I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2020
,
p
p
.
1
0
2
7
~
1
0
3
4
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
10
i
1
.
pp
1
0
2
7
-
1
0
3
4
1027
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
M
o
bile robo
t
co
nt
ro
ller using
nov
el
hybrid sy
ste
m
Ay
m
a
n A
bu
B
a
k
er
1
,
Ya
ze
ed
G
ha
di
2
1
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
A
p
p
li
e
d
S
c
ien
c
e
P
riv
a
te U
n
iv
e
rsity
,
Jo
rd
a
n
2
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
A
l
A
in
Un
iv
e
rsity
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
UA
E
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
2
9
,
2
0
1
9
R
ev
i
s
ed
Mar
2
4
,
2
0
1
9
A
cc
ep
ted
J
u
l 1
7
,
2
0
1
9
H
y
b
rid
n
e
u
ro
-
f
u
z
z
y
c
o
n
tro
ll
e
r
is
o
n
e
o
f
th
e
tec
h
n
iq
u
e
s
th
a
t
is
u
se
d
a
s
a
t
o
o
l
to
c
o
n
tr
o
l
a
m
o
b
il
e
ro
b
o
t
in
u
n
st
ru
c
tu
re
d
e
n
v
iro
n
m
e
n
t.
In
th
is
p
a
p
e
r
a
n
o
v
e
l
n
e
u
ro
-
f
u
z
z
y
t
e
c
h
n
iq
u
e
is
p
r
o
p
o
se
d
in
o
rd
e
r
to
tac
k
le
th
e
p
ro
b
lem
o
f
m
o
b
il
e
ro
b
o
t
a
u
to
n
o
m
o
u
s
n
a
v
ig
a
ti
o
n
in
u
n
str
u
c
tu
re
d
e
n
v
iro
n
m
e
n
t.
Ob
sta
c
le
a
v
o
id
a
n
c
e
is
a
n
i
m
p
o
rtan
t
tas
k
in
th
e
f
ield
o
f
ro
b
o
ti
c
s,
sin
c
e
t
h
e
g
o
a
l
o
f
a
u
to
n
o
m
o
u
s
ro
b
o
t
is
to
re
a
c
h
th
e
d
e
stin
a
ti
o
n
w
it
h
o
u
t
c
o
ll
isio
n
.
T
h
e
o
b
jec
ti
v
e
is
to
m
a
k
e
th
e
ro
b
o
t
m
o
v
e
a
lo
n
g
a
c
o
ll
isio
n
f
re
e
traje
c
to
ry
u
n
t
il
it
re
a
c
h
e
s
it
s
targ
e
t.
T
h
e
p
ro
p
o
se
d
a
p
p
ro
a
c
h
u
se
s
th
e
a
rti
f
icia
l
n
e
u
ra
l
n
e
t
w
o
rk
in
ste
a
d
o
f
th
e
f
u
z
z
i
f
ied
e
n
g
in
e
th
e
n
th
e
o
u
tp
u
t
f
ro
m
it
is
p
ro
c
e
ss
e
d
u
sin
g
a
d
a
p
ti
v
e
in
f
e
re
n
c
e
e
n
g
in
e
a
n
d
d
e
f
u
z
z
i
f
ic
a
ti
o
n
e
n
g
in
e
.
In
t
h
is
a
p
p
r
o
a
c
h
,
th
e
re
a
l
p
ro
c
e
ss
in
g
ti
m
e
i
s
re
d
u
c
e
d
th
a
t
is
in
c
re
a
se
th
e
m
o
b
il
e
ro
b
o
t
re
sp
o
n
se
.
T
h
e
p
ro
p
o
se
d
n
e
u
r
o
-
f
u
z
z
y
c
o
n
tr
o
ll
e
r
is
e
v
a
lu
a
ted
su
b
jec
ti
v
e
l
y
a
n
d
o
b
jec
ti
v
e
ly
w
it
h
o
th
e
r
a
p
p
ro
a
c
h
e
s
a
n
d
a
lso
t
h
e
p
r
o
c
e
ss
in
g
ti
m
e
i
s
tak
e
n
in
c
o
n
sid
e
ra
ti
o
n
.
K
ey
w
o
r
d
s
:
F
u
zz
i
f
icatio
n
Fu
zz
y
lo
g
ic
H
y
b
r
id
n
eu
r
o
-
f
u
zz
y
Mo
b
ile
r
o
b
o
t
Un
s
tr
u
ct
u
r
ed
E
n
v
ir
o
n
m
e
n
t
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
:
Ay
m
an
A
b
u
B
ak
er
,
Dep
ar
t
m
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
A
p
p
lied
Scien
ce
P
r
iv
ate
U
n
i
v
er
s
it
y
,
166
-
1
1
9
3
1
,
Sh
af
a
B
ad
r
an
,
Am
m
an
,
J
o
r
d
an
.
E
m
ail:
a_
ab
u
b
ak
er
@
as
u
.
ed
u
.
j
o
1.
I
NT
RO
D
UCT
I
O
N
Am
o
n
g
all
th
e
s
o
f
t
-
co
m
p
u
t
in
g
m
et
h
o
d
s
s
u
g
g
e
s
ted
f
o
r
m
o
b
il
e
r
o
b
o
t
r
ea
ctiv
e
n
av
ig
at
io
n
,
f
u
zz
y
lo
g
i
c
s
y
s
te
m
s
h
av
e
b
ee
n
f
o
u
n
d
to
b
e
th
e
m
o
s
t
attr
ac
ti
v
e.
T
h
e
y
ar
e
to
ler
an
t
to
n
o
is
e
a
n
d
er
r
o
r
in
th
e
s
e
n
s
e
o
f
in
f
o
r
m
atio
n
co
m
in
g
f
r
o
m
t
h
e
s
en
s
o
r
y
s
y
s
te
m
,
a
n
d
m
o
s
t
i
m
p
o
r
tan
tl
y
t
h
e
y
ar
e
f
ac
tu
a
l r
e
f
lec
tio
n
o
f
t
h
e
b
e
h
av
io
r
o
f
h
u
m
an
e
x
p
er
tis
e
[
1
]
.
I
n
g
e
n
er
al,
th
er
e
ar
e
t
w
o
ap
p
r
o
ac
h
es
to
th
e
ap
p
l
icatio
n
o
f
f
u
zz
y
lo
g
ic
i
n
m
o
b
ile
r
o
b
o
t
n
av
i
g
atio
n
,
n
a
m
el
y
,
b
eh
av
io
r
-
b
ased
ap
p
r
o
ac
h
[
2
,
3
]
an
d
class
ical
f
u
zz
y
r
u
le
-
b
ase
ap
p
r
o
ac
h
[
4
,
5
]
.
T
h
e
d
esig
n
o
f
f
u
zz
y
lo
g
ic
r
u
l
es
is
o
f
te
n
r
elian
t
o
n
h
e
u
r
is
tic
ex
p
er
ien
ce
an
d
it
lack
s
s
y
s
te
m
atic
m
eth
o
d
o
lo
g
y
.
T
h
er
ef
o
r
e
th
is
r
u
les
m
i
g
h
t
n
o
t
b
e
co
r
r
ec
t
an
d
co
n
s
is
ten
t,
d
o
n
o
t
p
o
s
s
ess
co
m
p
lete
d
o
m
ai
n
k
n
o
w
led
g
e,
an
d
/o
r
co
u
ld
h
a
v
e
a
p
r
o
p
o
r
tio
n
o
f
r
ed
u
n
d
a
n
t
r
u
les
[
6
]
.
Fu
r
t
h
er
m
o
r
e,
w
h
e
n
a
b
etter
p
r
ec
is
io
n
is
n
ee
d
ed
th
e
n
u
m
b
er
o
f
in
p
u
t
v
ar
iab
les a
n
d
th
e
ir
f
u
zz
y
v
al
u
es
n
ee
d
to
b
e
in
cr
ea
s
ed
,
f
o
r
ex
a
m
p
le,
w
h
e
n
u
s
i
n
g
f
o
u
r
i
n
p
u
t
v
ar
iab
les ea
c
h
m
ap
p
ed
b
y
s
ev
e
n
f
u
zz
y
v
al
u
es
b
esid
es
2
4
0
1
if
–
th
en
r
u
les
m
a
y
b
e
r
eq
u
ir
ed
to
d
ef
in
e
th
e
r
u
le
-
b
ase
o
f
th
e
i
n
f
er
en
ce
s
y
s
te
m
.
S
u
c
h
h
u
g
e
ex
p
a
n
s
io
n
i
n
a
m
u
lti
-
d
i
m
en
s
io
n
al
f
u
zz
y
r
u
le
-
b
ased
s
y
s
te
m
ad
d
s
f
u
r
th
er
ad
h
o
c
to
th
e
d
esig
n
o
f
t
h
e
s
y
s
te
m
[
7
].
Sev
er
al
s
u
cc
es
s
f
u
l
r
ea
ctiv
e
n
a
v
ig
a
tio
n
ap
p
r
o
ac
h
es
b
ased
o
n
n
eu
r
al
n
et
w
o
r
k
s
h
av
e
b
ee
n
s
u
g
g
e
s
ted
in
th
e
liter
at
u
r
e
[
8
,
9
]
.
I
n
s
p
ite
o
f
v
ar
io
u
s
s
u
g
g
e
s
ted
n
e
t
w
o
r
k
t
o
p
o
lo
g
ies
an
d
lear
n
i
n
g
m
et
h
o
d
s
,
n
eu
r
al
r
ea
cti
v
e
n
av
i
g
ato
r
s
s
ti
ll
p
er
ce
iv
e
th
eir
k
n
o
w
led
g
e
an
d
s
k
i
lls
f
r
o
m
d
e
m
o
n
s
tr
atin
g
ac
tio
n
s
[
1
0
]
.
T
h
e
r
ef
o
r
e,
th
e
y
s
u
f
f
er
f
r
o
m
a
v
er
y
s
lo
w
co
n
v
er
g
en
ce
,
lack
o
f
g
e
n
er
aliza
tio
n
d
u
e
to
li
m
ited
p
atter
n
s
to
r
ep
r
esen
t
co
m
p
l
icate
d
en
v
ir
o
n
m
e
n
t
s
,
a
n
d
f
i
n
all
y
in
f
o
r
m
at
io
n
e
n
ca
p
s
u
l
ated
w
it
h
i
n
th
e
n
et
w
o
r
k
ca
n
n
o
t
b
e
i
n
ter
p
r
eted
in
to
p
h
y
s
ical
k
n
o
w
led
g
e
[
11
,
12
]
.
C
o
n
s
eq
u
en
tl
y
,
t
h
e
u
t
ilizatio
n
o
f
n
e
u
r
al
n
et
w
o
r
k
s
i
n
r
ea
ctiv
e
m
o
b
ile
r
o
b
o
t
n
av
ig
atio
n
i
s
li
m
ited
w
h
e
n
co
m
p
ar
ed
to
f
u
z
z
y
lo
g
ic.
Ho
w
e
v
er
,
t
h
e
r
o
le
o
f
n
eu
r
al
n
et
w
o
r
k
s
h
as b
ee
n
f
o
u
n
d
to
b
e
v
er
y
u
s
e
f
u
l
an
d
ef
f
ec
ti
v
e
w
h
e
n
i
n
te
g
r
ated
w
it
h
f
u
zz
y
s
y
s
te
m
s
[
1
3
]
.
T
h
e
b
ir
th
o
f
th
is
i
n
te
g
r
atio
n
b
et
w
ee
n
th
e
s
e
t
w
o
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t
J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
1
0
2
7
-
1
0
3
4
1028
s
o
f
t
-
co
m
p
u
ti
n
g
p
ar
ad
ig
m
s
i
s
t
h
e
n
eu
r
o
-
f
u
zz
y
s
y
s
te
m
s
.
Ne
u
r
o
-
f
u
zz
y
s
y
s
te
m
s
p
r
o
v
id
e
a
n
u
r
g
en
t
s
y
n
er
g
y
t
h
at
ca
n
b
e
f
o
u
n
d
b
et
w
ee
n
t
h
e
t
w
o
p
ar
ad
ig
m
s
,
esp
ec
iall
y
t
h
e
ca
p
ab
ilit
y
to
m
i
m
ic
h
u
m
a
n
ex
p
er
ts
as
in
f
u
zz
y
lo
g
ic
,
an
d
lear
n
i
n
g
f
r
o
m
p
r
ev
io
u
s
ex
p
er
ien
ce
ca
p
ab
ilit
y
as i
n
n
e
u
r
al
n
et
w
o
r
k
s
.
I
n
g
e
n
er
al,
n
e
u
r
o
-
f
u
zz
y
s
y
s
te
m
s
ca
n
b
e
class
if
ied
in
to
t
h
r
ee
ca
teg
o
r
ies,
n
e
u
r
all
y
ad
ap
tiv
e
f
u
zz
y
in
f
er
en
ce
s
y
s
te
m
,
n
e
u
r
all
y
p
e
r
f
o
r
m
ed
FIS,
an
d
co
m
b
i
n
ato
r
i
al,
o
r
h
y
b
r
id
,
n
eu
r
o
-
f
u
zz
y
s
y
s
te
m
s
.
T
h
e
n
eu
r
all
y
ad
ap
tiv
e
f
u
zz
y
in
f
er
en
ce
s
y
s
t
e
m
is
th
e
m
o
s
t
w
id
el
y
u
s
ed
n
eu
r
o
-
f
u
zz
y
s
y
s
te
m
s
,
a
n
d
t
h
e
y
ar
e
d
esig
n
ed
to
co
m
b
i
n
e
t
h
e
lear
n
in
g
ca
p
ab
ilit
ies
o
f
n
eu
r
al
n
et
w
o
r
k
s
a
n
d
r
ea
s
o
n
i
n
g
p
r
o
p
er
ties
o
f
f
u
zz
y
lo
g
ic
[
1
4
,
1
5
]
.
I
n
th
is
p
ap
er
,
a
n
e
w
n
o
v
el
ap
p
r
o
ac
h
is
p
r
o
p
o
s
ed
u
s
i
n
g
t
h
e
h
y
b
r
i
d
n
eu
r
o
-
f
u
zz
y
co
n
tr
o
ller
as
a
m
o
b
ile
n
a
v
i
g
atio
n
s
y
s
te
m
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
h
as
ap
p
ar
en
t
ad
v
an
ta
g
e
in
s
t
r
u
ctu
r
es
t
h
at
s
i
m
p
li
f
y
a
n
d
r
ed
u
ce
th
e
p
r
o
ce
s
s
i
n
g
ti
m
e
a
n
d
i
m
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
.
T
h
is
ar
ch
i
v
ed
b
y
u
s
i
n
g
a
n
ar
tific
ial
n
e
u
r
al
n
et
w
o
r
k
i
n
s
tead
o
f
f
u
zz
if
ica
tio
n
e
n
g
i
n
e.
W
ith
s
u
ch
a
tech
n
iq
u
e,
t
h
e
r
eq
u
ir
ed
ti
m
e
n
ee
d
ed
to
in
f
er
th
e
d
ec
i
s
io
n
f
o
r
th
e
r
o
b
o
t
m
o
v
e
m
e
n
t is
g
r
ea
tl
y
r
ed
u
ce
d
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
P
r
ev
io
u
s
a
u
th
o
r
s
h
a
v
e
ap
p
lied
v
ar
io
u
s
t
y
p
e
s
o
f
tec
h
n
iq
u
es
to
co
n
tr
o
l th
e
m
o
b
ile
r
o
b
o
t u
s
in
g
d
i
f
f
er
e
n
t
in
telli
g
e
n
t
tec
h
n
iq
u
es.
S
in
g
h
et
al
[
16
]
d
ev
elo
p
ed
an
d
s
u
cc
e
s
s
f
u
ll
y
i
m
p
le
m
e
n
ted
a
p
atter
n
r
ec
o
g
n
it
io
n
ap
p
r
o
ac
h
to
r
ea
ctiv
e
n
av
ig
ati
o
n
b
ased
o
n
r
ea
l
ti
m
e
s
en
s
o
r
y
in
f
o
r
m
atio
n
.
A
h
e
u
r
is
t
ic
f
u
zz
y
n
eu
r
o
n
et
w
o
r
k
i
s
d
ev
elo
p
ed
f
o
r
p
atter
n
–
m
ap
p
in
g
b
et
w
ee
n
q
u
a
n
tized
u
l
tr
as
o
n
ic
s
en
s
o
r
y
d
ata
an
d
th
e
v
el
o
cit
y
co
m
m
an
d
s
to
th
e
r
o
b
o
t.
T
h
e
d
esig
n
g
o
al
was
to
en
ab
le
an
au
to
n
o
m
o
u
s
m
o
b
ile
r
o
b
o
t
to
n
av
ig
a
te
s
a
f
e
l
y
a
n
d
ef
f
icie
n
tl
y
to
tar
g
et
p
o
s
itio
n
i
n
a
p
r
ev
io
u
s
l
y
u
n
k
n
o
w
n
e
n
v
ir
o
n
m
en
t.
T
o
b
u
ild
th
e
d
e
s
ir
ed
m
ap
p
in
g
b
et
w
ee
n
p
er
ce
p
tio
n
an
d
m
o
tio
n
,
u
s
e
f
u
ll
y
h
eu
r
i
s
tic
r
u
les
w
er
e
co
m
b
i
n
ed
w
ith
t
h
e
Fu
zz
y
Ko
h
o
n
e
n
C
l
u
s
ter
i
n
g
Net
w
o
r
k
(
FKC
N)
.
I
n
Yu
n
g
an
d
Ye
[
17
]
p
ap
er
,
a
n
alter
n
a
ti
v
e
tr
ain
i
n
g
ap
p
r
o
ac
h
to
th
e
E
E
M
b
ased
t
r
ain
in
g
m
et
h
o
d
is
p
r
esen
ted
an
d
f
u
zz
y
r
ea
cti
v
e
n
av
ig
at
io
n
ar
ch
itect
u
r
e
is
d
escr
ib
ed
.
Us
in
g
t
h
e
r
u
le
b
ase
lear
n
ed
f
r
o
m
t
h
e
n
e
w
m
et
h
o
d
,
th
e
p
r
o
p
o
s
ed
f
u
zz
y
r
ea
cti
v
e
n
av
i
g
ato
r
f
u
s
es
t
h
e
o
b
s
tacle
av
o
id
an
ce
b
e
h
av
io
r
a
n
d
g
o
al
s
ee
k
i
n
g
b
eh
a
v
io
r
to
d
eter
m
in
e
it
s
co
n
tr
o
l a
ctio
n
s
T
h
e
n
e
w
tr
ain
i
n
g
m
e
th
o
d
is
2
7
0
ti
m
e
s
f
a
s
ter
in
lear
n
i
n
g
s
p
ee
d
; a
n
d
is
o
n
l
y
4
% o
f
th
e
lear
n
i
n
g
co
s
t
o
f
t
h
e
E
E
M
m
e
th
o
d
,
w
h
er
e
ad
ap
tab
ilit
y
is
ac
h
ie
v
ed
w
ith
t
h
e
aid
o
f
an
en
v
ir
o
n
m
en
t
ev
alu
a
to
r
.
Hag
r
as
an
d
So
b
h
(
1
9
9
8
)
d
is
cu
s
s
ed
t
h
e
co
n
tr
o
l
o
f
au
to
n
o
m
o
u
s
i
n
telli
g
e
n
t
r
o
b
o
tic
ag
e
n
t
o
p
er
atin
g
i
n
u
n
s
tr
u
ct
u
r
ed
c
h
an
g
i
n
g
e
n
v
ir
o
n
m
e
n
t
s
.
O
n
li
n
e
lear
n
i
n
g
as
a
u
s
e
f
u
l
m
et
h
o
d
p
r
o
d
u
cin
g
i
n
tel
lig
e
n
t
m
ac
h
i
n
es
f
o
r
in
ac
ce
s
s
ib
le
en
v
ir
o
n
m
en
t
s
w
a
s
in
tr
o
d
u
ce
d
.
I
n
th
ese
en
v
ir
o
n
m
e
n
t
s
it
is
r
eq
u
ir
ed
to
p
e
r
f
o
r
m
o
n
lin
e
lear
n
in
g
th
r
o
u
g
h
i
n
ter
ac
tio
n
w
i
th
t
h
e
r
ea
l
en
v
ir
o
n
m
e
n
t
an
d
p
er
f
o
r
m
i
n
g
a
n
y
ad
ap
tatio
n
w
i
th
i
n
s
h
o
r
t
ti
m
e
i
n
ter
v
al
s
.
Un
d
er
s
u
c
h
co
n
d
itio
n
s
,
r
o
b
o
tic
ag
en
t
s
h
a
v
e
to
b
e
ad
ap
tiv
e.
C
ao
et
al.
[
18
]
d
escr
ib
e
a
N
eu
r
o
-
f
u
zz
y
co
n
tr
o
l
m
et
h
o
d
f
o
r
th
e
n
av
i
g
atio
n
o
f
an
A
GV
r
o
b
o
t.
A
n
o
v
er
all
s
y
s
te
m
d
esi
g
n
an
d
d
ev
elo
p
m
en
t
w
as
p
r
esen
ted
.
T
h
e
Neu
r
o
-
Fu
zz
y
co
m
p
u
tatio
n
an
d
its
ap
p
licatio
n
f
o
r
m
o
b
ile
r
o
b
o
t
n
av
ig
atio
n
w
er
e
d
is
cu
s
s
ed
.
T
h
e
s
y
s
te
m
th
at
w
as
to
b
e
co
n
tr
o
lled
is
an
elec
tr
icall
y
p
r
o
p
elled
m
o
b
il
e
v
eh
icle
n
a
m
ed
B
ea
r
ca
t
I
I
,
w
h
ic
h
is
a
co
m
p
u
ter
co
n
tr
o
lled
in
telli
g
en
t
s
y
s
te
m
.
A
s
a
u
to
n
o
m
o
u
s
n
a
v
ig
at
io
n
r
eq
u
ir
es
a
n
u
m
b
er
o
f
h
eter
o
g
e
n
eo
u
s
ca
p
ab
ilit
ie
s
,
in
cl
u
d
in
g
th
e
ab
ilit
y
to
ex
ec
u
t
e
ele
m
en
tar
y
g
o
al
-
ac
h
iev
i
n
g
ac
tio
n
s
,
li
k
e
r
ea
ch
in
g
a
g
i
v
e
n
lo
ca
tio
n
;
to
r
ea
ch
in
r
ea
l
ti
m
e
to
u
n
e
x
p
ec
ted
ev
e
n
t
s
,
lik
e
th
e
s
u
d
d
en
ap
p
ea
r
an
ce
o
f
an
o
b
s
tacle
;
to
d
eter
m
i
n
e
t
h
e
r
o
b
o
t’
s
p
o
s
itio
n
;
an
d
to
ad
ap
t
to
ch
a
n
g
es
i
n
th
e
e
n
v
ir
o
n
m
en
t,
t
h
e
p
ap
er
in
tr
o
d
u
ce
s
a
Ne
u
r
o
-
f
u
zz
y
c
o
n
tr
o
l
m
et
h
o
d
f
o
r
n
av
i
g
atio
n
o
f
an
A
u
to
n
o
m
o
u
s
Gu
id
e
d
Ve
h
icle
(
A
GV)
r
o
b
o
t.
Ng
a
n
d
C
ar
p
en
ter
e
t
al.
[
1
9
]
in
tr
o
d
u
ce
a
n
e
u
r
al
in
te
g
r
ated
F
u
zz
y
co
n
tr
o
ller
(
NiF
-
T
)
,
w
h
ic
h
in
te
g
r
ates
t
h
e
f
u
zz
y
lo
g
ic
r
ep
r
esen
tatio
n
o
f
h
u
m
an
k
n
o
w
led
g
e
w
it
h
t
h
e
lear
n
i
n
g
ca
p
ab
ilit
y
o
f
n
eu
r
al
n
et
w
o
r
k
s
,
is
d
ev
el
o
p
ed
f
o
r
n
o
n
lin
ea
r
d
y
n
a
m
ic
co
n
tr
o
l
p
r
o
b
lem
s
.
I
t
co
v
er
s
in
te
g
r
ated
s
en
s
i
n
g
,
c
o
n
tr
o
l,
ac
tu
ato
r
m
o
d
u
le
s
,
r
ea
l
-
ti
m
e
p
er
f
o
r
m
a
n
ce
,
ab
ilit
y
to
s
u
cc
es
s
f
u
ll
y
h
a
n
d
le
n
o
is
y
s
e
n
s
o
r
s
ig
n
als,
r
ea
cti
v
e
co
n
tr
o
ller
d
esig
n
w
h
ic
h
c
ap
tu
r
es
h
ig
h
-
le
v
el,
li
n
g
u
i
s
tic
all
y
b
ased
h
u
m
a
n
ex
p
er
tis
e
i
n
a
s
et
o
f
f
u
zz
y
r
u
l
es,
tr
ain
i
n
g
o
f
n
eu
r
al
n
et
w
o
r
k
s
d
ir
ec
tl
y
w
it
h
f
u
zz
y
r
u
le
s
i
n
s
tead
o
f
n
u
m
er
ica
l
s
a
m
p
le
d
ata,
as
w
ell
as
lear
n
in
g
ca
p
ab
ilit
ies
an
d
g
en
er
al
ap
p
licab
ilit
y
.
NiF
-
T
ar
ch
itectu
r
e
c
o
m
p
r
i
s
es
"
o
f
th
r
ee
d
is
tin
ct
p
ar
ts
:
1
)
F
u
zz
y
lo
g
ic
Me
m
b
er
s
h
ip
F
u
n
ct
io
n
s
(
F
MF
)
,
2
)
a
R
u
le
Ne
u
r
al
Net
w
o
r
k
(
R
NN)
,
an
d
3
)
a
n
d
Ou
tp
u
t
-
R
e
f
in
e
m
e
n
t
Ne
u
r
al
Net
w
o
r
k
(
O
R
NN)
.
FMF
ar
e
u
ti
lized
to
f
u
zz
if
y
s
e
n
s
o
r
y
i
n
p
u
t
s
.
R
NN
in
ter
p
o
lates
th
e
f
u
zz
y
r
u
le
s
et;
a
f
ter
d
ef
u
z
zif
icatio
n
,
th
e
o
u
tp
u
t
is
u
s
ed
to
tr
ain
OR
NN.
T
h
e
w
ei
g
h
t
s
o
f
th
e
O
R
NN
ca
n
b
e
ad
j
u
s
ted
o
n
-
li
n
e
to
f
i
n
e
-
tu
n
e
t
h
e
co
n
tr
o
ller
"
.
On
l
y
f
iv
e
r
u
les
w
er
e
u
s
ed
to
tr
ain
th
e
w
al
l
f
o
llo
w
i
n
g
b
e
h
av
io
r
,
w
h
ile
n
i
n
e
w
er
e
u
s
ed
f
o
r
th
e
h
all
ce
n
ter
i
n
g
.
Als
o
,
a
r
o
b
o
t
co
n
v
o
y
i
n
g
b
eh
a
v
io
r
w
as
r
ea
li
ze
d
w
it
h
o
n
l
y
n
i
n
e
r
u
les.
Fo
r
all
o
f
t
h
e
d
escr
ib
ed
b
eh
av
io
r
s
—
w
all
f
o
llo
w
i
n
g
,
h
all
ce
n
ter
i
n
g
,
a
n
d
co
n
v
o
y
i
n
g
,
th
eir
R
NN
’
s
w
er
e
tr
ain
ed
o
n
l
y
f
o
r
a
f
e
w
h
u
n
d
r
ed
iter
atio
n
s
an
d
s
o
ar
e
th
eir
OR
NN
’
s
tr
ai
n
ed
f
o
r
o
n
l
y
les
s
th
an
o
n
e
h
u
n
d
r
ed
iter
atio
n
s
to
lear
n
t
h
eir
p
ar
en
t
r
u
le
s
ets.
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
Mo
b
ile
r
o
b
o
t c
o
n
tr
o
ller
u
s
in
g
n
o
ve
l h
yb
r
id
s
ystem
(
A
yma
n
A
b
u
B
a
ke
r
)
1029
3.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
m
o
b
ile
r
o
b
o
t
is
r
eq
u
ir
ed
to
ex
p
lo
r
e
s
ev
er
al
p
at
h
s
i
n
a
m
az
e,
o
f
a
p
atter
n
o
f
s
u
cc
e
s
s
i
v
e
co
m
b
i
n
atio
n
s
o
f
lef
t
an
d
r
ig
h
t
tu
r
n
s
.
I
ts
task
i
s
to
r
ea
ch
a
d
esire
d
p
o
s
itio
n
at
th
e
en
d
o
f
o
n
e
ch
an
n
el.
T
h
e
m
o
b
ile
r
o
b
o
t
u
s
es
a
k
i
n
d
p
r
o
ce
s
s
,
s
eq
u
en
t
iall
y
ad
o
p
tin
g
c
y
clic
p
atter
n
o
f
th
e
l
ef
t
an
d
r
ig
h
t
t
u
r
n
s
.
E
v
en
t
u
all
y
,
it
e
n
d
s
u
p
w
it
h
t
h
e
d
esire
d
p
o
s
itio
n
,
at
w
h
ich
t
i
m
e
a
s
ig
n
al
i
s
i
n
j
ec
ted
,
ca
u
s
in
g
t
h
e
r
o
b
o
t
to
r
ec
o
r
d
th
e
co
r
r
ec
t
p
atter
n
.
T
h
e
m
o
b
i
le
r
o
b
o
t
is
ass
u
m
ed
to
b
e
eq
u
ip
p
ed
w
it
h
t
h
r
ee
p
h
y
s
ical
u
ltr
aso
n
ic
s
e
n
s
o
r
s
a
n
d
o
n
e
v
ir
t
u
al
s
e
n
s
o
r
as s
h
o
w
n
i
n
Fig
u
r
e
1.
Fig
u
r
e
1
.
Mo
b
ile
r
o
b
o
t
w
i
th
f
r
o
n
tal
s
e
n
s
o
r
s
T
h
e
p
h
y
s
ical
s
e
n
s
o
r
s
ar
e
u
s
e
d
to
d
etec
t
o
b
s
tacle
s
in
f
r
o
n
t
o
f
th
e
r
o
b
o
t,
th
e
r
ig
h
t
s
id
e,
an
d
th
e
lef
t
s
id
e,
r
esp
ec
tiv
el
y
.
T
h
e
m
ax
i
m
u
m
d
i
s
ta
n
ce
t
h
at
ca
n
b
e
s
e
n
s
ed
b
y
th
e
s
e
s
e
n
s
o
r
s
is
a
s
s
u
m
ed
to
b
e
8
m
eter
s
.
T
h
e
v
ir
tu
al
s
e
n
s
o
r
is
u
s
ed
to
g
u
id
e
th
e
r
o
b
o
t
to
w
ar
d
s
th
e
tar
g
et.
T
h
is
s
en
s
o
r
is
esp
ec
i
all
y
n
ee
d
ed
w
h
e
n
th
e
tar
g
et
d
ir
ec
tio
n
o
f
m
o
v
e
m
en
t
is
to
tall
y
b
lo
ck
ed
b
y
a
n
o
b
s
tacle
.
T
h
e
v
ir
tu
al
s
e
n
s
o
r
w
il
l
g
u
id
e
t
h
e
r
o
b
o
t
b
ac
k
to
w
ar
d
s
th
e
tar
g
et
o
n
ce
t
h
e
o
b
s
tacle
is
av
o
id
ed
as
i
n
[
2
0
,
21]
.
Hen
ce
f
o
r
th
,
th
e
r
o
b
o
t
tr
av
els
q
u
ick
l
y
a
n
d
ac
cu
r
atel
y
alo
n
g
t
h
e
tr
ac
k
to
a
cc
o
m
p
li
s
h
an
y
j
o
b
th
at
h
a
s
b
e
en
as
s
i
g
n
ed
.
I
t
i
s
a
s
s
u
m
ed
th
a
t
th
e
r
o
b
o
t
w
ill
n
o
t
f
ac
e
a
n
y
tr
ap
s
(
o
r
g
et
in
to
a
s
i
tu
atio
n
w
h
er
e
it
i
s
r
eq
u
ir
ed
to
b
ac
k
tr
ac
k
o
r
t
u
r
n
ar
o
u
n
d
)
.
S
u
ch
a
p
r
o
b
le
m
i
s
o
u
t
o
f
th
i
s
p
ap
er
s
co
p
e.
T
h
e
f
o
u
r
s
e
n
s
o
r
s
p
r
o
v
id
e
t
h
e
p
ath
p
lan
n
i
n
g
s
y
s
te
m
(
i
n
o
u
r
ca
s
e
a
n
e
u
r
o
-
f
u
zz
y
lo
g
ic
s
y
s
te
m
)
o
f
th
e
r
o
b
o
t
w
ith
th
r
ee
d
i
s
ta
n
ce
s
f
r
o
n
t
(
d
c)
,
r
ig
h
t
(
d
r
)
,
lef
t
(
d
l)
,
an
d
tar
g
et
o
r
i
en
tatio
n
(
t
h
eta)
,
r
esp
ec
tiv
e
l
y
.
Fro
m
th
e
s
e
in
p
u
ts
,
th
e
n
eu
r
o
-
f
u
zz
y
lo
g
ic
co
n
tr
o
ller
w
ill
m
ak
e
u
p
a
d
ec
is
io
n
in
w
h
i
ch
d
ir
ec
tio
n
s
h
o
u
ld
th
e
r
o
b
o
t
m
o
v
e
in
o
r
d
er
to
r
ea
ch
th
e
tar
g
et.
T
h
e
n
eu
r
o
-
f
u
zz
y
co
n
tr
o
ller
s
h
o
u
ld
p
ass
t
h
r
o
u
g
h
th
r
ee
s
tag
e
s
,
i.e
.
,
A
N
N
f
u
zz
i
f
icatio
n
,
i
n
f
er
en
ce
,
an
d
d
ef
u
zz
i
f
icat
io
n
as s
h
o
w
n
i
n
Fi
g
u
r
e
2.
Fig
u
r
e
2
.
Neu
r
o
-
f
u
zz
y
co
n
tr
o
ll
er
s
tag
es
3
.
1
.
F
o
urt
y
rules f
uzzy
na
v
i
g
a
t
o
r
s
y
s
t
em
T
h
e
f
u
zz
y
lo
g
ic
co
n
tr
o
ller
(
F
L
C
4
0
)
w
as
a
n
al
y
ze
d
a
n
d
test
ed
f
o
r
d
if
f
er
en
t
ca
s
es
b
ased
o
n
th
e
s
a
m
e
p
ar
am
eter
s
an
d
r
u
le
s
u
s
ed
b
y
[
22
]
.
T
h
e
r
o
b
o
t
m
o
tio
n
r
esu
lt
s
h
a
v
e
b
ee
n
co
n
s
id
er
ed
w
ith
r
elatio
n
to
d
if
f
er
en
t
ca
s
es.
P
r
o
b
lem
s
w
er
e
r
ec
o
r
d
ed
an
d
in
v
e
s
ti
g
ated
an
d
t
h
e
r
e
aso
n
s
b
eh
i
n
d
th
e
f
ail
u
r
e
o
f
t
h
is
r
o
b
o
t,
in
t
h
es
e
ca
s
es,
w
er
e
r
elate
d
to
th
e
l
i
m
i
ted
n
u
m
b
er
o
f
t
h
e
s
et
s
u
s
ed
(
F
AR
,
NE
AR
)
,
an
d
th
e
li
m
ited
a
n
g
le
o
f
o
r
ien
ta
tio
n
(
tu
r
n
i
n
g
an
g
le)
,
w
h
ic
h
ar
e
f
i
v
e
s
ets.
Du
e
to
th
is
l
i
m
itatio
n
,
th
e
r
o
b
o
t
to
u
ch
es
t
h
e
o
b
s
tacle
s
s
lig
h
tl
y
i
n
all
ca
s
es
co
n
s
id
er
ed
as
s
h
o
w
n
i
n
Fi
g
u
r
e
3
.
T
o
av
o
id
th
ese
p
r
o
b
lem
s
,
a
r
elax
atio
n
o
f
th
e
r
u
les
w
as
d
o
n
e
b
y
in
cr
ea
s
i
n
g
th
e
n
u
m
b
er
o
f
s
e
ts
f
o
r
t
h
e
i
n
p
u
t
d
is
ta
n
ce
s
f
r
o
m
t
w
o
to
t
h
r
ee
s
et
s
;
ac
co
r
d
in
g
l
y
,
t
h
e
n
u
m
b
er
o
f
r
u
les
w
as
in
cr
ea
s
ed
to
1
3
5
ac
tiv
atio
n
r
u
l
es
w
h
ic
h
w
ill b
e
d
is
c
u
s
s
ed
in
t
h
e
n
e
x
t sect
io
n
.
L
e
f
t
_
F
r
o
n
t
_
S
e
n
s
o
r
D
i
r
e
c
t
_
F
r
o
n
t
_
S
e
n
s
o
r
R
i
g
h
t
_
F
r
o
n
t
_
S
e
n
s
o
r
T
a
r
g
e
t
i
n
g
_
S
e
n
s
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t
J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
1
0
2
7
-
1
0
3
4
1030
Fig
u
r
e
3
.
FLC4
0
,
s
i
m
u
lated
m
o
tio
n
3
.
2
.
Dev
el
o
p
m
ent
o
f
t
he
i
m
p
ro
v
ed
f
uzzy
na
v
ig
a
t
o
r
s
y
s
t
e
m
As
it
h
as
b
ee
n
alr
ea
d
y
n
o
ted
,
th
at
t
h
e
F
L
C
4
0
is
n
o
t
ca
p
ab
le
to
av
o
id
co
llis
io
n
w
it
h
t
h
e
ed
g
es
o
f
th
e
o
b
s
tacle
s
in
al
l
ca
s
es.
An
i
m
p
r
o
v
e
m
e
n
t
to
t
h
e
s
y
s
t
e
m
ca
n
b
e
ea
s
il
y
m
ad
e
b
y
s
lig
h
tl
y
i
n
cr
ea
s
i
n
g
th
e
n
u
m
b
er
o
f
f
u
zz
y
s
ets
i
n
o
r
d
er
t
o
ac
h
iev
e
b
etter
r
eso
lu
tio
n
.
I
n
th
i
s
p
a
p
er
,
it
is
p
r
o
p
o
s
ed
to
in
cr
ea
s
e
th
e
f
u
zz
y
s
et
s
to
t
h
r
ee
li
n
g
u
i
s
tic
lab
els
(
L
,
M,
S)
as
s
h
o
w
n
in
Fi
g
u
r
e
4
(
a,
b
,
c)
.
T
h
e
f
u
z
z
y
s
ets
in
t
h
is
ca
s
e
b
ec
o
m
e
s
h
o
r
ter
th
a
n
b
ef
o
r
e
,
s
o
th
e
ac
cu
r
ac
y
an
d
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
co
n
tr
o
ller
ar
e
i
m
p
r
o
v
ed
.
As
th
e
n
u
m
b
er
o
f
s
et
s
is
i
n
cr
ea
s
ed
th
e
f
u
zz
y
r
u
le
s
ar
e
in
cr
ea
s
ed
as
w
ell
u
p
to
1
3
5
ac
tiv
atio
n
r
u
le
s
(3
3
3
5
=
1
3
5
ac
tiv
atio
n
r
u
les).
(
a)
(
b
)
(
c)
Fig
u
r
e
4
.
(
a
)
L:
La
r
g
e,
M:
Me
d
iu
m,
S
:
S
ma
ll
,
Dis
tan
ce
(
b
)
LB:
ta
r
g
et_
Left B
ig
,
LS
:
ta
r
g
et
_
Left S
ma
ll,
Z:
ta
r
g
et
_
Zer
o
,
R
S
:
ta
r
g
et_
R
i
g
h
t S
ma
ll,
R
B
:
ta
r
g
et_
R
ig
h
t B
ig
,
tar
g
et
o
r
ien
tatio
n
(
c
)
TL
B
:
Tu
r
n
_
Left
_
B
ig
,
TL
S
:
Tu
r
n
_
Left_
S
ma
ll,
TRB
:
Tu
r
n
_
R
ig
h
t_
B
ig
,
T
u
r
n
in
g
An
g
le
Me
m
b
er
s
h
ip
f
u
n
ctio
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
Mo
b
ile
r
o
b
o
t c
o
n
tr
o
ller
u
s
in
g
n
o
ve
l h
yb
r
id
s
ystem
(
A
yma
n
A
b
u
B
a
ke
r
)
1031
As an
e
x
a
m
p
le,
a
s
a
m
p
le
is
p
r
esen
ted
w
h
er
e
th
e
ac
ti
v
atio
n
r
u
les ar
e:
I
F
d
r
is
L a
n
d
d
c
is
L a
n
d
d
l
is
L a
n
d
tr
is
LB
THEN S
a
is
TL
B
I
F
d
r
is
S
a
n
d
d
c
is
M a
n
d
d
l i
s
L a
n
d
tr
is
R
B
THEN S
a
is
T
Z
I
F
d
r
is
L
a
n
d
d
c
is
M a
n
d
d
l i
s
S
a
n
d
tr
is
R
S
THEN S
a
is
TRS
T
h
e
r
esu
lts
o
b
tain
ed
f
r
o
m
t
h
is
i
m
p
r
o
v
ed
f
u
zz
y
lo
g
ic
co
n
t
r
o
ller
h
av
e
b
ee
n
i
m
p
r
o
v
ed
.
T
h
e
r
o
b
o
t
av
o
id
s
co
llis
io
n
w
i
th
t
h
e
o
b
s
t
ac
les
as
s
h
o
w
n
in
Fi
g
u
r
e
5
.
A
l
s
o
,
th
e
p
r
o
ce
s
s
i
n
g
ti
m
e
f
o
r
th
i
s
s
m
al
l
n
u
m
b
er
o
f
r
u
le
s
i
s
v
er
y
s
h
o
r
t
w
h
ic
h
i
n
cr
ea
s
ed
t
h
e
r
esp
o
n
s
e
ti
m
e
o
f
th
e
r
o
b
o
t
co
m
p
ar
in
g
w
i
th
u
s
in
g
6
2
5
ac
tiv
atio
n
r
u
les
as
i
n
r
ef
er
en
ce
[
23
]
.
Fu
r
th
er
m
o
r
e,
t
h
is
p
ap
er
f
o
cu
s
ed
o
n
ev
alu
ati
n
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
i
s
f
u
zz
y
co
n
tr
o
ller
b
y
co
m
p
ar
i
n
g
t
h
e
r
esu
lt
s
w
i
th
o
th
er
ap
p
r
o
ac
h
es
s
u
ch
as
[
24
]
.
T
h
ese
co
m
p
ar
is
o
n
s
ar
e
p
r
esen
ted
i
n
th
e
n
e
x
t sec
tio
n
.
Fig
u
r
e
5
.
I
m
p
r
o
v
e
m
e
n
t F
L
C
1
3
5
s
u
cc
ess
ca
s
e
s
3.
3
.
H
y
brid neuro
-
f
uzzy
t
ec
hn
iq
ue
T
h
e
m
ai
n
p
r
o
b
lem
i
n
t
h
e
f
u
zz
y
lo
g
ic
co
n
tr
o
ller
is
t
h
e
F
u
zz
i
f
icatio
n
b
lo
ck
,
w
h
ic
h
n
e
ed
a
lo
n
g
p
r
o
ce
s
s
in
g
ti
m
e.
T
o
s
o
lv
e
th
i
s
p
r
o
b
lem
o
f
p
r
o
ce
s
s
in
g
ti
m
e,
th
e
ar
tif
icial
n
e
u
r
al
n
et
w
o
r
k
(
A
NN)
is
p
r
o
p
o
s
ed
in
s
tead
o
f
t
h
e
F
u
zz
i
f
icatio
n
en
g
i
n
e
to
r
ed
u
ce
th
e
co
m
p
u
tatio
n
al
ti
m
e.
T
h
e
s
y
s
te
m
is
in
v
esti
g
ated
b
y
co
n
s
id
er
in
g
th
e
r
es
u
lt
s
o
f
th
e
in
te
g
r
atio
n
b
et
w
ee
n
b
o
th
s
y
s
t
e
m
s
(
F
u
zz
y
lo
g
ic
an
d
n
e
u
r
al
n
et
w
o
r
k
s
)
as
s
h
o
wn
in
Fi
g
u
r
e
2.
3
.
3
.
1
.
Cre
a
t
ing
t
he
I
np
ut
a
nd
t
he
O
utput
Da
t
a
T
h
e
n
eu
r
al
n
et
w
o
r
k
tr
ain
in
g
i
n
th
e
f
ee
d
f
o
r
w
ar
d
m
et
h
o
d
,
th
e
in
p
u
ts
,
an
d
th
e
o
u
tp
u
ts
d
at
a
m
u
s
t
b
e
k
n
o
w
n
.
T
h
e
i
n
p
u
t
s
d
ata
ar
e
c
r
is
p
v
al
u
e
f
o
r
t
h
e
t
h
r
ee
d
i
s
ta
n
ce
s
en
s
o
r
s
a
n
d
t
h
e
p
h
y
s
ical
o
r
ien
tatio
n
s
e
n
s
o
r
.
As
s
h
o
w
n
i
n
Fi
g
u
r
e
4
,
th
e
d
is
tan
ce
r
a
n
g
e
i
s
[
0
–
8
]
m
eter
s
,
b
u
t
th
e
i
n
ter
v
a
l
f
r
o
m
2
to
6
is
co
n
s
id
er
ed
s
i
n
ce
th
e
d
is
ta
n
ce
i
n
ter
v
al
[
0
,
2
]
h
a
s
th
e
l
in
g
u
is
t
ic
lab
el
as
1
m
eter
(
S)
an
d
th
e
d
is
ta
n
ce
i
n
te
r
v
al
[
5
,
6
]
h
as
also
th
e
l
in
g
u
is
tic
lab
el
5
m
eter
s
(
M)
.
T
h
e
s
a
m
e
th
in
g
i
s
f
o
r
t
h
e
a
n
g
le
o
r
ien
ta
tio
n
in
w
h
ic
h
t
h
e
i
n
ter
v
al
t
h
at
co
n
s
id
er
ed
is
[
-
6
5
,
6
5
]
d
eg
r
e
es
s
i
n
ce
th
e
s
id
ed
s
ets
h
a
v
e
t
h
e
li
n
g
u
i
s
tic
lab
els
a
s
–
6
5
an
d
6
5
r
esp
ec
tiv
el
y
.
T
h
e
d
is
tan
ce
i
s
d
i
v
id
ed
in
to
s
ev
en
tee
n
p
o
i
n
ts
w
it
h
s
tep
o
f
0
.
2
5
m
eter
b
et
w
ee
n
ea
c
h
p
o
in
t
an
d
s
tep
o
f
8
.
1
2
5
d
eg
r
ee
f
o
r
th
e
o
r
ien
tatio
n
a
n
g
le
i
n
p
u
t.
T
h
er
ef
o
r
e,
w
e
h
a
v
e
f
o
u
r
d
ed
icate
d
v
ec
to
r
s
(
lef
t
,
ce
n
ter
,
r
ig
h
t
a
n
d
o
r
ien
tatio
n
)
t
h
at
i
n
cl
u
d
e
1
7
v
alu
e
s
.
T
h
er
ef
o
r
e,
th
er
e
w
ill
b
e
f
o
u
r
p
ar
alle
l
f
u
zz
i
f
icatio
n
n
eu
r
al
n
et
w
o
r
k
.
E
ac
h
f
u
zz
i
f
icatio
n
n
e
u
r
al
n
et
w
o
r
k
h
as
f
iv
e
o
u
tp
u
t
n
o
d
es
w
h
ich
ar
e
t
h
e
p
r
o
b
ab
ilit
y
v
a
lu
e
f
o
r
ea
ch
lin
g
u
is
ti
c
lab
el
(
S,
M,
L
f
o
r
d
is
tan
ce
s
en
s
o
r
s
an
d
L
B
,
L
S,
Z
,
R
S,R
B
f
o
r
o
r
ien
tatio
n
s
en
s
o
r
)
.
T
h
e
s
ev
en
tee
n
cr
is
p
v
al
u
es
f
o
r
ea
ch
i
n
p
u
t
v
ec
to
r
ar
e
p
r
o
c
ess
ed
in
a
r
ea
l
f
u
zz
i
f
icatio
n
e
n
g
i
n
e
i
n
o
r
d
er
to
co
m
p
u
te
th
e
lin
g
u
i
s
tic
v
al
u
e
f
o
r
ea
ch
i
n
p
u
t.
T
h
is
li
n
g
u
is
tic
v
al
u
e
is
co
n
s
id
er
ed
as
a
n
o
u
tp
u
t
f
o
r
th
e
f
u
zz
if
icatio
n
n
e
u
r
al
n
e
t
w
o
r
k
.
As
a
r
es
u
lt,
th
e
o
u
tp
u
t
m
atr
i
x
is
d
esi
g
n
t
o
b
e
1
7
×3
f
o
r
ea
ch
f
u
zz
if
ica
tio
n
n
e
u
r
al
n
e
t
w
o
r
k
,
w
h
er
e
n
u
m
b
er
3
r
ep
r
esen
t
th
e
f
u
zz
y
s
et
s
f
o
r
in
p
u
t se
n
s
o
r
s
3
.
3
.
2
.
T
ra
ini
ng
a
nd
l
ea
rning
t
he
neura
l net
w
o
rk
As
h
as
b
e
en
s
h
o
w
n
in
t
h
e
p
r
ev
io
u
s
s
ec
tio
n
,
t
h
e
i
n
p
u
t
an
d
o
u
t
p
u
t d
ata
to
tr
ain
t
h
e
f
ee
d
-
f
o
r
war
d
n
eu
r
al
n
et
w
o
r
k
ar
e
g
e
n
er
ated
.
T
h
en
th
e
v
al
u
es
o
f
th
e
i
n
p
u
t
m
atr
i
ce
s
ar
e
ar
r
an
g
ed
in
tr
ain
i
n
g
v
ec
to
r
s
in
a
m
an
n
er
s
i
m
ilar
to
th
e
J
ac
k
k
n
i
f
e
tech
n
iq
u
e,
w
h
er
e
7
0
%
o
f
t
h
e
d
ata
w
er
e
u
s
ed
f
o
r
th
e
NN
tr
ain
i
n
g
p
h
ase
s
an
d
th
e
r
e
m
ain
in
g
3
0
%
w
er
e
u
s
e
d
f
o
r
th
e
NN
te
s
ti
n
g
p
h
ase
s
.
T
h
e
f
u
zz
i
f
icat
io
n
n
e
u
r
al
n
e
t
wo
r
k
is
d
esi
g
n
u
s
i
n
g
f
o
u
r
p
ar
allel
n
e
u
r
al
n
et
w
o
r
k
.
T
h
e
to
p
o
l
o
g
y
o
f
t
h
e
ea
ch
o
f
th
e
f
u
zz
i
f
icatio
n
n
e
u
r
al
n
e
t
wo
r
k
co
n
s
is
t
s
o
f
o
n
e
in
p
u
t
n
o
d
es,
h
id
d
en
la
y
er
an
d
f
i
v
e
o
u
tp
u
t
n
o
d
es.
T
o
f
in
d
th
e
o
p
tim
u
m
to
p
o
lo
g
y
(
i.e
.
,
th
e
o
p
ti
m
u
m
n
u
m
b
er
o
f
h
id
d
en
n
o
d
es
i
n
t
h
e
h
id
d
en
la
y
er
)
,
s
ev
er
al
f
ee
d
f
o
r
w
ar
d
N
N
s
tr
u
ct
u
r
es
w
er
e
tr
ain
ed
u
s
in
g
t
h
e
tr
ai
n
i
n
g
d
ata
to
f
i
n
d
th
e
m
i
n
i
m
u
m
tr
ai
n
in
g
er
r
o
r
.
A
s
a
r
esu
l
t,
it
is
f
o
u
n
d
t
h
at
t
h
e
f
ee
d
f
o
r
w
ar
d
NN
w
it
h
t
w
o
h
id
d
en
la
y
er
s
(
9
n
o
d
es
in
t
h
e
f
ir
s
t
la
y
er
an
d
3
in
th
e
s
ec
o
n
d
la
y
er
)
an
d
f
i
v
e
n
o
d
es
f
o
r
o
u
tp
u
t
la
y
er
p
r
o
d
u
ce
th
e
m
i
n
i
m
u
m
er
r
o
r
s
,
as sh
o
w
n
i
n
Fi
g
u
r
e
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t
J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
1
0
2
7
-
1
0
3
4
1032
Fig
u
r
e
6
.
Fu
zz
i
f
ied
A
NN
to
p
o
lo
g
y
4.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
h
e
m
ai
n
p
r
o
b
le
m
i
n
t
h
e
f
u
z
z
y
lo
g
ic
co
n
tr
o
ller
p
r
ese
n
ted
in
r
e
f
er
en
ce
[
25
]
is
t
h
e
in
f
er
e
n
ce
b
lo
ck
,
w
h
ic
h
co
n
s
is
t
s
o
f
a
lar
g
e
n
u
m
b
er
o
f
r
u
les
th
at
n
ee
d
a
lo
n
g
p
r
o
ce
s
s
in
g
t
i
m
e.
T
o
s
o
lv
e
th
i
s
p
r
o
b
le
m
o
f
p
r
o
ce
s
s
in
g
ti
m
e,
t
h
e
f
u
zz
i
f
ica
tio
n
en
g
in
e
w
a
s
r
ep
lace
d
w
it
h
an
A
N
N.
T
h
er
ef
o
r
e,
th
e
r
ea
l
p
r
o
ce
s
s
in
g
ti
m
e
i
s
r
ed
u
ce
an
d
th
e
m
o
b
ile
r
o
b
o
t
r
esp
o
n
s
e
is
i
n
cr
ea
s
ed
as
s
h
o
w
n
i
n
Fi
g
u
r
e
7
.
T
h
e
m
ai
n
a
d
v
an
ta
g
e
g
a
in
ed
b
y
u
tili
zi
n
g
h
y
b
r
id
n
e
u
r
o
-
f
u
zz
y
co
n
tr
o
ller
to
r
ed
u
ce
t
h
e
r
ea
l
p
r
o
ce
s
s
in
g
ti
m
e.
T
h
e
p
r
o
p
o
s
ed
tech
n
i
q
u
e
ca
n
s
u
cc
e
s
s
f
u
ll
y
r
ed
u
ce
t
h
e
p
r
o
ce
s
s
i
n
g
ti
m
e
7
2
8
s
co
m
p
ar
in
g
w
i
th
1
1
8
9
s
u
s
i
n
g
F
L
C
1
3
5
.
P
r
ac
tically
,
s
i
m
u
lat
io
n
-
u
s
i
n
g
P
C
d
o
es
n
’
t
s
h
o
w
t
h
e
d
if
f
er
e
n
ce
s
i
n
t
h
e
C
P
U
ti
m
e
f
o
r
th
e
t
h
r
ee
co
n
tr
o
ll
er
s
s
in
ce
th
e
P
C
is
v
er
y
f
a
s
t
a
n
d
t
h
e
r
e
s
p
o
n
s
e
o
f
th
e
h
ar
d
w
ar
e
is
s
lo
w
.
T
h
e
C
P
U
ti
m
e
f
o
r
t
h
e
t
h
r
ee
co
n
tr
o
ller
s
is
n
o
ticed
w
h
e
n
u
s
i
n
g
m
icr
o
co
n
tr
o
ller
c
h
ip
to
co
n
tr
o
l
t
h
e
r
o
b
o
t
m
o
tio
n
an
d
d
o
w
n
lo
ad
t
h
e
p
r
o
g
r
a
m
to
t
h
e
i
m
p
le
m
e
n
ted
r
o
b
o
t.
I
n
t
h
e
F
L
C
4
0
,
th
e
co
n
tr
o
ller
r
esp
o
n
s
e
t
i
m
e
w
ill
b
e
f
aster
th
a
n
b
o
th
co
n
tr
o
ller
s
,
b
u
t t
h
e
p
er
f
o
r
m
a
n
ce
i
s
l
i
m
ited
.
On
th
e
o
t
h
er
h
a
n
d
,
th
e
F
L
C
1
3
5
w
o
r
k
ed
o
u
t
w
e
ll
b
u
t
w
it
h
lo
w
r
esp
o
n
s
e,
w
h
ic
h
in
tr
o
d
u
ce
d
a
d
ef
icien
c
y
i
n
th
e
r
o
b
o
t
m
o
tio
n
(
cr
ea
te
a
d
ea
d
p
o
in
t
i
n
t
h
e
r
o
b
o
t
co
n
tr
o
ll
er
)
.
T
h
e
NNF
L
C
1
3
5
in
cr
ea
s
e
d
th
e
r
e
s
p
o
n
s
e
o
f
th
e
w
h
o
le
co
n
tr
o
ller
an
d
i
m
p
r
o
v
es
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
r
o
b
o
t
m
o
tio
n
.
Th
e
p
er
f
o
r
m
an
ce
ev
a
lu
at
io
n
o
f
FLC4
0
,
FLC1
3
5
,
an
d
NNFL
1
3
5
as sh
o
w
n
i
n
T
ab
le
1
.
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
Mo
b
ile
r
o
b
o
t c
o
n
tr
o
ller
u
s
in
g
n
o
ve
l h
yb
r
id
s
ystem
(
A
yma
n
A
b
u
B
a
ke
r
)
1033
(
a)
(
b
)
Fig
u
r
e
7
.
(
a)
FL
C
6
2
5
ca
s
es
,
(
b
)
FL
C
1
3
5
ca
s
es
T
ab
le
1
.
T
h
e
p
er
f
o
r
m
an
ce
e
v
a
lu
atio
n
o
f
F
L
C
4
0
,
F
L
C
1
3
5
,
an
d
NNFL
1
3
5
V
a
r
i
a
b
l
e
P
e
r
f
o
r
man
c
e
C
P
U
T
i
me
(
S
)
F
L
C
4
0
S
l
i
g
h
t
l
y
o
r
s
e
v
e
r
e
l
y
c
o
l
l
i
d
i
n
g
w
i
t
h
t
h
e
o
b
st
a
c
l
e
s
6
5
9
F
L
C
1
3
5
A
v
o
i
d
c
o
l
l
i
si
o
n
w
i
t
h
t
h
e
o
b
s
t
a
c
l
e
s w
i
t
h
l
o
w
r
e
sp
o
n
se
t
i
me
1
1
8
9
N
N
F
1
3
5
A
v
o
i
d
c
o
l
l
i
si
o
n
w
i
t
h
t
h
e
o
b
s
t
a
c
l
e
s w
i
t
h
h
i
g
h
r
e
sp
o
n
se
t
i
me
7
2
8
5.
CO
NCLU
SI
O
N
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
F
L
C
1
3
5
is
g
o
o
d
an
d
s
lig
h
tl
y
i
m
p
r
o
v
ed
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
r
o
b
o
t
co
m
p
ar
ed
to
th
e
FLC4
0
s
in
ce
th
e
r
o
b
o
t
d
o
esn
’
t
to
u
c
h
an
y
o
b
s
tacle
an
d
th
e
r
o
b
o
t
av
o
id
s
co
llis
io
n
w
ith
a
n
y
o
b
s
tacle
s
as
s
h
o
w
n
i
n
t
h
e
ab
o
v
e
ca
s
e
s
.
B
u
t
t
h
e
i
n
f
er
en
ce
ti
m
e
is
m
u
c
h
m
o
r
e
t
h
a
n
t
h
e
FLC4
0
.
Ho
w
ev
er
,
th
e
p
r
o
p
o
s
ed
n
e
u
r
o
-
f
u
zz
y
ap
p
r
o
ac
h
th
at
is
u
s
ed
A
NN
i
n
s
t
ea
d
o
f
f
u
zz
if
ica
tio
n
en
g
i
n
e
s
h
o
w
a
g
o
o
d
r
esu
lts
co
m
p
ar
i
n
g
w
i
th
F
L
C
1
3
5
.
T
h
e
m
o
b
ile
r
o
b
o
t
r
esp
o
n
s
e
is
in
cr
ea
s
e
s
in
ce
t
h
e
r
ea
l
p
r
o
ce
s
s
in
g
tin
e
is
d
ec
r
ea
s
e
b
y
4
0
% f
o
r
FL
C
1
3
5
p
r
o
ce
s
s
in
g
ti
m
e
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
is
g
r
atef
u
l
to
th
e
A
p
p
lied
Scien
ce
P
r
iv
ate
Un
iv
er
s
it
y
,
Am
m
a
n
,
J
o
r
d
an
,
f
o
r
th
e
f
u
l
l
f
i
n
an
cia
l.
RE
F
E
R
E
NC
E
S
[1
]
W
.
Zh
e
n
g
,
H.
W
a
n
g
,
Z.
Zh
a
n
g
,
N.
L
i,
P
.
Yin
,
―
M
u
l
ti
-
lay
e
r
F
e
e
d
-
f
o
r
w
a
rd
Ne
u
ra
l
Ne
t
w
o
rk
De
e
p
Lea
rn
in
g
Co
n
tr
o
l
w
it
h
H
y
b
rid
P
o
siti
o
n
a
n
d
V
irt
u
a
l
-
f
o
rc
e
A
lg
o
rit
h
m
f
o
r
M
o
b
il
e
Ro
b
o
t
Ob
sta
c
le
Av
o
id
a
n
c
e
,
‖
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
n
tro
l
,
A
u
to
m
a
ti
o
n
a
n
d
S
y
ste
m
s,
v
o
l.
1
7
(4
)
,
pp
.
1
0
0
7
–
1
0
1
8
,
2
0
1
9
.
[2
]
A
.
Ku
m
a
r,
D.
P
a
rh
i,
H.
C
h
a
n
d
r
a
Da
s,
P
.
Ku
m
a
r,
M
.
M
u
n
i,
K.
S
a
lo
n
y
,
―
P
a
th
o
p
ti
m
iza
ti
o
n
f
o
r
n
a
v
ig
a
ti
o
n
o
f
a
h
u
m
a
n
o
id
ro
b
o
t
u
sin
g
h
y
b
rid
ize
d
f
u
z
z
y
-
g
e
n
e
ti
c
a
lg
o
rit
h
m
,
‖
I
n
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
In
telli
g
e
n
t
Un
ma
n
n
e
d
S
y
ste
ms
,
v
o
l.
3
1
(2
),
p
p
.
1
3
2
-
1
5
0
,
2
0
1
9
.
[3
]
E.
A
g
u
irre
a
n
d
A
.
G
o
n
z
á
lez
,
―
F
u
z
z
y
b
e
h
a
v
io
rs
f
o
r
m
o
b
il
e
ro
b
o
t
n
a
v
ig
a
ti
o
n
:
d
e
sig
n
,
c
o
o
rd
i
n
a
ti
o
n
a
n
d
f
u
sio
n
,
‖
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
A
p
p
r
o
x
i
ma
te R
e
a
so
n
in
g
,
v
o
l
.
2
5
(3
)
,
p
p
.
2
5
5
-
2
8
9
,
2
0
0
0
.
[4
]
S
.
K.
Ha
rish
a
,
P
.
Ku
m
a
r
,
M
.
Kr
ish
n
a
,
a
n
d
S
.
C.
S
h
a
rm
a
,
―
F
u
z
z
y
L
o
g
ic
Re
a
so
n
in
g
to
Co
n
tr
o
l
M
o
b
il
e
R
o
b
o
t
o
n
P
re
-
d
e
f
in
e
d
S
tri
p
P
a
th
.
W
o
rld
A
c
a
d
e
m
y
o
f
S
c
ien
c
e
,
‖
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
2
,
p
p
.
6
4
2
-
6
4
6
,
2
0
0
8
.
[5
]
S
.
P
a
ra
su
ra
m
a
n
,
B
.
S
h
iri
n
z
a
d
e
h
a
n
d
V.
G
a
n
a
p
a
th
y
,
―
M
o
b
il
e
Ro
b
o
t
Na
v
ig
a
ti
o
n
Us
in
g
A
lp
h
a
Lev
e
l
F
u
z
z
y
L
o
g
ic
S
y
st
e
m
:
Ex
p
e
ri
m
e
n
tal
In
v
e
stig
a
ti
o
n
s
,‖
J
o
u
rn
a
l
o
f
Evo
l
u
ti
o
n
a
ry
Co
mp
u
ta
ti
on
,
p
p
.
5
5
7
-
5
6
3
,
2
0
0
9
.
[6
]
H.
P
o
n
c
e
,
E
.
M
o
y
a
-
A
lb
o
r,
a
n
d
J.
Briev
a
,
―
A
No
v
e
l
A
rti
f
icia
l
Or
g
a
n
ic
Co
n
tro
l
S
y
ste
m
f
o
r
M
o
b
il
e
R
o
b
o
t
Na
v
ig
a
ti
o
n
in
A
ss
isted
L
iv
in
g
Us
in
g
V
isio
n
-
a
n
d
Ne
u
ra
l
-
Ba
se
d
S
trate
g
ies
,
‖
Co
mp
u
t
a
ti
o
n
a
l
In
telli
g
e
n
c
e
a
n
d
Ne
u
ro
sc
ien
c
e
,
v
o
l.
1
4
(2
),
p
p
.
1
0
1
-
1
1
7
,
2
0
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t
J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
1
0
2
7
-
1
0
3
4
1034
[7
]
L
.
S
h
ih
-
A
n
,
F
.
Hs
u
a
n
-
M
in
g
,
C.
Ku
n
g
-
Ha
n
,
H.
W
e
n
-
Hu
n
g
,
―
Hig
h
ly
A
u
to
n
o
m
o
u
s
V
isu
a
li
z
a
ti
o
n
M
a
p
-
G
e
n
e
ra
ti
o
n
M
o
b
i
le
Ro
b
o
t
S
y
ste
m
De
sig
n
Th
ro
u
g
h
t
h
e
Ro
b
o
t
Op
e
ra
ti
n
g
S
y
s
tem
P
latf
o
rm
,
‖
J
o
u
rn
a
l
o
f
Im
a
g
i
n
g
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
6
2
(
3
),
p
p
.
3
0
4
0
3
-
1
-
3
0
4
0
3
,
2
0
1
8
.
[8
]
T
.
J.
Ro
ss
,
―
F
u
z
z
y
L
o
g
ic i
n
En
g
in
e
e
rin
g
A
p
p
li
c
a
ti
o
n
s
,‖
M
c
Gr
a
w
-
Hill
In
c
,
Ne
w
Yo
rk
,
1
9
9
8
.
[9
]
B.
S
a
leh
,
A
.
a
l
-
A
q
b
i,
A
.
S
a
e
d
i,
―
A
No
v
e
l
Bio
g
e
o
g
ra
p
h
y
In
sp
ired
T
ra
jec
to
ry
-
F
o
ll
o
w
in
g
Co
n
tro
ll
e
r
f
o
r
Na
ti
o
n
a
l
In
stru
m
e
n
t
Ro
b
o
t
,
‖
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ne
w
T
re
n
d
s
in
In
fo
rm
a
ti
o
n
a
n
d
Co
mm
u
n
ica
ti
o
n
s
T
e
c
h
n
o
l
o
g
y
Ap
p
li
c
a
ti
o
n
s
,
p
p
.
1
7
1
-
1
8
9
,
2
0
1
8
.
[1
0
]
P
.
G
a
b
riel,
C.
Da
n
tas
,
P
.
M
a
ik
o
l,
M
.
Ro
d
rig
u
e
s,
J.
P
a
u
l
o
,
A
.
Ba
rro
z
o
Jo
se
,
P
.
M
o
re
ira
d
e
O
li
v
e
iraP
lác
id
o
,
―
A
M
o
b
il
e
T
e
rre
strial
S
u
rv
e
il
lan
c
e
Ro
b
o
t
Us
in
g
th
e
W
a
ll
-
F
o
ll
o
w
in
g
T
e
c
h
n
iq
u
e
a
n
d
a
De
riv
a
ti
v
e
In
teg
ra
ti
v
e
P
r
o
p
o
rti
o
n
a
l
Co
n
tr
o
ll
e
r,
‖
Pro
c
e
e
d
in
g
s
o
f
t
h
e
Co
mp
u
ta
ti
o
n
a
l
M
e
th
o
d
s
in
S
y
ste
ms
a
n
d
S
o
ft
wa
re
,
In
t
e
ll
ig
e
n
t
S
y
ste
ms
in
Cy
b
e
rn
e
ti
c
s a
n
d
Au
t
o
ma
t
io
n
C
o
n
tro
l
T
h
e
o
ry
,
v
o
l.
4
0
(3
),
p
p
.
2
7
6
-
2
8
6
,
2
0
1
8
.
[1
1
]
K.
T
a
n
a
k
a
,
―
A
n
In
tro
d
u
c
ti
o
n
to
F
u
z
z
y
L
o
g
ic
f
o
r
P
ra
c
ti
c
a
l
A
p
p
li
c
a
ti
o
n
,‖
1
st
E
d
it
i
o
n
.
S
p
ri
n
g
-
Ver
la
g
,
Ne
w
Y
o
rk
,
1
9
9
6
.
[1
2
]
L
.
A
.
Zad
e
h
,
―
T
h
e
ro
les
o
f
f
u
z
z
y
lo
g
ic
a
n
d
so
f
t
c
o
m
p
u
ti
n
g
in
th
e
c
o
n
c
e
p
ti
o
n
,
d
e
sig
n
a
n
d
d
e
p
lo
y
m
e
n
t
o
f
in
telli
g
e
n
t
s
y
ste
m
s
,‖
BT
T
e
c
h
n
o
lo
g
y
,
v
o
l.
1
4
(4
),
p
p
.
32
-
3
6
,
1
9
9
6
.
[1
3
]
R.
Ca
ll
a
n
,
T
h
e
Esse
n
c
e
o
f
Ne
u
ra
l
Ne
two
rk
s
,
P
re
n
ti
c
e
-
Ha
ll
,
Eu
r
o
p
e
,
1
9
9
9
.
[1
4
]
A
.
A
.
A
b
u
Ba
k
e
r,
―
A
n
In
telli
g
e
n
t
M
o
b
il
e
Ro
b
o
t
C
o
n
tr
o
ll
e
r
U
sin
g
Ne
u
ro
-
F
u
z
z
y
T
e
c
h
n
iq
u
e
s,
‖
M
S
c
.
T
h
e
sis,
Un
iv
e
rsit
y
o
f
Jo
rd
a
n
,
2
0
0
2
.
[1
5
]
M
.
K.
S
in
g
h
,
D.R.
P
a
rh
i,
S
.
B
h
o
wm
i
k
,
S
.
K.Ka
sh
y
a
p
,
―
In
telli
g
e
n
t
Co
n
tr
o
ll
e
r
f
o
r
M
o
b
il
e
Ro
b
o
t:
F
u
z
z
y
L
o
g
ic
A
p
p
ro
a
c
h
,
‖
T
h
e
1
2
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
f
In
ter
n
a
ti
o
n
a
l
Asso
c
ia
ti
o
n
fo
r
C
o
mp
u
ter
M
e
th
o
d
s
a
n
d
Ad
v
a
n
c
e
s
in
Ge
o
me
c
h
a
n
ics
(
IACM
AG)
,
p
p
.
1
-
6
,
2
0
0
8
.
[1
6
]
N.
H.
C.
Yu
n
g
a
n
d
Ye
C.
,
―
A
n
In
telli
g
e
n
t
M
o
b
il
e
V
e
h
icle
Na
v
ig
a
to
r
Ba
se
d
o
n
F
u
z
z
y
L
o
g
ic
a
n
d
Re
in
f
o
rc
e
m
e
n
t
L
e
a
rn
in
g
,
‖
I
EE
E
T
ra
n
s
a
c
ti
o
n
o
n
S
y
ste
ms
,
M
a
n
a
n
d
Cy
b
e
rn
e
ti
c
s
-
Pa
rt C:
A
p
p
li
c
a
ti
o
n
a
n
d
Rev
iews
,
v
o
l.
2
9
(
2
),
1
9
9
9
.
[1
7
]
J.
Ca
o
,
L
iao
X
.
a
n
d
Ha
ll
E.
,
―
Re
a
c
ti
v
e
Na
v
ig
a
ti
o
n
f
o
r
A
u
to
n
o
m
o
u
s
G
u
id
e
d
V
e
h
icle
Us
in
g
t
h
e
Ne
u
ro
-
f
u
z
z
y
T
e
c
h
n
iq
u
e
s,‖
En
g
in
e
e
rin
g
A
p
p
li
c
a
ti
o
n
o
f
a
rt
if
icia
l
in
telli
g
e
n
t
,
v
o
l.
6
(4
),
p
p
.
3
2
0
-
3
2
9
,
2
0
0
0
.
[1
8
]
G
.
Ca
rp
e
n
ter,
S
.
G
ro
ss
b
e
rg
,
M
a
rk
u
z
o
n
N.,
Re
y
n
o
ld
H.
J.
a
n
d
Ro
se
n
D.
B
.
1
,
―
F
u
z
z
y
A
R
T
M
A
P
:
A
Ne
u
ra
l
Ne
tw
o
rk
A
rc
h
it
e
c
tu
re
f
o
r
In
c
re
m
e
n
tal
S
u
p
e
rv
ise
d
L
e
a
rn
in
g
o
f
A
n
a
lo
g
u
e
M
u
lt
i
-
d
im
e
n
sio
n
a
l
M
a
p
s,‖
IEE
E
T
ra
n
o
n
Ne
u
ra
l
Ne
two
rk
s
,
v
o
l.
3
(
5
)
,
p
p
.
6
9
8
-
7
1
3
,
1
9
9
2
.
[1
9
]
A
.
S
a
ff
io
tt
i.
S
.
P
ra
d
h
a
n
,
D.
P
a
r
h
i,
A
.
P
a
n
d
a
,
―
F
u
z
z
y
lo
g
ic
tec
h
n
iq
u
e
s
f
o
r
n
a
v
i
g
a
ti
o
n
o
f
se
v
e
r
a
l
m
o
b
il
e
ro
b
o
ts,
‖
J
o
u
rn
a
l
A
p
p
li
e
d
S
o
ft
C
o
mp
u
ti
n
g
,
v
o
l.
9
(
1
),
2
0
0
9
.
[2
0
]
L
.
F
a
u
se
tt
,
Fu
n
d
a
me
n
ta
ls
o
f
Ne
u
ra
l
Ne
two
rk
s
,
Pre
n
t
ice
-
Ha
ll
,
E
u
ro
p
e
,
1
9
9
4
.
[2
1
]
A
.
R.
M
e
d
sk
e
r,
Hy
b
rid
In
telli
g
e
n
t
S
y
ste
ms
,
Klu
w
e
r
A
c
a
d
e
m
ic P
u
b
li
sh
e
rs
,
Eu
r
o
p
e
,
1
9
9
5
.
[2
2
]
W
.
L
.
X
u
,
S
.
K.
T
so
.
,
―
Re
a
l
ti
m
e
S
e
lf
–
Re
a
c
ti
o
n
o
f
a
M
o
b
i
le
Ro
b
o
t
i
n
Un
str
u
c
tu
re
d
En
v
ir
o
n
m
e
n
t
Us
in
g
F
u
z
z
y
Re
a
so
n
in
g
,‖
En
g
in
e
e
rin
g
A
p
p
l
ica
ti
o
n
o
f
a
rtif
ici
a
l
i
n
telli
g
e
n
t
,
v
o
l.
9
(5
)
,
p
p
.
4
7
5
-
4
8
5
,
1
9
9
6
.
[2
3
]
A
.
Ku
m
a
r,
V
.
Ku
m
a
r,
―
P
e
rf
o
r
m
a
n
c
e
a
n
a
ly
sis
o
f
o
p
ti
m
a
l
h
y
b
rid
n
o
v
e
l
in
terv
a
l
ty
p
e
-
2
f
ra
c
ti
o
n
a
l
o
rd
e
r
f
u
z
z
y
lo
g
ic
c
o
n
tro
ll
e
rs f
o
r
f
ra
c
ti
o
n
a
l
o
rd
e
r
sy
ste
m
s,
‖
Exp
e
rt S
y
ste
ms
wit
h
Ap
p
l
ica
ti
o
n
s
,
v
o
l.
9
3
(1
),
p
p
.
4
3
5
-
4
5
5
,
2
0
1
8
.
[2
4
]
N.
Na
k
ra
n
ia,
M
.
Jo
sh
ib
,
―
A
n
In
telli
g
e
n
t
F
u
z
z
y
b
a
se
d
H
y
b
rid
A
p
p
ro
a
c
h
f
o
r
P
a
ra
ll
e
l
P
a
rk
in
g
in
Dy
n
a
m
i
c
En
v
iro
n
m
e
n
t,
‖
Pro
c
e
d
i
a
Co
m
p
u
t
e
r S
c
ien
c
e
,
v
o
l.
1
3
3
(
2
),
p
p
.
82
-
9
1
,
2
0
1
8
.
[2
5
]
M.
Zab
i
h
i,
A
.
A
las
t
y
,
―
D
y
n
a
m
ic
sta
b
il
it
y
a
n
d
c
o
n
tr
o
l
o
f
a
n
o
v
e
l
h
a
n
d
s
p
rin
g
in
g
ro
b
o
t,
‖
M
e
c
h
a
n
is
m
a
n
d
M
a
c
h
in
e
T
h
e
o
ry
,
v
o
l.
1
3
7
(
3
),
pp.
1
5
4
-
1
7
1
,
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.