z
s
c
o
(
1
4
)
5
23
1
5
4
1
5
4
23
1
x
c
c
c
c
s
s
s
c
s
c
a
(
1
5
)
5
23
1
5
4
1
5
4
23
1
y
c
c
s
s
s
c
s
c
s
s
a
(
1
6
)
5
23
5
4
23
z
c
s
s
c
c
a
(
1
7
)
Fro
m
eq
u
at
io
n
s
(
6
)
th
r
o
u
g
h
(
1
7
)
,
th
e
p
o
s
itio
n
a
n
d
o
r
ien
tatio
n
o
f
th
e
ar
m
e
n
d
-
e
f
f
ec
to
r
ca
n
b
e
ca
lcu
lated
an
d
p
r
o
v
id
e
all
t
h
e
j
o
in
t a
n
g
le
s
.
T
h
is
g
iv
e
s
s
o
l
u
tio
n
to
th
e
f
o
r
w
ar
d
k
i
n
e
m
a
tic
p
r
o
b
le
m
.
I
t is o
b
v
io
u
s
th
at
t
h
e
in
v
er
s
e
k
in
e
m
atic
s
s
o
l
u
tio
n
i
s
d
if
f
ic
u
lt
to
o
b
tain
.
T
h
is
w
o
r
k
u
s
e
s
v
ar
io
u
s
tr
ick
y
s
tr
a
teg
ies
to
s
o
l
v
e
th
e
in
v
er
s
e
k
i
n
e
m
atic
s
o
f
th
e
r
o
b
o
t
m
an
ip
u
lato
r
.
Fro
m
eq
u
atio
n
s
(
6
)
an
d
(
1
5
)
,
th
e
f
o
llo
w
i
n
g
eq
u
atio
n
i
s
d
er
iv
ed
:
)
(
1
2
2
23
2
1
3
a
c
a
c
d
c
a
d
p
x
x
(
1
8
)
Si
m
i
lar
l
y
b
y
m
a
n
ip
u
lat
in
g
i
n
s
i
m
ilar
w
a
y
f
r
o
m
(
7
)
an
d
(
1
6
)
,
th
e
f
o
llo
w
i
n
g
eq
u
atio
n
is
d
er
iv
ed
as:
)
(
1
2
2
23
2
1
3
a
c
a
c
d
s
a
d
p
y
y
(
1
9
)
I
t
ca
n
b
e
n
o
ted
t
h
at
t
h
e
v
al
u
e
s
o
f
2
an
d
3
in
r
o
b
o
t
m
a
n
ip
u
la
to
r
o
n
l
y
ta
k
es
in
te
g
r
al
v
al
u
es
in
a
li
m
ited
r
an
g
e.
B
y
ch
ec
k
i
n
g
al
l
p
o
s
s
ib
le
j
o
in
t
an
g
les
2
an
d
3
th
at
0
)
(
1
2
2
23
2
a
c
a
c
d
h
o
ld
s
g
o
o
d
,
w
h
ic
h
m
ea
n
s
t
h
at
x
x
a
d
p
3
an
d
y
y
a
d
p
3
w
ill
n
o
t
eq
u
als
to
ze
r
o
at
s
a
m
e
ti
m
e.
I
f
0
)
(
1
2
2
23
2
a
c
a
c
d
,
th
e
s
o
l
u
tio
n
f
o
r
1
is
,
)
,
(
2
t
a
n
3
3
1
x
x
y
y
a
d
p
a
d
p
a
(
2
0
)
Oth
er
w
i
s
e,
)
,
(
2
t
a
n
3
3
1
x
x
y
y
p
a
d
p
a
d
a
(
2
1
)
Fo
r
d
er
iv
in
g
s
o
lu
tio
n
s
f
o
r
2
an
d
3
,
(
1
8
)
an
d
(
1
9
)
ca
n
b
e
r
e
p
r
ese
n
ted
as f
o
llo
w
s
:
1
1
3
2
2
23
2
/
)
(
a
c
a
d
p
c
a
c
d
x
x
(
2
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
RA
I
SS
N:
2089
-
4856
I
n
ve
r
s
e
K
in
ema
tic
S
o
lu
tio
n
o
f
5
R
Ma
n
ip
u
l
a
to
r
Usi
n
g
A
N
N
a
n
d
A
N
F
I
S
(
P
a
n
c
h
a
n
a
n
d
J
h
a
)
113
1
1
3
2
2
23
2
/
)
(
a
s
a
d
p
c
a
c
d
y
y
(
2
3
)
Fro
m
(
8
)
an
d
(
1
7
)
,
th
e
f
o
llo
w
i
n
g
eq
u
atio
n
ca
n
b
e
d
er
iv
ed
:
1
2
2
23
2
3
d
s
a
s
d
a
d
p
z
z
(
2
4
)
No
w
co
n
s
id
er
in
g
(
2
2
)
an
d
(
2
4
)
,
L
et
1
1
3
/
)
(
a
c
a
d
p
r
x
x
(
2
5
)
An
d
1
2
2
23
2
d
s
a
s
d
r
z
(
2
6
)
No
w
s
q
u
ar
in
g
t
h
e
eq
u
atio
n
s
(
2
5
)
an
d
(
2
6
)
f
o
llo
w
ed
b
y
ad
d
in
g
it,
eq
u
atio
n
(
2
7
)
ca
n
b
e
d
er
iv
ed
as
f
o
llo
w
:
2
2
2
23
2
23
2
2
2
2
2
)
(
2
z
r
r
a
s
s
c
c
d
a
d
(
2
7
)
So
lv
i
n
g
t
h
e
ter
m
s
23
2
23
2
s
s
c
c
in
th
e
ab
o
v
e
eq
u
atio
n
(
2
7
)
,
w
e
g
et
)
c
o
s
(
)
c
o
s
(
)
c
o
s
(
c
o
s
)
(
3
3
3
3
23
2
23
2
s
s
c
c
T
h
er
ef
o
r
e,
th
er
e
ar
e
s
ev
er
al
p
o
s
s
ib
le
s
o
l
u
tio
n
s
f
o
r
3
,
w
h
ic
h
ar
e
as f
o
llo
w
s
:
2
2
2
2
2
2
2
2
3
2
a
c
o
s
±
=
d
a
d
a
r
a
z
(
2
8
)
Or
,
2
2
2
2
2
2
2
2
3
2
c
o
s
d
a
r
r
d
a
a
z
(
2
9
)
No
w
co
n
s
id
er
th
e
p
o
s
s
ib
le
s
o
l
u
tio
n
s
f
o
r
2
.
Fo
r
th
e
s
ak
e
o
f
co
n
v
en
ie
n
ce
,
eq
u
atio
n
(
2
4
)
ca
n
b
e
r
e
w
r
itte
n
as e
q
u
at
io
n
(
3
0
)
,
2
2
1
23
2
s
a
B
s
d
(
3
0
)
w
h
er
e,
1
1
2
B
d
p
a
d
z
z
C
o
n
s
id
er
in
g
t
h
e
eq
u
at
io
n
s
(
2
2
)
an
d
(
2
3
)
,
eq
u
atio
n
(
3
1
)
is
d
er
iv
ed
as,
2
3
2
3
2
2
23
2
)
(
)
(
=
c
a
+
c
d
y
y
x
x
p
d
a
p
d
a
(
3
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4856
IJ
RA
Vo
l.
4
,
No
.
2
,
J
u
n
e
2
0
1
5
:
1
0
9
–
12
3
114
L
et
2
3
2
3
2
)
(
)
(
=
B
y
y
x
x
p
d
a
p
d
a
,
s
o
e
q
u
atio
n
(
3
1
)
ca
n
b
e
r
e
w
r
itte
n
as,
2
2
2
23
2
c
a
B
c
d
(
3
2
)
R
ea
r
r
an
g
in
g
eq
u
atio
n
(
2
8
)
,
(
3
0
)
an
d
s
o
lv
in
g
f
o
r
2
1
B
,
B
.
E
q
u
atio
n
(
3
1
)
,
(
3
2
)
is
d
er
iv
ed
as:
2
3
2
2
2
3
2
1
c
)
s
(d
+
s
)
a
+
c
(d
=
B
(
3
3
)
2
3
2
2
2
3
2
2
s
)
s
(d
-
c
)
a
+
c
(d
=
B
(
3
4
)
Div
i
n
g
b
o
th
s
id
e
o
f
(
3
3
)
an
d
(
3
4
)
,
b
y
2
2
2
1
B
B
,
eq
u
atio
n
(
3
5
)
an
d
(
3
6
)
is
d
er
iv
ed
as,
2
2
2
1
1
2
2
B
B
B
=
c
o
s
*
si
n
+
si
n
*
c
o
s
(
3
5
)
2
2
2
1
2
2
2
B
B
B
=
c
o
s
*
si
n
-
si
n
*
c
o
s
(
3
6
)
w
h
er
e,
2
2
2
1
2
3
2
)
(
=
c
o
s
B
B
a
c
d
an
d
2
2
2
1
3
2
)
(
=
s
i
n
B
B
s
d
T
h
e
eq
u
atio
n
(
3
4
)
an
d
(
3
5
)
a
r
e
r
e
w
r
itte
n
as,
2
2
2
1
1
2
B
B
B
=
)
+
s
i
n
(
(
3
7
)
An
d
,
2
2
2
1
2
2
B
B
B
=
)
+
c
o
s
(
(
3
8
)
T
h
er
ef
o
r
e,
m
2
)
B
,
B
(
2
t
a
n
a
2
1
2
an
d
2
2
2
1
2
3
2
)
(
a
c
o
s
±
=
B
B
a
c
d
,
W
h
er
e
m
=
-
1
,
0
o
r
1
.
I
t
is
clea
r
th
at
co
u
ld
b
e
in
,
0
o
r
0
,
.
T
h
e
r
a
n
g
e
o
f
w
ill d
ep
en
d
o
n
th
e
r
an
g
e
o
f
3
.
T
h
er
ef
o
r
e,
if
3
0
,
th
en
0
s
3
an
d
0
)
s
i
n
(
,
th
u
s
0
.
T
h
en
2
ca
n
b
e
d
er
iv
ed
as:
2m
+
)
(
c
o
s
-
)
B
,
a
t
a
n
2
(
B
=
2
2
2
1
2
3
2
2
1
2
B
B
a
c
d
a
(
3
9
)
Oth
er
w
i
s
e,
if
0
3
,
th
en
0
s
3
an
d
0
)
s
i
n
(
,
th
u
s
0
.
T
h
en
th
e
n
ex
t p
o
s
s
ib
le
s
o
lu
tio
n
f
o
r
2
is
as:
2m
+
)
(
c
o
s
+
)
B
,
a
t
a
n
2
(
B
=
2
2
2
1
2
3
2
2
1
2
B
B
a
c
d
a
(
4
0
)
No
w
t
h
at
3
2
1
a
n
d
,
ar
e
k
n
o
w
n
,
th
e
s
o
lu
tio
n
s
f
o
r
4
an
d
5
ca
n
b
e
f
o
u
n
d
b
y
u
s
in
g
t
h
e
r
e
m
ain
in
g
f
o
r
w
ar
d
k
i
n
e
m
atics
eq
u
atio
n
s
.
C
o
n
s
id
er
i
n
g
eq
u
a
ti
o
n
(
1
4
)
,
th
e
v
alu
e
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
RA
I
SS
N:
2089
-
4856
I
n
ve
r
s
e
K
in
ema
tic
S
o
lu
tio
n
o
f
5
R
Ma
n
ip
u
l
a
to
r
Usi
n
g
A
N
N
a
n
d
A
N
F
I
S
(
P
a
n
c
h
a
n
a
n
d
J
h
a
)
115
23
z
4
c
o
=
s
,
w
h
e
n
0
c
23
(
4
1
)
Si
m
i
lar
l
y
f
r
o
m
eq
u
at
io
n
(
1
2
)
a
n
d
(
1
3
)
,
th
e
p
o
s
s
ib
le
s
o
lu
tio
n
f
o
r
4
c
is
d
er
iv
ed
as:
1
23
z
23
1
x
4
s
)
c
/
o
s
c
o
(
c
(
4
2
)
An
d
ag
ai
n
1
23
z
23
1
y
4
c
)
c
/
o
s
s
o
(
c
(
4
3
)
Usi
n
g
eq
u
at
io
n
(
4
2
)
an
d
(
4
3
)
f
o
r
s
m
all
v
al
u
e
o
f
1
c
,
th
e
s
o
lu
tio
n
f
o
r
4
is
1
23
z
23
1
z
23
z
4
s
)
c
/
o
s
c
o
(
,
c
o
2
t
a
n
a
(
4
4
)
Oth
er
w
i
s
e
f
o
r
s
m
all
1
s
,
1
23
z
23
1
y
23
z
4
c
)
c
/
o
s
s
o
(
,
c
o
2
t
a
n
a
(
4
5
)
No
w
f
o
r
s
o
lu
tio
n
o
f
5
,
co
n
s
id
er
in
g
eq
u
atio
n
(
1
1
)
,
th
e
v
al
u
e
o
f
4
23
5
23
z
5
c
c
s
s
n
c
(
4
6
)
Si
m
i
lar
l
y
t
h
e
v
a
lu
e
o
f
5
s
is
d
er
iv
ed
b
y
u
s
in
g
eq
u
atio
n
(
1
7
)
i.e
.
,
4
23
5
23
z
5
c
c
c
s
a
s
(
4
7
)
Usi
n
g
eq
u
at
io
n
(
4
3
)
in
(
4
2
)
an
d
v
ice
v
er
s
a,
th
e
ter
m
5
c
an
d
5
s
is
r
e
w
r
itte
n
as:
2
23
2
4
2
23
z
23
4
23
z
5
s
c
c
a
s
c
c
n
c
A
n
d
2
23
2
4
2
23
z
23
4
23
z
5
s
c
c
)
n
s
c
c
a
(
s
No
w
u
s
i
n
g
t
h
i
s
ab
o
v
e
d
er
iv
ati
o
n
o
f
5
c
an
d
5
s
,
5
is
d
er
iv
ed
as f
o
ll
o
w
s
:
z
23
4
23
z
z
23
4
23
z
5
a
s
c
c
n
,
n
s
c
c
a
2
t
a
n
a
(
4
8
)
I
t
is
o
b
v
io
u
s
f
r
o
m
t
h
e
g
i
v
e
n
e
q
u
atio
n
s
f
r
o
m
(
3
)
th
r
o
u
g
h
(
4
8
)
th
at
th
er
e
ex
is
t
m
u
ltip
le
s
o
l
u
tio
n
s
to
th
e
in
v
er
s
e
k
i
n
e
m
at
ics
p
r
o
b
le
m
.
T
h
e
ab
o
v
e
d
er
iv
atio
n
s
w
it
h
v
a
r
io
u
s
co
n
d
it
io
n
s
b
ein
g
ta
k
e
n
i
n
to
ac
co
u
n
t
p
r
o
v
id
e
a
co
m
p
lete
an
al
y
tica
l
s
o
lu
tio
n
to
in
v
er
s
e
k
i
n
e
m
atics
o
f
ar
m
.
I
t
is
n
o
ted
th
at
th
er
e
ex
i
s
t
t
wo
p
o
s
s
ib
le
s
o
lu
tio
n
s
f
o
r
5
4
3
2
1
,
,
,
and
d
ep
icted
in
(
2
0
)
o
r
(
2
1
)
,
(
3
9
)
o
r
(
4
0
)
,
(
2
8
)
o
r
(
2
9
)
,
(
4
4
)
o
r
(
4
5
)
r
esp
ec
tiv
el
y
.
So
t
o
k
n
o
w
w
h
ic
h
s
o
l
u
tio
n
h
o
ld
s
g
o
o
d
to
s
tu
d
y
t
h
e
i
n
v
er
s
e
k
i
n
e
m
atics,
all
j
o
in
ts
a
n
g
les
ar
e
o
b
tain
ed
an
d
co
m
p
ar
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4856
IJ
RA
Vo
l.
4
,
No
.
2
,
J
u
n
e
2
0
1
5
:
1
0
9
–
12
3
116
u
s
i
n
g
f
o
r
w
ar
d
k
in
e
m
atic
s
s
o
lu
tio
n
.
T
h
is
p
r
o
ce
s
s
is
b
ee
n
ap
p
lied
f
o
r
5
4
3
2
1
,
,
,
and
.
T
o
ch
o
o
s
e
th
e
co
r
r
ec
t
s
o
lu
tio
n
,
all
th
e
f
o
u
r
s
ets
o
f
p
o
s
s
ib
le
s
o
lu
t
io
n
s
(
j
o
in
t
an
g
le
s
)
ca
lcu
lated
,
w
h
ic
h
g
en
er
ate
f
o
u
r
p
o
s
s
ib
le
co
r
r
esp
o
n
d
in
g
p
o
s
itio
n
s
a
n
d
o
r
ien
tatio
n
s
u
s
i
n
g
th
e
f
o
r
w
ar
d
k
in
e
m
atics.
B
y
co
m
p
ar
in
g
th
e
er
r
o
r
s
b
etw
ee
n
th
ese
f
o
u
r
g
en
er
ated
p
o
s
itio
n
s
an
d
o
r
ien
tatio
n
s
an
d
t
h
e
g
i
v
e
n
p
o
s
itio
n
a
n
d
o
r
ien
tatio
n
,
o
n
e
s
et
o
f
j
o
in
t
an
g
les,
w
h
ic
h
p
r
o
d
u
ce
s
th
e
m
i
n
i
m
u
m
er
r
o
r
,
is
ch
o
s
en
as
th
e
co
r
r
ec
t
s
o
lu
tio
n
.
T
h
e
s
o
lu
tio
n
s
(
2
1
)
,
(
3
9
)
,
(
2
8
)
,
(
4
5
)
an
d
(
4
8
)
h
o
ld
s
co
r
r
ec
t f
o
r
o
b
tain
in
g
th
e
v
al
u
es o
f
5
4
3
2
1
,
,
,
and
r
esp
ec
tiv
el
y
.
3.
ARCH
I
T
E
C
T
UR
E
S O
F
AN
N
AND
ANF
I
S
3
.
1
Arc
hite
ct
ure
o
f
M
L
P
NN
I
t
is
w
ell
k
n
o
w
n
t
h
at
n
e
u
r
al
n
et
w
o
r
k
s
h
a
v
e
th
e
b
etter
ab
ilit
y
th
a
n
o
th
er
tech
n
iq
u
e
s
to
s
o
lv
e
v
ar
io
u
s
co
m
p
le
x
p
r
o
b
le
m
s
.
I
n
v
er
s
e
k
i
n
e
m
a
tics
is
a
tr
an
s
f
o
r
m
a
tio
n
o
f
a
w
o
r
ld
co
o
r
d
in
ate
f
r
a
m
e
(
P
x
,
P
y
,
an
d
P
z
)
to
a
lin
k
co
o
r
d
in
ate
f
r
a
m
e
(
5
4
3
2
1
,
,
,
and
)
.
T
h
is
tr
an
s
f
o
r
m
atio
n
ca
n
b
e
p
er
f
o
r
m
ed
o
n
i
n
p
u
t/o
u
tp
u
t
w
o
r
k
th
at
u
s
e
s
a
n
u
n
k
n
o
w
n
tr
an
s
f
e
r
f
u
n
ctio
n
.
M
L
P
n
e
u
r
al
n
et
w
o
r
k
's
n
eu
r
o
n
is
a
s
i
m
p
le
w
o
r
k
ele
m
e
n
t,
a
n
d
h
a
s
a
lo
ca
l
m
e
m
o
r
y
.
A
n
e
u
r
o
n
tak
e
s
a
m
u
lti
-
d
i
m
en
s
io
n
al
i
n
p
u
t,
an
d
th
en
d
eliv
er
s
it
to
th
e
o
th
er
n
eu
r
o
n
s
ac
co
r
d
in
g
to
th
eir
w
ei
g
h
ts
.
T
h
is
g
iv
e
s
a
s
ca
lar
r
esu
lt
at
t
h
e
o
u
tp
u
t
o
f
a
n
e
u
r
o
n
.
T
h
e
tr
an
s
f
er
f
u
n
ct
io
n
o
f
a
n
M
L
P
,
ac
tin
g
o
n
t
h
e
lo
ca
l
m
e
m
o
r
y
,
u
s
e
s
a
lear
n
in
g
r
u
le
to
p
r
o
d
u
ce
a
r
el
atio
n
s
h
ip
b
et
w
ee
n
t
h
e
i
n
p
u
t
a
n
d
o
u
tp
u
t.
Fo
r
t
h
e
ac
tiv
atio
n
in
p
u
t,
a
ti
m
e
f
u
n
ct
i
o
n
is
n
ee
d
ed
[
4
]
,
[
1
7
]
.
Fig
u
r
e
2
.
Mu
lti
-
la
y
er
ed
p
er
ce
p
tr
o
n
n
eu
r
al
n
et
w
o
r
k
s
tr
u
ct
u
r
e
W
e
p
r
o
p
o
s
e
th
e
s
o
lu
tio
n
u
s
i
n
g
a
m
u
l
ti
-
la
y
er
ed
p
er
ce
p
tr
o
n
w
it
h
b
ac
k
-
p
r
o
p
ag
atio
n
al
g
o
r
ith
m
f
o
r
tr
ain
i
n
g
.
T
h
e
n
et
w
o
r
k
i
s
t
h
en
tr
ain
ed
w
it
h
d
ata
f
o
r
a
n
u
m
b
e
r
o
f
e
n
d
e
f
f
ec
to
r
p
o
s
itio
n
s
ex
p
r
ess
ed
i
n
C
ar
tesi
a
n
co
-
o
r
d
in
ates
a
n
d
t
h
e
co
r
r
esp
o
n
d
in
g
j
o
in
t
a
n
g
les.
T
h
e
d
ata
c
o
n
s
is
t
o
f
t
h
e
d
if
f
er
e
n
t
co
n
f
i
g
u
r
atio
n
s
a
v
ailab
le
f
o
r
th
e
ar
m
.
A
b
lo
ck
d
ia
g
r
a
m
o
f
th
e
s
tr
u
ct
u
r
e
is
s
h
o
w
n
i
n
Fig
u
r
e
2
.
T
h
e
s
i
g
n
a
ls
,
O
jn
,
ar
e
p
r
ese
n
ted
to
a
h
id
d
en
la
y
er
n
e
u
r
o
n
in
t
h
e
n
et
w
o
r
k
v
i
a
th
e
in
p
u
t
n
e
u
r
o
n
s
.
E
ac
h
o
f
t
h
e
s
i
g
n
a
ls
f
r
o
m
th
e
i
n
p
u
t
n
e
u
r
o
n
s
is
m
u
ltip
lied
b
y
th
e
v
al
u
e
o
f
t
h
e
w
ei
g
h
ts
o
f
t
h
e
co
n
n
ec
tio
n
,
w
j
,
b
et
w
ee
n
th
e
r
esp
ec
tiv
e
i
n
p
u
t
n
eu
r
o
n
s
an
d
t
h
e
h
id
d
en
n
e
u
r
o
n
.
T
h
e
n
et
w
o
r
k
u
s
e
s
a
lear
n
i
n
g
m
o
d
e,
i
n
w
h
ic
h
a
n
i
n
p
u
t
is
p
r
esen
ted
to
t
h
e
n
et
w
o
r
k
a
lo
n
g
w
it
h
th
e
d
esire
d
o
u
tp
u
t
a
n
d
t
h
e
w
e
ig
h
ts
ar
e
ad
j
u
s
ted
s
o
t
h
at
th
e
n
et
w
o
r
k
a
tte
m
p
t
s
to
p
r
o
d
u
ce
th
e
d
esire
d
o
u
tp
u
t.
W
eig
h
t
s
af
ter
tr
ain
i
n
g
co
n
tai
n
m
ea
n
in
g
f
u
l
i
n
f
o
r
m
atio
n
w
h
er
ea
s
b
ef
o
r
e
tr
ain
i
n
g
t
h
e
y
ar
e
r
a
n
d
o
m
an
d
h
av
e
n
o
m
ea
n
in
g
.
Net
in
p
u
t o
f
h
id
d
en
n
e
u
r
o
n
s
(
f
o
r
k
in
p
u
ts
)
=
(
(
4
9
)
T
h
e
o
u
tp
u
t,
O
mj
o
f
a
h
id
d
en
n
eu
r
o
n
as
a
f
u
n
c
tio
n
o
f
its
n
et
in
p
u
t
is
d
escr
ib
ed
in
eq
u
atio
n
(
4
9
)
.
T
h
e
s
ig
m
o
id
f
u
n
ctio
n
i
s
:
1
1
h
mj
n
O
u
tp
u
t
o
e
(
(
5
0
)
1
k
h
j
jn
j
n
w
o
Out
pu
t
s
Out
pu
t
l
a
y
e
r
B
i
a
s
H
i
dde
n
l
a
y
e
r
I
n
put
l
a
y
e
r
B
i
a
s
C
o
n
ne
c
t
i
o
n
s
we
i
g
h
t
I
n
put
s
X
Y
5
4
3
2
1
,
,
,
and
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
RA
I
SS
N:
2089
-
4856
I
n
ve
r
s
e
K
in
ema
tic
S
o
lu
tio
n
o
f
5
R
Ma
n
ip
u
l
a
to
r
Usi
n
g
A
N
N
a
n
d
A
N
F
I
S
(
P
a
n
c
h
a
n
a
n
d
J
h
a
)
117
On
ce
t
h
e
o
u
tp
u
ts
o
f
th
e
h
id
d
en
la
y
er
n
e
u
r
o
n
s
h
a
v
e
b
ee
n
ca
l
cu
lated
,
t
h
e
n
et
in
p
u
t to
ea
ch
o
u
tp
u
t
la
y
er
is
ca
lcu
la
ted
in
a
s
i
m
ilar
m
an
n
er
as in
eq
u
atio
n
(
5
0
).
'
(
)
(
)
m
n
d
o
f
(
(
5
1
)
(
1
)
(
)
m
m
m
o
o
d
o
(
(
1
3
)
W
h
er
e
d
is
th
e
tar
g
et
o
r
d
esir
ed
v
alu
e,
an
d
O
m
is
t
h
e
ac
tu
a
l
v
alu
e
f
r
o
m
o
u
tp
u
t
n
e
u
r
o
n
af
ter
g
o
in
g
th
r
o
u
g
h
t
h
e
f
ee
d
f
o
r
w
ar
d
ca
lcu
latio
n
.
T
h
e
er
r
o
r
ca
lcu
latio
n
w
a
s
i
m
p
le
m
e
n
ted
o
n
a
n
eu
r
o
n
-
by
-
n
eu
r
o
n
b
asi
s
o
v
er
th
e
e
n
tire
s
et
(
ep
o
ch
)
o
f
p
atter
n
s
.
T
h
is
er
r
o
r
v
al
u
e
δ
wa
s
u
s
ed
to
p
er
f
o
r
m
th
e
ap
p
r
o
p
r
iate
w
ei
g
h
t
ad
j
u
s
t
m
e
n
ts
o
f
t
h
e
w
ei
g
h
t c
o
n
n
ec
tio
n
b
et
w
ee
n
th
e
o
u
tp
u
t la
y
er
an
d
h
id
d
en
la
y
er
.
00
'
(
)
(
1
)
ll
kk
h
h
l
h
l
h
h
l
h
l
ll
f
n
w
o
o
w
(
(
5
2
)
W
h
er
e
δ
h
t
h
e
er
r
o
r
v
alu
e
o
f
t
h
e
h
id
d
en
la
y
er
i
s
,
δ
l
is
t
h
e
e
r
r
o
r
v
alu
e
o
f
t
h
e
o
u
tp
u
t
la
y
er
,
O
h
i
s
t
h
e
o
u
tp
u
t
o
f
t
h
e
s
ig
m
o
id
f
u
n
c
tio
n
an
d
W
lh
is
th
e
co
n
n
ec
tio
n
weig
h
ts
b
et
w
ee
n
t
h
e
o
u
tp
u
t
a
n
d
h
id
d
en
la
y
er
s
.
T
h
e
w
ei
g
h
t c
h
a
n
g
es
w
er
e
ca
lc
u
late
d
ac
co
r
d
in
g
to
eq
u
atio
n
(
5
2
).
)]
(
[
)
(
)
(
0
o
l
d
w
n
e
w
w
o
l
d
w
(
(
5
3
)
I
n
th
i
s
w
o
r
k
,
a
f
i
v
e
h
id
d
en
la
y
er
n
eu
r
al
n
et
w
o
r
k
w
it
h
th
r
ee
i
n
p
u
t
s
,
x
,
y
a
n
d
z,
an
d
f
i
v
e
o
u
t
p
u
ts
,
θ1
,
θ
2
,
θ
3
,
θ
4
,
an
d
θ
5
w
a
s
tr
ain
ed
u
s
in
g
t
h
e
b
ac
k
-
p
r
o
p
ag
atio
n
alg
o
r
ith
m
d
escr
ib
ed
ea
r
lier
,
a
lo
n
g
a
tr
aj
ec
to
r
y
o
f
th
e
en
d
-
ef
f
ec
to
r
in
t
h
e
x
y
-
p
la
n
e.
3
.
2
Arc
hite
ct
ure
o
f
ANF
I
S
T
h
e
A
N
FIS
ca
n
p
er
f
o
r
m
th
e
m
ap
p
in
g
r
elatio
n
b
et
w
ee
n
t
h
e
in
p
u
t
a
n
d
o
u
tp
u
t
d
ata
t
h
r
o
u
g
h
a
lear
n
i
n
g
alg
o
r
ith
m
to
o
p
ti
m
ize
th
e
p
ar
am
eter
s
o
f
a
g
i
v
e
n
FIS.
T
h
e
ANFI
S
ar
ch
itectu
r
e
co
n
s
i
s
ts
o
f
f
u
zz
y
la
y
er
,
p
r
o
d
u
ct
la
y
er
,
n
o
r
m
alize
d
la
y
er
,
d
e
-
f
u
zz
y
la
y
er
,
a
n
d
s
u
m
m
a
t
io
n
la
y
er
.
A
t
y
p
ical
ar
ch
i
tectu
r
e
o
f
A
N
FIS
i
s
s
h
o
w
n
i
n
Fig
.
3
,
in
w
h
ic
h
a
cir
cle
in
d
ic
ates
a
f
i
x
ed
n
o
d
e,
w
h
er
ea
s
a
s
q
u
ar
e
in
d
icate
s
a
n
ad
j
u
s
tab
le
n
o
d
e.
Fo
r
ex
a
m
p
le,
w
e
co
n
s
id
er
t
w
o
i
n
p
u
t
s
x
,
y
a
n
d
o
n
e
o
u
tp
u
t
z
i
n
t
h
e
FIS.
T
h
e
A
N
FIS
u
s
ed
in
th
is
p
ap
er
i
m
p
le
m
en
t
s
a
f
ir
s
t
-
o
r
d
er
Su
g
en
o
FIS.
Am
o
n
g
m
a
n
y
f
u
zz
y
s
y
s
te
m
s
,
t
h
e
S
u
g
en
o
f
u
zz
y
m
o
d
el
is
t
h
e
m
o
s
t
w
id
el
y
ap
p
lied
,
b
ec
au
s
e
o
f
its
h
ig
h
i
n
ter
p
r
etab
ilit
y
a
n
d
co
m
p
u
tatio
n
al
ef
f
icie
n
c
y
,
an
d
b
u
ilt
-
in
o
p
ti
m
al
an
d
ad
ap
tiv
e
t
ec
h
n
iq
u
es [
8
]
.
Fo
r
a
f
ir
s
t
-
o
r
d
er
Su
g
en
o
f
u
zz
y
s
y
s
te
m
,
t
h
e
t
y
p
ical
r
u
le
s
et
ca
n
b
e
ex
p
r
ess
ed
as:
R
u
le
1
: I
f
x
is
A
1
a
n
d
y
is
B
1
,
th
en
z1
=
p
1
x
+
q
1
y
+
r
1
R
u
le
2
: I
f
x
is
A
2
a
n
d
y
is
B
2
,
th
en
z2
=
p
2
x
+
q
2
y
+
r
2
w
h
er
e
A
i
a
n
d
B
i
ar
e
th
e
f
u
zz
y
s
ets
i
n
th
e
a
n
tece
d
en
t,
an
d
p
i,
q
i,
an
d
r
i
ar
e
th
e
p
a
r
am
e
te
r
s
th
at
ar
e
ass
i
g
n
ed
d
u
r
i
n
g
t
h
e
tr
ain
i
n
g
p
r
o
ce
d
u
r
e.
A
s
in
Fi
g
.
3
,
th
e
ANFI
S
co
n
s
i
s
ts
o
f
f
i
v
e
la
y
er
s
.
E
v
er
y
it
h
n
o
d
e
in
th
e
f
ir
s
t la
y
er
is
a
n
ad
ap
tiv
e
n
o
d
e
w
it
h
a
n
o
d
e
o
u
tp
u
t d
ef
i
n
ed
b
y
:
2
,
1
),
(
1
i
x
O
i
A
i
4
,
3
),
(
2
1
i
y
O
i
B
i
W
h
er
e
)
(
x
i
A
a
n
d
)
(
2
y
i
B
ca
n
ad
o
p
t
an
y
f
u
zz
y
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
(
MF)
.
I
n
t
h
i
s
p
ap
er
,
th
e
f
o
llo
w
in
g
Ga
u
s
s
ian
M
F is
u
s
e
d
:
2
2
2
)
(
)
,
,
(
s
c
x
e
s
c
x
g
a
u
s
s
m
f
W
h
er
e
{
c
i
,
s
i}
i
s
t
h
e
p
ar
a
m
et
er
s
et
th
a
t
ch
a
n
g
es
t
h
e
s
h
ap
es
o
f
th
e
MF.
T
h
e
p
ar
a
m
eter
s
o
f
th
is
la
y
er
ar
e
ter
m
ed
t
h
e
p
r
e
m
i
s
e
p
ar
a
m
eter
s
.
E
v
er
y
n
o
d
e
in
th
e
s
ec
o
n
d
la
y
er
is
a
f
i
x
ed
n
o
d
e
lab
elled
Π,
w
h
o
s
e
o
u
tp
u
t
is
th
e
p
r
o
d
u
ct
o
f
all
t
h
e
in
co
m
i
n
g
i
n
p
u
t
s
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4856
IJ
RA
Vo
l.
4
,
No
.
2
,
J
u
n
e
2
0
1
5
:
1
0
9
–
12
3
118
F
ig
u
re
3
.
A
rc
h
it
e
c
tu
re
o
f
A
NF
IS
2
,
1
),
(
)
(
2
i
y
x
O
i
i
B
A
i
i
E
ac
h
n
o
d
e
o
u
tp
u
t r
ep
r
esen
t
s
t
h
e
f
ir
i
n
g
s
tr
en
g
t
h
o
f
a
r
u
le.
E
v
er
y
n
o
d
e
in
t
h
e
t
h
ir
d
la
y
er
i
s
a
f
i
x
ed
n
o
d
e
lab
elled
N.
I
n
th
is
la
y
er
,
th
e
a
v
er
ag
e
is
ca
lc
u
l
ated
b
ased
o
n
w
e
ig
h
ts
ta
k
e
n
f
r
o
m
f
u
zz
y
r
u
les:
2
,
1
,
2
1
1
i
O
i
i
i
W
h
er
e
i
is
r
ef
er
r
ed
to
as
th
e
n
o
r
m
al
ized
f
ir
i
n
g
s
tr
en
g
th
s
.
E
v
er
y
i
th
n
o
d
e
in
th
e
f
o
u
r
t
h
la
y
e
r
is
an
ad
ap
tiv
e
n
o
d
e
w
it
h
t
h
e
f
o
llo
w
i
n
g
n
o
d
e
f
u
n
ctio
n
:
2
,
1
),
(
4
i
r
y
q
x
p
z
O
i
i
i
i
i
i
i
W
h
er
e
i
is
th
e
o
u
tp
u
t
o
f
la
y
er
3
,
an
d
{
p
i,
q
i,
ri
}
is
th
e
p
ar
am
eter
s
et.
T
h
e
p
ar
am
ete
r
s
o
f
th
i
s
la
y
er
ar
e
ter
m
ed
th
e
co
n
s
eq
u
en
t
p
ar
a
m
eter
s
.
T
h
e
s
in
g
le
n
o
d
e
in
th
e
f
if
t
h
la
y
er
is
a
f
ix
ed
n
o
d
e
lab
eled
Σ
th
at
co
m
p
u
tes t
h
e
o
v
er
all
o
u
tp
u
t a
s
th
e
s
u
m
m
at
io
n
o
f
all
i
n
co
m
in
g
in
p
u
ts
:
2
1
2
1
2
2
1
1
4
i
i
i
i
z
z
z
O
3
.
2
.
1
L
ea
rning
a
lg
o
rit
h
m
I
t
is
s
ee
n
f
r
o
m
t
h
e
A
N
FIS
ar
c
h
itect
u
r
e
th
a
t
w
h
en
th
e
v
al
u
es
o
f
th
e
p
r
e
m
is
e
p
ar
a
m
eter
s
ar
e
f
i
x
ed
,
th
e
o
u
tp
u
t o
f
t
h
e
A
NFI
S c
an
b
e
ca
lcu
lated
as:
2
2
1
2
1
2
1
1
z
z
z
Su
b
s
ti
tu
t
in
g
E
q
.
(
5
)
in
to
E
q
.
(
8
)
y
ield
s
:
2
2
1
1
z
z
z
Su
b
s
ti
tu
t
in
g
t
h
e
f
u
zz
y
i
f
-
t
h
en
r
u
les i
n
to
E
q
.
(
9
)
,
it
b
ec
o
m
es
:
)
(
)
(
2
2
2
2
1
1
1
1
r
q
x
p
r
y
q
x
p
z
Af
ter
r
ea
r
r
an
g
e
m
e
n
t,
th
e
o
u
tp
u
t c
an
b
e
w
r
itte
n
as a
li
n
ea
r
co
m
b
in
at
io
n
o
f
t
h
e
co
n
s
eq
u
en
t
p
ar
am
eter
s
:
2
2
2
2
2
2
1
1
1
1
1
1
)
(
)
(
)
(
)
(
)
(
)
(
r
q
y
p
x
r
q
y
p
x
z
Evaluation Warning : The document was created with Spire.PDF for Python.