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
R
A)
Vo
l.
6
,
No
.
1
,
Ma
r
ch
2
0
1
7
,
p
p
.
2
1
~3
0
I
SS
N:
2
0
8
9
-
4
8
5
6
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
r
a.
v
6
i1
.
p
p
2
1
-
30
21
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
JR
A
Path P
la
nning
of
the
Fire
Es
ca
ping
Sys
te
m
U
sing
Ac
tive
Dete
c
tion M
o
dule
Ying
-
Ya
o
T
ing
1
,
H
ua
n Sheng
Wa
ng
2
,
K
uo
L
a
n Su
3
1
P
r
o
g
ra
m
in
En
g
in
e
e
rin
g
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
Na
ti
o
n
a
l
Ka
o
h
si
u
n
g
F
irst
Un
iv
e
rsity
o
f
S
c
ien
c
e
&
T
e
c
h
n
o
lo
g
y
,
T
a
i
w
a
n
,
Ch
in
a
2
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter an
d
C
o
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
,
Na
ti
o
n
a
l
Ka
o
h
siu
n
g
F
irst
Un
iv
e
rsit
y
o
f
S
c
ien
c
e
&
T
e
c
h
n
o
lo
g
y
,
T
a
i
w
a
n
,
Ch
in
a
3
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Na
ti
o
n
a
l
Y
u
n
l
in
U
n
iv
e
rsity
o
f
S
c
ien
c
e
&
T
e
c
h
n
o
lo
g
y
,
T
a
i
w
a
n
,
Ch
in
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
1
9
,
2
0
1
6
R
ev
i
s
ed
Dec
1
6
,
2
0
1
6
A
cc
ep
ted
J
an
2
,
2
0
1
7
T
h
is
a
rti
c
le
p
ro
p
o
se
s
a
s
e
c
u
rit
y
s
y
ste
m
w
h
ich
d
e
tec
ts
th
e
f
ir
e
e
v
e
n
ts
a
n
d
p
lan
s
th
e
m
o
v
in
g
ro
u
te.
Eac
h
ro
b
o
t
w
it
h
se
v
e
ra
l
m
o
d
u
les
o
w
n
s
th
e
sh
a
p
e
o
f
c
y
li
n
d
e
r
a
n
d
h
e
ig
h
t,
w
e
ig
h
t
a
n
d
d
iam
e
ter
is
1
8
c
m
,
1
.
5
k
g
a
n
d
8
c
m
.
A
m
a
in
c
o
n
tro
ll
e
r
(S
T
C1
2
C
5
A
6
0
S
2
)
e
q
u
ip
s
ro
b
o
ts
a
s
a
m
icro
p
ro
c
e
ss
o
r.
Eac
h
ro
b
o
t
h
a
s
th
e
c
a
p
a
b
il
it
y
to
e
sc
a
p
e
f
ro
m
th
e
f
ire
sc
e
n
e
.
W
h
e
n
e
v
e
r
d
e
tec
ti
n
g
f
ires
a
n
d
o
b
sta
c
les
u
sin
g
im
a
g
e
se
n
so
r
a
n
d
re
f
lec
ti
v
e
IR
se
n
so
rs,
ro
b
o
ts
s
e
n
d
th
e
ID
c
o
d
e
,
o
r
ien
tati
o
n
,
a
n
d
p
o
siti
o
n
t
o
th
e
c
e
n
tralize
d
c
o
m
p
u
ter
a
n
d
o
t
h
e
r
ro
b
o
ts.
Af
ter
o
th
e
r
ro
b
o
ts
h
a
v
e
c
o
n
f
ir
m
e
d
th
e
f
ire
e
v
e
n
ts,
th
e
c
e
n
tralize
d
c
o
m
p
u
ter
u
se
s
th
e
G
a
u
ss
ian
p
ro
b
a
b
il
it
y
f
u
n
c
ti
o
n
to
c
a
lcu
late
th
e
d
a
n
g
e
r
v
a
lu
e
s
o
f
th
e
su
rro
u
n
d
in
g
p
o
i
n
ts
n
e
a
r
th
e
f
ire
so
u
rc
e
.
A
n
d
Ba
y
e
sia
n
e
sti
m
a
ti
o
n
m
e
th
o
d
is
a
p
p
li
e
d
t
o
c
o
m
p
u
te
th
e
to
tal
e
s
ti
m
a
ted
v
a
lu
e
o
f
e
a
c
h
p
o
in
t
i
n
p
latf
o
rm
.
F
u
rth
e
rm
o
re
,
th
e
to
tal
w
e
ig
h
ted
v
a
lu
e
s
o
f
a
ll
p
o
in
ts
a
re
sh
o
w
n
in
a
p
latf
o
r
m
a
n
d
it
s
a
im
is
to
e
n
larg
e
th
e
d
if
fe
re
n
c
e
b
e
tw
e
e
n
d
a
n
g
e
r
a
n
d
sa
f
e
ty
w
it
h
o
u
t
a
m
b
ig
u
it
y
.
A*
a
l
g
o
rit
h
m
is
u
se
d
in
th
e
e
sc
a
p
in
g
r
o
u
tes
a
re
p
la
n
n
e
d
b
y
a
c
e
n
tralize
d
c
o
m
p
u
ter.
T
h
e
m
o
b
il
e
ro
b
o
t
f
o
ll
o
w
s
th
e
lea
d
i
n
g
o
f
th
e
s
u
p
e
rv
ise
d
c
o
m
p
u
ter
a
u
to
n
o
m
o
u
sly
to
e
sc
a
p
e
f
ro
m
d
a
n
g
e
ro
u
s
a
re
a
s.
T
h
e
a
ir
-
f
u
e
l
ra
ti
o
a
n
d
th
e
ra
te
o
f
in
c
re
a
sin
g
in
te
m
p
e
ra
tu
re
w
it
h
d
istan
c
e
a
r
e
d
irec
tl
y
p
ro
p
o
rti
o
n
a
l
t
o
th
e
d
a
n
g
e
r
v
a
lu
e
.
A
s
so
c
iatin
g
th
e
in
c
re
a
sin
g
te
m
p
e
ra
tu
re
ra
te
w
it
h
th
re
e
-
f
ire so
u
rc
e
s,
it
is
v
e
rif
i
e
d
to
b
e
a
n
e
f
f
icie
n
t
s
y
ste
m
.
K
ey
w
o
r
d
:
A*
al
g
o
r
ith
m
A
ir
-
f
u
el
m
as
s
r
atio
P
ath
p
lan
n
i
n
g
Co
p
y
rig
h
t
©
2
0
1
7
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
:
Yin
g
-
Yao
T
in
g
,
P
r
o
g
r
am
i
n
E
n
g
i
n
ee
r
in
g
Scie
n
ce
an
d
T
ec
h
n
o
lo
g
y
,
C
o
lle
g
e
o
f
E
n
g
i
n
ee
r
in
g
,
Natio
n
al
Kao
h
s
i
u
n
g
Firs
t U
n
i
v
er
s
it
y
o
f
Scie
n
ce
&
T
ec
h
n
o
lo
g
y
,
No
.
1
,
Un
iv
er
s
it
y
R
D.
,
Ya
n
C
h
ao
Dis
t.,
Kao
h
s
i
u
n
g
C
it
y
8
2
4
,
T
aiw
a
n
,
C
h
i
n
a
.
E
m
ail:
u
9
6
1
5
9
0
3
@
n
k
f
u
s
t.e
d
u
.
t
w
1.
I
NT
RO
D
UCT
I
O
N
T
h
er
e
ar
e
m
u
lt
ip
le
s
e
n
s
o
r
s
f
o
r
p
eo
p
le,
i.e
.
,
to
n
g
u
e,
n
o
s
e,
s
k
in
,
ea
r
s
,
an
d
e
y
es,
r
e
s
p
o
n
s
ib
le
f
o
r
en
v
ir
o
n
m
e
n
tal
v
ar
iat
io
n
[
1
]
.
I
n
s
p
ir
ed
f
r
o
m
m
u
ltis
e
n
s
o
r
y
u
s
ef
u
ln
e
s
s
,
i
n
tel
lig
e
n
t
r
o
b
o
ts
w
i
th
s
en
s
iti
v
e
s
en
s
o
r
s
o
f
ac
o
u
s
tic
s
i
g
n
al,
h
ea
t
an
d
li
g
h
t
w
i
ll
en
h
an
ce
t
h
e
s
tr
e
n
g
t
h
o
f
d
etec
tin
g
f
ir
e
ev
e
n
ts
i
m
m
e
d
iatel
y
.
W
h
en
e
v
er
a
f
ir
e
tak
e
s
p
lace
,
en
v
ir
o
n
m
e
n
t
al
p
ar
am
eter
s
c
h
a
n
g
e,
r
es
u
lti
n
g
i
n
b
r
in
g
in
g
e
x
ce
s
s
iv
e
h
ea
t
,
ab
n
o
r
m
al
ac
o
u
s
tic
s
ig
n
al,
s
m
o
k
e,
UV
(
u
ltra
v
io
let
)
in
te
n
s
i
v
e
li
g
h
t,
a
n
d
s
o
f
o
r
th
.
L
i
u
et
al.
p
r
o
p
o
s
ed
th
e
co
n
ce
p
t
o
f
i
n
te
g
r
atin
g
t
h
e
f
ir
e
d
etec
tio
n
s
y
s
te
m
w
i
th
m
u
lti
-
f
u
n
ct
io
n
s
e
n
s
o
r
s
a
n
d
an
al
ar
m
s
y
s
te
m
w
it
h
w
ir
ele
s
s
tec
h
n
o
lo
g
y
to
n
o
t
o
n
l
y
in
cr
ea
s
e
f
ir
e
s
a
f
et
y
b
u
t
also
r
ed
u
ce
f
alse
alar
m
s
[
2
]
.
So
n
s
ale
et
al.
p
r
o
p
o
s
ed
a
m
u
l
ti
-
s
en
s
o
r
s
y
s
te
m
w
i
th
a
f
ir
e
-
d
etec
tio
n
f
u
n
ctio
n
an
d
a
f
ir
e
-
ex
tin
g
u
is
h
i
n
g
f
u
n
ctio
n
[
3
]
.
Z
h
a
n
g
an
d
W
a
n
g
d
esi
g
n
e
d
an
a
u
to
m
at
ic
f
ir
e
alar
m
s
y
s
te
m
b
ased
o
n
a
p
er
io
d
ical
w
ir
eles
s
s
en
s
o
r
n
et
wo
r
k
b
y
m
ea
s
u
r
in
g
t
h
e
s
m
o
k
e
co
n
ce
n
tr
atio
n
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N:
2
0
89
-
4856
I
J
R
A
Vo
l.
6
,
No
.
1
,
Ma
r
ch
2
0
1
7
:
2
1
–
30
22
d
ep
lo
y
i
n
g
te
m
p
er
atu
r
e
i
n
th
e
b
u
ild
in
g
[
4
]
.
C
alav
ia
et
al.
p
r
o
p
o
s
ed
a
s
y
s
te
m
d
esig
n
ed
to
m
in
i
m
ize
v
id
eo
p
r
o
ce
s
s
in
g
an
d
tr
a
n
s
m
is
s
io
n
,
w
h
ic
h
ca
n
d
etec
t
ab
n
o
r
m
al
o
b
j
ec
ts
an
d
alar
m
i
n
g
s
it
u
atio
n
s
b
y
a
n
al
y
zi
n
g
o
b
j
ec
t
m
o
v
e
m
e
n
t
[
5
]
.
I
n
p
ar
ticu
lar
,
W
an
g
et
al.
p
r
o
p
o
s
ed
th
e
m
u
lt
is
en
s
o
r
y
s
y
s
te
m
i
n
li
n
e
w
it
h
th
e
n
ex
t
g
en
er
atio
n
o
f
f
ir
e
d
etec
tio
n
tec
h
n
o
lo
g
y
[
6
]
.
R
ec
en
t
l
y
,
Yan
g
a
n
d
Z
h
u
a
n
g
p
r
o
p
o
s
ed
a
b
eh
av
io
r
co
n
tr
o
l
o
f
r
o
b
o
t
to
en
h
a
n
ce
th
e
ca
p
ac
it
y
o
f
r
o
b
o
t
esp
ec
iall
y
to
a
v
o
id
o
b
s
tacle
s
w
h
ic
h
i
m
p
r
o
v
ed
th
e
ef
f
icie
n
c
y
o
f
p
ath
p
lan
n
i
n
g
f
o
r
s
ec
u
r
it
y
s
y
s
te
m
[
7
]
.
A
p
ar
t f
r
o
m
I
C
tec
h
n
o
lo
g
y
,
w
ir
eles
s
co
m
m
u
n
icatio
n
is
ad
o
p
ted
as a
n
o
th
er
tr
en
d
.
As
f
o
r
th
e
an
a
l
y
s
is
al
g
o
r
ith
m
o
f
m
ea
s
u
r
ed
d
ata,
d
ata
f
u
s
io
n
is
o
f
ten
u
s
ed
in
t
h
ese
ap
p
licatio
n
s
.
Fo
r
d
ata
f
u
s
io
n
alg
o
r
it
h
m
s
,
t
h
er
e
ar
e
th
e
De
m
p
s
ter
-
S
h
af
er
ev
id
en
ce
m
e
t
h
o
d
[
8
]
,
lo
g
ic
f
ilter
[
9
]
,
B
ay
esia
n
esti
m
atio
n
m
et
h
o
d
[
1
0
]
,
Neu
r
o
n
et
w
o
r
k
,
f
u
zz
y
co
n
tr
o
ller
,
an
d
s
o
o
n
.
Fu
r
th
er
,
Neu
r
o
f
u
zz
y
i
n
f
er
en
ce
s
y
s
te
m
[
1
1
]
w
as
w
id
el
y
u
s
ed
to
s
h
o
w
t
h
e
ef
f
icie
n
c
y
i
n
th
e
r
elate
d
f
ield
s
o
f
r
o
b
o
tics
.
I
n
th
is
ar
ticle,
th
e
ce
n
tr
alize
d
c
o
m
p
u
ter
k
ee
p
in
g
tr
ac
k
i
n
g
o
f
m
o
b
ile
r
o
b
o
ts
is
a
h
ea
v
y
lo
ad
in
g
.
R
ad
io
Fre
q
u
en
c
y
I
d
en
t
if
i
ca
tio
n
(
R
FID
)
[
1
2
]
p
r
o
v
id
ed
th
e
p
o
w
er
f
u
l
tec
h
n
iq
u
e
as
a
r
e
m
ed
y
to
d
ea
l
w
it
h
lo
ca
tio
n
d
eter
m
in
a
tio
n
o
f
m
o
b
il
e
r
o
b
o
ts
.
Gu
o
et
al.
u
s
ed
th
e
B
a
y
e
s
ia
n
esti
m
atio
n
m
eth
o
d
to
co
m
p
u
te
th
e
e
s
ti
m
ated
v
al
u
e
o
f
i
n
ter
ac
tin
g
p
o
in
ts
s
ta
n
d
i
n
g
f
o
r
d
if
f
er
e
n
t
le
v
el
s
o
f
d
an
g
er
,
f
o
u
n
d
t
h
e
s
h
o
r
test
escap
in
g
p
ath
,
an
d
g
u
id
ed
p
eo
p
le
to
escap
e
f
r
o
m
th
e
f
ir
e
s
ce
n
e
[
1
0
]
.
B
u
t
in
r
ea
l
ca
s
es,
s
u
ch
1
-
D
r
is
k
v
al
u
es
ar
e
n
o
t
s
u
f
f
icie
n
t
to
d
eter
m
i
n
e
th
e
d
is
t
r
ib
u
tio
n
o
f
h
ea
t
o
f
t
h
e
f
ir
e,
b
ec
au
s
e
th
e
h
ea
t
d
ec
r
ea
s
es
f
r
o
m
f
ir
e
ce
n
ter
to
th
e
s
u
r
r
o
u
n
d
in
g
u
n
i
f
o
r
m
l
y
.
A
s
a
r
e
m
ed
y
,
th
e
Gau
s
s
ia
n
2
D
d
is
cr
ete
m
a
s
s
f
u
n
ctio
n
is
u
s
e
f
u
l
to
p
r
o
v
id
e
e
n
o
u
g
h
i
n
f
o
r
m
a
tio
n
ab
o
u
t
th
e
h
ea
t
-
d
i
s
tr
ib
u
tio
n
p
h
e
n
o
m
en
o
n
.
I
n
lig
h
t
o
f
t
h
is
,
t
h
is
ar
tic
le
d
ev
elo
p
s
th
e
h
ea
t
-
d
is
tr
ib
u
tio
n
m
o
d
el
ad
o
p
tin
g
t
h
e
Gau
s
s
ia
n
2
D
d
is
cr
ete
m
ass
f
u
n
ctio
n
i
n
o
u
r
s
y
s
te
m
.
Fu
r
t
h
er
m
o
r
e,
ex
p
er
i
m
en
ta
l
r
esu
lt
s
ar
e
s
h
o
w
n
to
v
alid
ate
t
h
e
s
y
s
te
m
w
it
h
b
etter
r
eliab
ilit
y
an
d
e
f
f
icien
c
y
.
2.
SYST
E
M
ARCH
I
T
E
CT
U
R
E
T
h
e
s
y
s
te
m
ar
c
h
i
tect
u
r
e
is
illu
s
tr
ated
in
Fi
g
u
r
e
1
,
w
h
ich
i
s
co
m
p
o
s
ed
o
f
a
ce
n
tr
alize
d
co
m
p
u
ter
,
th
r
ee
m
o
b
ile
r
o
b
o
ts
w
it
h
m
o
d
u
les.
T
h
e
co
m
m
u
n
icat
io
n
tec
h
n
o
lo
g
y
b
et
w
ee
n
t
h
e
ce
n
tr
alize
d
co
m
p
u
ter
a
n
d
t
h
e
r
o
b
o
ts
is
R
F
tr
an
s
m
is
s
io
n
te
ch
n
o
lo
g
y
,
eli
m
i
n
ati
n
g
th
e
n
e
ed
o
f
cu
m
b
er
s
o
m
e
ca
b
le
lin
e
s
.
R
o
b
o
ts
A
a
n
d
B
ac
tiv
el
y
p
atr
o
l
f
o
r
f
ir
e
s
o
u
r
c
es
au
to
n
o
m
o
u
s
l
y
,
a
n
d
r
o
b
o
t
C
f
o
llo
w
s
t
h
e
co
m
m
a
n
d
f
r
o
m
th
e
ce
n
tr
alize
d
co
m
p
u
ter
to
lea
v
e
t
h
e
f
ir
e
s
ce
n
e.
R
o
b
o
t
A
d
etec
ts
th
e
lef
t
h
alf
o
f
th
e
p
latf
o
r
m
an
d
r
o
b
o
t
B
is
r
esp
o
n
s
ib
le
f
o
r
th
e
r
ig
h
t
h
alf
at
t
h
e
s
a
m
e
ti
m
e
Fig
u
r
e
1
.
S
y
s
te
m
ar
ch
itect
u
r
e
A
ll
r
o
b
o
ts
w
it
h
m
u
ltip
le
m
o
d
u
les
w
h
ic
h
ar
e
I
R
,
f
la
m
e
s
e
n
s
o
r
,
R
F
an
d
en
co
d
er
m
o
d
u
le
i
s
s
h
o
w
n
in
Fig
u
r
e
2
.
I
n
I
R
m
o
d
u
le,
th
er
e
ar
e
f
iv
e
C
NY7
0
an
d
th
r
ee
I
R
s
en
s
o
r
s
e
m
b
ed
d
ed
in
m
o
b
ile
r
o
b
o
ts
to
d
etec
t
o
b
s
tacle
s
.
T
o
m
a
k
e
s
u
r
e
it’s
co
llis
io
n
-
f
r
ee
in
s
y
s
te
m
,
w
e
p
u
t
t
h
e
t
h
r
ee
r
ef
lec
tiv
e
I
R
s
e
n
s
o
r
s
w
i
th
ef
f
ec
t
iv
e
d
etec
tin
g
le
n
g
t
h
b
et
w
ee
n
1
0
cm
an
d
4
0
c
m
o
n
t
h
e
r
ig
h
t
s
id
e
,
f
r
o
n
t
s
id
e
an
d
le
f
t
s
id
e
to
d
ete
ct
o
b
s
tacle
s
.
T
h
e
i
m
a
g
e
s
e
n
s
o
r
,
R
2
8
6
8
,
is
u
s
ed
to
d
etec
t
f
ir
e
s
o
u
r
ce
in
f
la
m
e
s
e
n
s
o
r
m
o
d
u
le.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
R
A
I
SS
N:
2
0
8
9
-
4856
P
a
th
P
la
n
n
in
g
o
f th
e
F
ir
e
E
s
ca
p
in
g
S
ystem
u
s
in
g
A
ctive
Dete
ctio
n
Mo
d
u
le
(
Yin
g
-
Ya
o
Tin
g
)
23
Fig
u
r
e
2
.
B
lo
ck
d
iag
r
a
m
o
f
r
o
b
o
t
T
h
e
m
o
v
in
g
d
is
ta
n
ce
o
n
t
h
e
e
x
p
er
i
m
e
n
tal
p
lat
f
o
r
m
is
ca
lc
u
l
ated
b
y
t
h
e
en
co
d
er
m
o
d
u
le
o
f
th
e
DC
s
er
v
o
m
o
to
r
.
A
l
l
t
h
e
r
o
b
o
ts
p
atr
o
l
th
e
p
lat
f
o
r
m
a
u
to
n
o
m
o
u
s
l
y
.
A
s
s
o
o
n
a
s
a
f
ir
e
e
v
e
n
t
o
r
o
b
s
tacle
is
d
etec
ted
,
th
e
r
o
b
o
t
s
en
d
s
r
ea
l
ti
m
e
s
ig
n
als
o
f
I
D
co
d
e,
lo
ca
tio
n
,
an
d
o
r
ien
tatio
n
to
t
h
e
s
u
p
er
v
is
ed
co
m
p
u
ter
an
d
o
t
h
er
r
o
b
o
ts
.
W
h
en
ev
er
t
h
e
s
u
p
er
v
i
s
ed
co
m
p
u
ter
r
ec
ei
v
es
a
f
ir
e
alar
m
s
i
g
n
al
f
r
o
m
t
h
e
r
o
b
o
ts
,
it
d
e
m
a
n
d
s
o
th
er
r
o
b
o
ts
to
p
er
f
o
r
m
th
e
r
ec
h
ec
k
task
an
d
d
eter
m
i
n
e
w
h
et
h
er
th
e
f
ir
e
ev
en
t
is
h
ap
p
en
in
g
o
r
n
o
t.
T
h
e
r
o
b
o
t
s
ea
r
ch
th
e
en
tire
p
latf
o
r
m
a
s
s
h
o
w
n
i
n
Fig
u
r
e
3
(
a)
f
o
r
all
th
e
f
ir
e
s
o
u
r
ce
s
,
w
h
ic
h
is
th
e
n
u
s
ed
to
d
is
p
la
y
th
e
r
ea
l
ti
m
e
s
tatu
s
o
f
t
h
e
s
h
o
r
test
escap
i
n
g
p
ath
w
ith
1
3
X1
3
g
r
id
s
.
T
h
e
f
o
r
m
at
o
f
ea
ch
g
r
id
is
s
h
o
w
n
i
n
Fig
u
r
e
3
(
b
)
.
(
a)
P
latf
o
r
m
d
iag
r
a
m
(
b
)
C
ell
d
iag
r
a
m
Fig
u
r
e
3
.
2
D
E
x
p
er
im
e
n
tal
p
la
tf
o
r
m
3.
AL
G
O
RI
T
H
M
ANALYSI
S
3
.
1
.
G
a
us
s
ia
n 2
D
Dis
cr
et
e
P
ro
ba
bil
it
y
F
un
ct
io
n
T
h
e
Gau
s
s
ia
n
f
u
n
ctio
n
is
n
o
r
m
al
d
is
tr
ib
u
tio
n
a
n
d
p
r
esen
ts
n
ea
r
b
ell
-
s
h
ap
ed
g
r
ap
h
.
T
h
e
Gau
s
s
ia
n
f
u
n
ctio
n
is
a
s
m
o
o
th
in
g
o
p
er
ato
r
an
d
b
elo
n
g
s
to
a
s
y
m
m
etr
i
c
f
u
n
ctio
n
.
I
n
t
h
e
2
d
i
m
en
s
io
n
al
s
p
ac
e,
Gau
s
s
ia
n
p
r
o
b
a
b
ilit
y
f
u
n
ctio
n
i
s
d
ef
i
n
ed
as b
elo
w
(
1
)
:
2
2
2
2
2
2
1
)
,
(
y
x
e
y
x
g
(
1
)
w
h
er
e
:
x
: th
e
d
i
s
p
lace
m
e
n
t
f
r
o
m
th
e
o
r
ig
in
i
n
h
o
r
izo
n
tal
d
ir
ec
tio
n
y
: t
h
e
d
is
p
lace
m
e
n
t f
r
o
m
t
h
e
o
r
ig
in
i
n
v
er
tical
d
ir
ec
tio
n
σ
: stan
d
ar
d
d
ev
iatio
n
T
h
e
Gau
s
s
ia
n
2
-
D
f
i
lter
in
g
o
f
k
er
n
el
co
ef
f
icie
n
ts
ar
e
s
a
m
p
l
ed
f
r
o
m
t
h
e
Gau
s
s
ia
n
2
-
D
d
is
cr
ete
m
a
s
s
f
u
n
ctio
n
.
T
h
e
Gau
s
s
ia
n
co
n
v
o
lu
tio
n
co
e
f
f
ic
ien
t
s
ar
e
s
a
m
p
l
ed
f
r
o
m
th
e
2
-
D
Ga
u
s
s
ian
f
u
n
ctio
n
a
s
s
h
o
w
n
i
n
E
q
u
atio
n
1
.
T
h
e
5
X
5
k
er
n
e
l
co
ef
f
icien
ts
o
f
d
is
cr
ete
ap
p
r
o
x
i
m
at
io
n
to
Ga
u
s
s
ian
f
i
lter
i
s
lis
ted
i
n
T
ab
le.
1
w
h
ic
h
th
e
v
al
u
e
L
1
o
f
ce
n
ter
is
th
e
lar
g
est
o
n
e,
L
2
is
t
h
e
s
ec
o
n
d
,
L
3
,
L
4
…
an
d
s
o
o
n
.
T
h
e
d
an
g
er
v
alu
e
d
ec
r
ea
s
es f
r
o
m
t
h
e
ce
n
ter
to
o
u
ts
id
e
s
u
r
r
o
u
n
d
in
g
g
r
ad
u
al
l
y
.
T
h
e
Gau
s
s
ia
n
f
ilter
f
(
x
,
y
)
i
s
p
ar
t
o
f
t
h
e
s
p
atial
f
ilter
s
an
d
is
also
ca
lled
s
p
atia
l
co
n
v
o
l
u
tio
n
.
Ass
u
m
in
g
t
h
e
s
o
u
r
ce
i
n
f
o
r
m
a
tio
n
to
b
e
I
(
x
,
y
)
,
af
ter
co
n
v
o
lu
tin
g
,
w
e
ca
n
g
et
t
h
e
co
n
v
o
lu
ted
in
f
o
r
m
atio
n
g
(
x
,
y
)
.
T
h
is
o
p
er
atio
n
is
t
h
e
co
n
v
o
l
u
tio
n
p
r
esen
ted
in
E
q
u
at
io
n
(
2
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N:
2
0
89
-
4856
I
J
R
A
Vo
l.
6
,
No
.
1
,
Ma
r
ch
2
0
1
7
:
2
1
–
30
24
T
ab
le.
1
C
o
n
v
o
lu
tio
n
C
o
e
f
f
icie
n
ts
o
f
Dis
cr
ete
A
p
p
r
o
x
i
m
a
tio
n
to
Gau
s
s
ia
n
Fi
lter
L6
L5
L4
L5
L6
L5
L3
L2
L3
L5
L4
L2
L1
L2
L4
L5
L3
L2
L3
L5
L6
L5
L4
L5
L6
22
22
(
)
(
,
)
(
,
)
(
,
)
MM
MM
mn
p
d
g
i
j
I
m
n
f
i
m
j
n
(
2
)
I
n
s
tead
i
n
g
o
f
p
r
o
b
ab
ilit
y
d
en
s
it
y
f
u
n
ct
io
n
s
,
t
h
ese
d
is
cr
ete
v
ar
iab
les
ar
e
t
h
e
p
r
o
b
ab
ilit
y
m
a
s
s
f
u
n
ctio
n
w
h
ich
i
s
th
e
p
r
o
b
ab
ilit
y
to
r
ep
r
esen
t th
e
d
a
n
g
er
o
u
s
v
alu
e
s
atis
f
y
i
n
g
t
h
e
p
r
o
p
er
ties
o
f
0
p
(
d
)
a
n
d
11
()
nn
ji
pd
=
1
.
B
ay
e
s
ian
esti
m
atio
n
m
eth
o
d
p
r
o
v
id
es
a
r
u
le
o
f
f
o
r
m
a
lis
m
to
m
er
g
e
s
en
s
o
r
y
i
n
f
o
r
m
atio
n
o
f
m
u
l
tip
le
s
en
s
o
r
s
ac
co
r
d
in
g
t
h
e
p
r
o
b
ab
i
lit
y
t
h
eo
r
y
.
T
h
e
co
n
d
itio
n
al
p
r
o
b
ab
ilit
y
,
P
(
Y
|
X)
,
e
x
is
t
s
i
n
th
e
r
an
g
e
o
f
0
an
d
1
.
B
ay
e
s
’
r
u
le
is
t
h
e
b
asis
o
f
B
a
y
esian
al
g
o
r
ith
m
(
3
)
:
(
|
)
(
)
(
|
)
()
P
X
Y
P
Y
P
Y
X
PX
(
3
)
w
h
er
e
X
is
th
e
g
iv
e
n
in
f
o
r
m
at
io
n
,
h
y
p
o
th
e
s
is
Y
a
n
d
w
e
ca
lc
u
late
th
e
p
o
s
ter
io
r
p
r
o
b
ab
ilit
y
,
P
(
Y
|
X)
ac
co
r
d
in
g
to
th
e
X
an
d
Y.
T
h
e
p
o
s
ter
io
r
p
r
o
b
a
b
ilit
y
is
co
m
p
u
ted
b
y
m
u
ltip
l
y
i
n
g
t
h
e
p
r
io
r
p
r
o
b
a
b
ilit
y
ass
o
ciate
d
w
it
h
Y,
P
(
Y)
,
b
y
t
h
e
li
k
elih
o
o
d
f
o
r
P
(
X
|
Y)
s
h
o
w
n
i
n
E
q
u
atio
n
(
4
)
u
s
in
g
X
an
d
Y
.
T
h
e
r
ed
u
n
d
an
t
in
f
o
r
m
atio
n
ca
n
b
e
m
er
g
ed
u
s
i
n
g
lik
eli
h
o
o
d
r
atio
f
o
r
m
u
latio
n
an
d
th
e
o
d
d
s
o
f
B
ay
es
’
r
u
le.
T
h
e
i
n
f
o
r
m
atio
n
d
en
o
te
d
as
X
i
r
elati
n
g
Y
f
r
o
m
S
i
i
s
ch
ar
ac
ter
ized
b
y
P
(
X
i
|
Y)
an
d
t
h
e
li
k
eli
h
o
o
d
P
(
X
i
|
-
Y)
g
i
v
e
n
th
e
n
eg
at
io
n
o
f
Y,
o
r
b
y
t
h
e
li
k
elih
o
o
d
r
atio
(
4
)
:
(
|
)
(
|
)
(
|
)
i
i
i
P
X
Y
L
X
Y
P
X
Y
(
4
)
Def
i
n
i
n
g
t
h
e
p
r
io
r
o
d
d
s
o
n
Y
a
s
b
elo
w
(
5
)
:
()
()
(
Y
)
PY
OY
P
(
5
)
E
ac
h
s
e
n
s
o
r
is
in
d
ep
en
d
e
n
t
m
u
tu
al
l
y
to
t
h
e
o
t
h
er
s
en
s
o
r
s
.
Fro
m
t
h
e
i
n
f
o
r
m
atio
n
X1
,
X2
….
Xn
o
f
t
h
e
n
s
en
s
o
r
s
,
th
e
p
o
s
ter
io
r
o
d
d
s
o
n
Y
g
i
v
en
b
y
t
h
e
p
r
o
d
u
ct
o
f
lik
e
lih
o
o
d
s
h
o
w
n
a
s
b
elo
w
(
6
)
:
12
1
(
|
,
.
.
.
)
(
)
(
|
)
n
ni
i
O
Y
X
X
X
O
Y
L
X
Y
(
6
)
T
h
e
p
o
s
ter
io
r
o
d
d
s
ar
e
r
elate
d
to
th
e
p
o
s
ter
io
r
p
r
o
b
ab
ilit
y
b
y
(
7
)
:
12
12
12
(
|
,
X
.
.
.
)
P
(
Y
|
X
,
.
.
.
.
.
)
1
(
|
X
,
.
.
.
)
n
n
n
O
Y
X
X
XX
O
Y
X
X
(
7
)
W
e
tak
e
an
ex
a
m
p
le
to
co
m
p
u
te
th
e
d
an
g
er
v
a
lu
e
o
f
all
p
o
in
t
f
o
r
f
ir
e
ev
e
n
t
Y.
T
h
e
f
i
r
e
ev
en
t
i
s
h
ap
p
en
ed
as
t
w
o
f
ir
e
s
o
u
r
ce
s
d
ef
in
ed
X
1
an
d
X
2
.
W
e
co
m
p
u
te
th
e
d
an
g
er
p
r
o
b
ab
ilit
y
v
a
l
u
es
o
f
p
o
in
t
f
o
r
t
w
o
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
R
A
I
SS
N:
2
0
8
9
-
4856
P
a
th
P
la
n
n
in
g
o
f th
e
F
ir
e
E
s
ca
p
in
g
S
ystem
u
s
in
g
A
ctive
Dete
ctio
n
Mo
d
u
le
(
Yin
g
-
Ya
o
Tin
g
)
25
f
ir
es
s
o
u
r
ce
s
as
P
(
X
1
|
Y)
=
0
.
7
5
an
d
P
(X
2
|
Y)
=0
.
2
5
.
W
e
ca
lc
u
late
th
e
p
o
s
ter
io
r
o
d
d
s
an
d
p
o
s
ter
io
r
p
r
o
b
ab
ilit
y
o
f
th
e
p
o
in
t
(8
-
9)
,
12
12
12
(
|
)
(
|
)
(
|
,
)
(
|
)
(
|
)
P
X
Y
P
X
Y
O
Y
X
X
P
X
Y
P
X
Y
(
8
)
=
(
0
.
7
5
/0
.
2
5
)
(
0
.
2
5
/0
.
7
5
)
=1
12
12
12
(
|
,
X
)
P
(
Y
|
X
,
)
1
(
|
X
,
)
O
Y
X
X
O
Y
X
(
9
)
1
0
.
5
11
T
h
e
p
o
s
ter
io
r
p
r
o
b
ab
ilit
y
v
al
u
e
is
0
.
5
f
o
r
th
e
p
o
in
t.
A
n
d
w
e
n
ee
d
to
ca
lc
u
late
t
h
e
v
alu
es
o
f
p
o
s
ter
io
r
p
r
o
b
a
b
ilit
y
f
o
r
th
e
r
e
s
t
p
o
in
t
s
o
f
p
latf
o
r
m
.
T
h
e
i
n
cr
ea
s
i
n
g
te
m
p
er
at
u
r
e
(
△
T
)
w
ith
d
is
ta
n
ce
v
ar
ian
ce
(
△
X)
,
,
an
d
th
e
air
-
f
u
el
m
as
s
r
atio
ar
e
d
ir
ec
tl
y
p
r
o
p
o
r
tio
n
al
to
th
e
d
an
g
er
v
alu
e
s
.
T
h
e
lo
w
er
th
e
v
al
u
e
o
f
is
,
t
h
e
s
af
er
it
is
.
An
i
n
cr
ea
s
e
in
th
e
v
alu
e
o
f
△
T
,
ch
an
g
e
i
n
te
m
p
e
r
atu
r
e,
m
ea
n
s
it
is
clo
s
i
n
g
in
o
n
t
h
e
f
ir
e
s
o
u
r
ce
.
I
f
<
0
it is
s
af
e,
o
th
er
w
i
s
e,
it is
d
an
g
er
o
u
s
-
clo
s
i
n
g
i
n
o
n
t
h
e
f
ir
e
s
o
u
r
ce
.
3
.
2
.
J
o
int
P
ro
ba
bil
it
y
I
n
a
r
ea
l
ca
s
e
s
ce
n
ar
io
,
it
is
p
o
s
s
ib
le
f
o
r
s
e
v
er
al
f
ir
e
e
v
e
n
ts
to
h
ap
p
en
s
i
m
u
l
tan
eo
u
s
l
y
.
W
e
u
s
e
j
o
in
t
p
r
o
b
a
b
ilit
y
to
r
ep
r
esen
t
th
e
d
an
g
er
v
a
lu
e
s
o
f
p
o
in
ts
w
it
h
i
n
t
h
e
in
ter
ac
ti
n
g
ar
ea
f
o
r
s
ev
er
al
f
ir
e
ev
en
ts
.
Fo
r
all
f
ir
e
ev
e
n
t
s
,
th
e
y
ar
e
m
u
t
u
al
l
y
i
n
d
ep
en
d
en
t
to
ea
c
h
o
th
e
r
.
T
h
u
s
,
w
h
e
n
t
w
o
f
ir
es
s
o
u
r
ce
s
i
n
ter
ac
t,
th
e
p
r
o
b
a
b
ilit
y
o
f
t
h
e
d
an
g
er
v
al
u
es
ch
a
n
g
e.
F
1
a
n
d
F
2
s
ta
n
d
f
o
r
f
ir
e
s
o
u
r
ce
1
an
d
f
ir
e
s
o
u
r
c
e
2
.
A
n
d
th
e
P
(
F
1
)
r
ep
r
esen
ts
t
h
e
p
r
o
b
ab
ilit
y
o
f
th
e
d
an
g
er
v
alu
e
f
o
r
F
1
.
A
f
te
r
in
ter
ac
ti
n
g
,
th
e
f
i
n
al
p
r
o
b
ab
ilit
y
o
f
t
h
e
d
an
g
er
v
alu
e
i
s
ca
lc
u
lated
u
s
in
g
E
q
u
a
tio
n
(
10
)
.
2
1
2
1
2
1
2
1
2
1
F
P
F
P
F
P
F
P
F
F
P
F
P
F
P
F
F
P
(
1
0
)
Fig
u
r
e
4
s
h
o
w
s
th
e
d
is
tr
ib
u
ti
o
n
o
f
th
e
n
o
n
ze
r
o
d
an
g
er
v
al
u
es
f
o
r
ea
c
h
p
o
in
t
in
th
e
p
lat
f
o
r
m
w
h
ile
o
th
er
s
s
ta
n
d
f
o
r
ze
r
o
if
it
d
o
es
n
o
t
s
h
o
w
a
n
y
t
h
in
g
.
A
ll
t
h
e
p
r
o
b
a
b
ilit
y
v
al
u
es
s
h
o
w
n
i
n
Fig
u
r
e
4
s
h
o
u
ld
b
e
d
iv
id
ed
b
y
2
7
3
.
Fro
m
Fig
u
r
e
4
(
b
)
,
th
e
ce
n
ter
o
f
f
ir
e
s
o
u
r
ce
o
n
e
a
n
d
t
w
o
ar
e
p
o
i
n
t
s
(
5
,
6
)
an
d
(
8
,
7
)
r
esp
ec
tiv
el
y
.
T
o
tally
,
th
er
e
ar
e
8
p
o
in
ts
w
i
th
in
th
e
in
ter
ac
ti
o
n
ar
ea
,
an
d
t
h
e
co
o
r
d
in
ates
a
r
e
(
7
,
7
)
,
(
6
,
6
)
,
(
6
,
7
)
,
(
7
,
6
)
,
(
6
,
5
)
,
(
7
,
8
)
,
(
7
,
5
)
,
an
d
(
6
,
8
)
.
Af
ter
i
n
ter
ac
ti
n
g
,
th
e
n
e
w
d
a
n
g
er
v
alu
e
s
o
f
t
h
e
p
o
in
ts
l
is
ted
ab
o
v
e
ar
e
u
p
d
ated
u
s
in
g
E
q
u
a
tio
n
4
.
T
h
e
p
o
in
ts
(
7
,
7
)
an
d
(
6
,
6
)
ar
e
o
n
le
v
el_
2
in
T
ab
le
3
w
h
i
ch
m
ea
n
s
t
h
e
n
e
w
d
an
g
er
v
alu
e
is
3
0
/2
7
3
.
T
h
e
(
6
,
7
)
an
d
(
7
,
6
)
p
o
in
ts
ar
e
o
n
le
v
el_
4
w
h
ic
h
m
ea
n
s
t
h
e
n
e
w
d
a
n
g
er
v
al
u
e
is
2
3
/2
7
3
.
A
ls
o
,
(
6
,
5
)
an
d
(
7
,
8
)
ar
e
o
n
L
ev
e
l_
5
w
h
ic
h
m
ea
n
s
th
e
n
e
w
d
a
n
g
er
v
al
u
e
i
s
1
7
/2
7
3
.
T
h
e
last
p
air
i
s
(
7
,
5
)
an
d
(
6
,
8
)
,
w
h
ic
h
ar
e
o
n
L
ev
e
l_
7
,
m
e
a
n
i
n
g
th
e
n
e
w
d
a
n
g
er
v
alu
e
i
s
8
/2
7
3
.
Fo
r
ex
am
p
le,
th
e
n
e
w
v
alu
e
o
f
(
7
,
7
)
is
P
(
F1
)
+
P
(
F2
)
-
P
(
F1
)
‧
P
(
F2
)
=
(
2
6
+
4
-
2
6
*
4
/2
7
3
)
/2
7
3
=3
0
/2
7
3
.
T
h
e
p
latf
o
r
m
is
d
r
a
w
n
i
n
th
r
ee
d
if
f
er
en
t
r
ad
iu
m
cir
cles,
i.e
.
,
r
,
2
r
an
d
3
r
,
w
h
ich
s
ta
n
d
f
o
r
d
if
f
er
en
t
d
an
g
er
lev
el
s
.
T
h
e
m
o
s
t
d
an
g
e
r
o
u
s
n
o
d
e
is
th
e
ce
n
ter
o
f
th
e
r
ed
cir
cle
an
d
it
is
s
af
e
if
th
e
d
i
s
tan
ce
o
f
t
h
e
p
o
in
t
is
b
e
y
o
n
d
th
e
3
r
cir
cle
f
r
o
m
t
h
e
ce
n
ter
w
h
er
e
th
e
d
a
n
g
er
v
alu
e
is
ze
r
o
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N:
2
0
89
-
4856
I
J
R
A
Vo
l.
6
,
No
.
1
,
Ma
r
ch
2
0
1
7
:
2
1
–
30
26
(
a)
Sin
g
le
f
ir
e
s
o
u
r
ce
(
b
)
Do
u
b
le
f
ir
e
s
o
u
r
ce
Fig
u
r
e
4
.
Dis
tr
ib
u
tio
n
E
x
a
m
p
l
e
o
f
Dan
g
er
Valu
e
s
w
it
h
μ
=0
an
d
σ
=
3
.
3
.
Weig
hte
d E
s
t
i
m
a
t
io
n Va
l
ue
t
(
n)
T
h
e
v
alu
es
lis
ted
i
n
T
ab
le
1
ar
e
all
th
e
d
an
g
er
v
al
u
e
s
o
f
co
o
r
d
in
ates.
I
n
o
r
d
er
to
em
p
h
asize
t
h
e
d
if
f
er
e
n
ce
b
et
w
ee
n
d
an
g
er
an
d
s
af
et
y
,
w
e
u
s
e
t
h
e
w
ei
g
h
ted
v
alu
e
t(
n
)
o
f
d
an
g
er
v
al
u
es
d
i
v
id
ed
b
y
le
v
el_
5
o
r
lev
el_
9
f
o
r
s
in
g
le
s
o
u
r
ce
f
ir
e
e
v
en
t
s
o
r
t
w
o
s
o
u
r
ce
f
ir
e
ev
e
n
t
s
.
Fo
r
s
in
g
le
s
o
u
r
ce
f
ir
e
ev
e
n
t,
t
h
e
w
ei
g
h
ted
v
al
u
e
t(
n
)
is
o
b
tai
n
ed
u
s
in
g
E
q
u
atio
n
(
11
)
.
A
n
d
th
e
lis
tin
g
o
f
w
eig
h
ted
v
a
lu
e
s
is
s
h
o
w
n
in
T
ab
le
2
.
Fo
r
tw
o
s
o
u
r
ce
f
i
r
e
ev
en
t
s
,
th
e
w
ei
g
h
ted
v
al
u
e
t(
n
)
is
ca
lc
u
lated
u
s
i
n
g
E
q
u
atio
n
(
12
)
.
Fu
r
th
er
,
t
h
e
n
e
w
d
a
n
g
er
v
a
lu
e
a
f
ter
in
te
r
ac
tin
g
ar
e
li
s
ted
in
T
ab
le.
3
.
W
eig
h
t
ed
Val
u
e
alue
da
ng
e
r
L
e
v
e
l
v
alue
da
ng
e
r
n
t
v
)
(
5
(
1
1
)
W
eig
h
ted
Val
u
e
v
alue
da
ng
e
r
L
e
v
e
l
v
alue
da
ng
e
r
n
t
)
(
9
(
1
2
)
3
.
4
.
A*
Sea
rc
hin
g
Alg
o
rit
h
m
I
n
t
h
is
s
ec
u
r
it
y
s
y
s
te
m
,
th
e
alg
o
r
ith
m
w
e
u
s
e
is
a
n
A*
s
ea
r
ch
in
g
al
g
o
r
ith
m
to
f
in
d
th
e
s
h
o
r
tes
t
escap
in
g
p
ath
.
A
n
d
t
h
e
f
(
n
)
v
a
lu
e
o
f
t
h
e
n
o
d
e
(
i,
j
)
is
ca
lcu
lated
u
s
in
g
E
q
u
atio
n
(
13
)
.
f(
n
)
=g
(
n
)
+h
(
n
)
+t
(
n
)
(
1
3
)
w
h
er
e
:
f
: t
h
e
to
tal
esti
m
ated
v
al
u
e
o
f
th
e
cu
r
r
en
t
n
o
d
e
g
: th
e
d
is
p
lace
m
e
n
t f
r
o
m
t
h
e
s
tar
t n
o
d
e
to
th
e
cu
r
r
en
t
n
o
d
e
h
: th
e
p
r
ed
icted
d
is
p
lace
m
en
t
f
r
o
m
th
e
c
u
r
r
en
t
n
o
d
e
to
th
e
tar
g
et
n
o
d
e
t: th
e
r
elativ
e
w
ei
g
h
ted
v
al
u
e
o
f
d
an
g
er
v
al
u
e.
W
e
g
iv
e
an
e
x
a
m
p
le
to
ill
u
s
tr
ate
th
e
p
la
n
n
in
g
o
f
t
h
e
escap
i
n
g
p
ath
a
f
ter
s
ea
r
c
h
in
g
f
o
r
f
ir
es,
as s
h
o
wn
in
Fig
u
r
e
5
.
W
e
g
et
th
e
3
f
ir
e
s
o
u
r
ce
s
w
h
ic
h
ar
e
lo
ca
ted
at
(
2
,
7
)
,
(
9
,
5
)
,
an
d
(
1
2
,
1
0
)
.
T
h
e
s
tar
ti
n
g
p
o
in
t
is
S
(
7
,
8
)
an
d
th
e
tar
g
et
p
o
in
t is T
(
7
,
1
)
.
T
h
e
o
b
s
tacle
s
ex
i
s
t i
n
t
h
e
f
o
llo
w
i
n
g
p
o
s
itio
n
s
: (
3
,
6
)
,
(
4
,
4
)
,
(
4
,
6
)
,
(
6
,
2
)
,
(
6
,
5
)
,
(
7
,
6
)
,
(
8
,
1
)
,
(
1
0
,
4
)
,
(
1
1
,
4
)
,
(
1
1
,
7
)
,
(
1
1
,
8
)
.
Fo
r
all
th
e
o
b
s
tacle
s
p
lo
tted
w
it
h
g
r
a
y
co
lo
r
in
t
h
e
p
latf
o
r
m
,
w
e
s
et
t
h
e
w
ei
g
h
ted
v
alu
e
t a
s
2
0
0
m
ea
n
i
n
g
i
t is
m
u
ch
m
o
r
e
d
if
f
icu
lt to
p
ass
th
r
o
u
g
h
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
R
A
I
SS
N:
2
0
8
9
-
4856
P
a
th
P
la
n
n
in
g
o
f th
e
F
ir
e
E
s
ca
p
in
g
S
ystem
u
s
in
g
A
ctive
Dete
ctio
n
Mo
d
u
le
(
Yin
g
-
Ya
o
Tin
g
)
27
T
ab
le
2
.
W
eig
h
ted
Valu
e
t(
n
)
f
o
r
Sin
g
le
Fire
So
u
r
ce
L
e
v
e
l
#
D
a
n
g
e
r
V
a
l
u
e
s
W
e
i
g
h
t
e
d
V
a
l
u
e
t
(
n
)
L
e
v
e
l
_
1
L1
L
1
/
L
5
=
L
1
1
L
e
v
e
l
_
2
L2
L
2
/
L
5
=
L
1
2
L
e
v
e
l
_
3
L3
L
3
/
L
5
=
L
1
3
L
e
v
e
l
_
4
L4
L
4
/
L
5
=
L
1
4
L
e
v
e
l
_
5
L5
L
1
5
L
e
v
e
l
_
6
L6
L
6
/
L
5
=
L
1
6
T
ab
le
3
.
T
w
o
Fire
So
u
r
ce
s
I
n
t
er
ac
tio
n
w
ith
W
ei
g
h
ted
Valu
e
L
e
v
e
l
#
D
a
n
g
e
r
V
a
l
u
e
s
W
e
i
g
h
t
e
d
V
a
l
u
e
t
(
n
)
L
e
v
e
l
_
1
L1
L
1
/
L
9
=
L
2
1
L
e
v
e
l
_
2
L2
L
2
/
L
9
=
L
2
2
L
e
v
e
l
_
3
L3
L
3
/
L
9
=
L
2
3
L
e
v
e
l
_
4
L4
L
4
/
L
9
=
L
2
4
L
e
v
e
l
_
5
L5
L
5
/
L
9
=
L
2
5
L
e
v
e
l
_
6
L6
L
6
/
L
9
=
L
2
6
L
e
v
e
l
_
7
L7
L
7
/
L
9
=
L
2
7
L
e
v
e
l
_
8
L8
L
8
/
L
9
=
L
2
8
L
e
v
e
l
_
9
L9
L
2
9
L
e
v
e
l
_
1
0
L
1
0
L
1
0
/
L
9
=
L
2
1
0
(
a)
I
n
itial d
iag
r
a
m
(
b
)
Diag
r
a
m
w
it
h
s
h
o
r
test
p
ath
Fig
u
r
e
5
.
Dis
tr
ib
u
tio
n
o
f
d
an
g
er
v
alu
es
w
ith
j
o
in
t p
r
o
b
ab
ilit
y
4.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
W
h
en
e
v
er
d
etec
ti
n
g
th
e
f
ir
e
s
o
u
r
ce
,
t
h
e
r
o
b
o
t
s
en
d
s
t
h
e
r
elate
d
in
f
o
r
m
atio
n
to
t
h
e
s
u
p
er
v
i
s
ed
co
m
p
u
ter
a
n
d
o
th
er
r
o
b
o
ts
.
Af
ter
it
is
co
n
f
ir
m
ed
,
th
e
th
r
ee
f
ir
e
s
o
u
r
ce
s
i
n
o
u
r
e
x
a
m
p
le
w
er
e
lo
ca
ted
at
t
h
e
p
o
s
itio
n
s
(
2
,
7
)
,
(
9
,
5
)
,
an
d
(
1
2
,
1
0
)
w
i
th
a
d
an
g
er
v
a
lu
e
L
1
.
T
h
er
e
ar
e
3
cir
cles
in
3
co
lo
r
s
f
o
r
ea
ch
f
ir
e
ce
n
ter
s
h
o
w
n
i
n
Fi
g
u
r
e
5
.
T
h
e
ce
n
tr
ali
ze
d
co
m
p
u
ter
ca
lcu
late
s
th
e
d
an
g
er
v
al
u
es
f
o
r
th
e
ad
j
ac
en
t
n
o
d
es
o
f
3
f
ir
e
ce
n
ter
s
.
E
s
p
ec
iall
y
,
it
ca
lcu
la
t
es
th
e
d
an
g
er
v
al
u
es
o
f
th
e
i
n
t
er
ac
tin
g
ar
ea
b
y
j
o
in
t
p
r
o
b
ab
il
it
y
.
A
ll
t
h
e
d
an
g
er
v
alu
e
s
ar
e
s
h
o
w
n
in
Fi
g
u
r
e
5
.
T
h
en
,
th
e
s
u
p
er
v
i
s
ed
co
m
p
u
t
er
in
itiat
e
s
t
h
e
p
lan
n
i
n
g
o
f
t
h
e
s
h
o
r
test
p
at
h
f
r
o
m
S.
Usi
n
g
t
h
e
A*
a
lg
o
r
it
h
m
,
th
e
s
u
p
er
v
is
ed
co
m
p
u
ter
ca
l
cu
lates
t
h
e
g
(
n
)
,
h
(
n
)
,
an
d
w
ei
g
h
ted
v
al
u
e
t(
n
)
in
d
iv
id
u
all
y
.
T
h
en
,
w
e
ca
lcu
late
th
e
d
an
g
er
v
al
u
e
an
d
weig
h
ted
v
alu
e
o
f
t
h
e
d
an
g
er
co
s
t
o
f
ea
ch
n
o
d
e.
Fin
all
y
,
t
h
ese
v
a
lu
e
s
ar
e
s
u
m
m
ed
u
p
u
s
in
g
t
h
e
h
e
u
r
is
tic
f
u
n
ct
io
n
f
(
n
)
o
f
th
e
i
m
p
le
m
en
ted
n
o
d
e
(
i,
j
)
.
T
h
e
ce
n
tr
alize
d
co
m
p
u
ter
s
elec
t
t
h
e
m
i
n
i
m
u
m
co
s
t
f
as
s
h
o
w
n
in
Fig
u
r
e
6
(
b
)
f
r
o
m
all
ad
j
ac
en
t
n
o
d
es
to
b
e
th
e
ex
ten
s
io
n
n
o
d
e
o
f
th
e
s
h
o
r
test
p
ath
f
r
o
m
t
h
e
s
tar
ti
n
g
n
o
d
e
to
th
e
tar
g
et
n
o
d
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N:
2
0
89
-
4856
I
J
R
A
Vo
l.
6
,
No
.
1
,
Ma
r
ch
2
0
1
7
:
2
1
–
30
28
(
a)
Star
t n
o
d
e
S (
7
,
8
)
(
b
)
A
d
d
in
(
6
,
8
)
,
(
6
,
7
)
,
(
7
,
9
)
,
(
7
,
7
)
(
c)
A
d
d
in
(
6
,
9
)
,
(
8
,
9
)
(
d
)
A
d
d
in
(
6
,
6
)
,
(
5
,
6
)
,
(
5
,
9
)
(
e)
A
d
d
in
(
5
,
5
)
,
(
5
,
4
)
,
(
5
,
3
)
(
f
)
A
d
d
in
(
6
,
3
)
,
(
7
,
3
)
,
(
7
,
2
)
,
T
(
g
)
Dis
ca
r
d
(
5
,
9
)
,
(
6
,
9
)
,
(
7
,
9
)
,
(
8
,
9)
,
(
7
,
7
)
Fig
u
r
e
6
.
C
o
n
s
tr
u
ct
p
r
o
ce
s
s
in
g
f
r
o
m
(
a)
I
n
itial to
(
g
)
th
e
f
i
n
al
s
h
o
r
test
escap
i
n
g
p
at
h
Fro
m
th
e
s
tar
ti
n
g
p
o
in
t
S,
w
e
ca
lcu
late
all
th
e
f
v
al
u
es
o
f
ad
j
ac
en
t
n
o
d
es
o
f
S
u
s
in
g
t
h
e
A*
s
ea
r
ch
i
n
g
alg
o
r
ith
m
s
h
o
w
n
i
n
F
ig
u
r
e
6
(
a)
,
an
d
w
e
s
elec
t
th
e
s
m
alle
s
t
f
v
alu
e
to
b
e
th
e
ex
te
n
s
io
n
n
o
d
e.
T
h
e
s
eq
u
en
ce
o
f
ex
ten
s
io
n
n
o
d
es
f
r
o
m
S
(
7
,
8
)
,
(
6
,
8
)
,
(
6
,
7
)
,
(
7
,
9
)
to
(
7
,
7
)
is
th
e
p
r
ev
io
u
s
p
r
o
ce
s
s
in
g
f
o
r
f
in
a
l
s
h
o
r
test
escap
in
g
p
at
h
,
as
s
h
o
w
n
i
n
Fi
g
u
r
e
6
(
b
)
.
Fro
m
n
o
d
e
(
6
,
6
)
in
Fi
g
u
r
e
6
(
c)
,
th
er
e
ar
e
t
w
o
n
o
d
es
w
it
h
a
n
f
v
al
u
e
o
f
1
l,
lo
w
er
t
h
a
n
t
h
at
o
f
n
o
d
e
(
6
,
6
)
.
T
h
en
,
w
e
n
ee
d
to
g
o
b
ac
k
to
s
u
r
v
e
y
(
6
,
9
)
an
d
(
8
,
9
)
w
i
th
a
n
f
v
al
u
e
o
f
1
1
.
T
h
u
s
,
(
6
,
9
)
an
d
(
8
,
9
)
ar
e
in
s
er
ted
in
to
th
e
C
lo
s
ed
lis
t
as
ex
ten
s
io
n
n
o
d
es
a
s
s
h
o
w
n
in
Fig
u
r
e
6
(
c)
.
I
n
Fig
u
r
e
6
(
d
)
,
af
ter
n
o
d
e
(
6
,
6
)
w
it
h
f
=1
2
,
w
e
n
ee
d
to
v
i
s
it
n
o
d
e
(
5
,
9
)
w
it
h
f
=
1
3
.
T
h
en
,
th
er
e
ar
e
3
n
o
d
es a
d
j
ac
en
t to
t
h
e
p
r
ev
io
u
s
ex
te
n
s
io
n
n
o
d
es
w
i
th
th
e
s
a
m
e
f
v
al
u
e
o
f
1
4
,
i.e
.
,
(
5
,
8
)
,
(
5
,
7
)
,
(
5
,
6
)
.
I
n
o
r
d
er
to
f
in
d
t
h
e
s
h
o
r
test
p
at
h
,
w
e
s
ele
ct
th
e
n
o
d
e
clo
s
es
t
to
T
w
h
ic
h
i
s
n
o
d
e
(
5
,
6
)
in
Fig
u
r
e
6
(
d
)
.
So
,
(
6
,
6
)
,
(
5
,
9
)
,
an
d
(
5
,
6
)
ar
e
th
e
s
eq
u
en
ce
o
f
ex
te
n
s
io
n
n
o
d
es
as
s
h
o
w
n
in
Fi
g
u
r
e
6
(
d
)
.
T
h
e
n
o
d
es (
5
,
6
)
,
(
5
,
5
)
,
(
5
,
4
)
,
an
d
(
5
,
3
)
ar
e
th
e
s
eq
u
e
n
ce
o
f
e
x
t
en
s
io
n
n
o
d
es
w
it
h
th
e
lo
w
est
f
v
al
u
es
as
s
h
o
w
n
i
n
Fig
u
r
e
6
(
e)
.
Fro
m
n
o
d
e
(
5
,
3
)
,
th
e
ex
te
n
s
io
n
n
o
d
e
is
(
6
,
3
)
w
it
h
t
h
e
lo
w
e
s
t
f
v
alu
e,
9
.
T
h
en
,
n
o
d
es
(
7
,
3
)
an
d
(
7
,
2
)
ar
e
th
e
ex
ten
s
io
n
n
o
d
es
s
ee
n
i
n
Fi
g
u
r
e
6
(
f
)
.
T
h
e
last
n
o
d
e
is
t
h
e
d
esti
n
atio
n
n
o
te
T
(
7
,
1
)
w
it
h
t
h
e
lo
w
es
t
f
v
a
lu
e
o
f
7
as
s
ee
n
in
Fi
g
u
r
e
6
(
f
)
.
Fin
a
ll
y
,
w
e
n
ee
d
to
ch
ec
k
th
e
s
eq
u
e
n
ce
o
f
ex
te
n
s
io
n
n
o
d
es.
A
lt
h
o
u
g
h
w
e
ch
o
o
s
e
t
h
e
n
o
d
es
w
ith
t
h
e
lo
w
est
f
v
a
lu
e
s
,
b
u
t
s
o
m
e
o
f
t
h
e
m
s
h
o
u
ld
b
e
d
is
ca
r
d
ed
f
r
o
m
t
h
e
escap
in
g
p
ath
f
o
r
th
e
y
ar
e
n
eit
h
er
co
n
tin
u
o
u
s
n
o
r
d
o
th
e
y
ex
is
t
in
t
h
e
escap
in
g
p
ath
.
So
,
all
th
e
n
o
d
es
m
ar
k
ed
b
lu
e
f
r
o
m
S to
T
is
th
e
s
h
o
r
tes
t e
s
ca
p
in
g
p
ath
as s
h
o
w
n
in
F
i
g
u
r
e
6
(
g
)
.
T
h
er
e
ar
e
tw
o
k
in
d
s
o
f
g
r
ap
h
ic
s
ea
r
ch
in
g
alg
o
r
it
h
m
s
,
b
lin
d
s
ea
r
ch
an
d
h
eu
r
is
tic
s
ea
r
ch
.
T
h
e
m
o
s
t
f
a
m
o
u
s
s
ea
r
c
h
in
g
is
D
ij
k
s
tr
a
alg
o
r
ith
m
in
b
lin
d
s
ea
r
ch
w
h
i
ch
i
s
n
o
t
s
o
e
f
f
icie
n
t
a
n
d
co
m
p
u
tin
g
co
m
p
lex
i
t
y
.
Op
p
o
s
itel
y
,
h
eu
r
i
s
tic
in
f
o
r
m
a
tio
n
i
s
u
s
ed
i
n
h
e
u
r
is
t
ic
m
et
h
o
d
to
ch
o
o
s
e
th
e
b
est
n
o
d
e
f
r
o
m
c
u
r
r
en
t
s
et
to
ex
ten
d
th
e
p
ath
.
I
t
i
m
p
r
o
v
es
t
h
e
in
tell
ig
e
n
ce
an
d
ef
f
icie
n
c
y
d
u
r
in
g
th
e
s
ea
r
c
h
i
n
g
.
T
h
e
p
a
th
f
in
d
i
n
g
alg
o
r
ith
m
w
e
u
s
e
i
s
A*
al
g
o
r
ith
m
.
A*
s
ea
r
ch
in
g
al
g
o
r
ith
m
is
o
n
e
o
f
w
id
el
y
u
s
ed
h
e
u
r
is
tic
f
u
n
ctio
n
to
f
i
n
d
t
h
e
s
h
o
r
tes
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
R
A
I
SS
N:
2
0
8
9
-
4856
P
a
th
P
la
n
n
in
g
o
f th
e
F
ir
e
E
s
ca
p
in
g
S
ystem
u
s
in
g
A
ctive
Dete
ctio
n
Mo
d
u
le
(
Yin
g
-
Ya
o
Tin
g
)
29
p
ath
.
A*
i
s
s
i
m
i
lar
to
Dij
k
s
tr
a
’
s
al
g
o
r
ith
m
w
h
ic
h
i
s
A*
a
lg
o
r
ith
m
w
it
h
o
u
t
h
e
u
r
is
tic
f
u
n
ct
i
o
n
to
f
i
n
d
a
s
h
o
r
te
s
t
p
ath
.
A*
is
li
k
e
Gr
ee
d
y
B
est
-
Firs
t
-
Sear
ch
i
n
u
s
in
g
a
h
e
u
r
is
tic
to
g
u
id
e
its
el
f
.
T
h
e
A*
s
ea
r
ch
i
n
g
n
o
t
o
n
l
y
in
h
er
i
t
to
h
a
v
e
t
h
e
ad
v
a
n
ta
g
e
o
f
B
est
-
First
-
Sear
c
h
(
B
FS
)
alg
o
r
ith
m
w
i
th
lo
w
ti
m
e
-
s
p
ac
e
an
d
ex
ce
lle
n
t
ef
f
icien
c
y
,
b
u
t a
l
s
o
h
a
v
e
th
e
m
er
its
o
f
Dij
k
s
t
r
a
al
g
o
r
ith
m
w
it
h
ad
m
i
s
s
ib
ilit
y
a
n
d
co
m
p
leten
ess
.
Du
r
in
g
p
lan
n
i
n
g
t
h
e
escap
i
n
g
p
ath
,
w
e
e
m
p
h
a
s
ize
th
e
s
y
s
te
m
s
p
en
t
m
u
ch
ti
m
e
o
n
co
m
p
a
s
s
i
n
g
f
r
o
m
o
b
s
tacle
s
.
E
s
p
ec
iall
y
,
th
e
r
o
b
o
t
co
n
tr
o
ller
to
av
o
id
o
b
s
tacle
s
is
th
e
r
o
b
u
s
t
tech
n
iq
u
e
f
o
r
i
m
p
r
o
v
in
g
e
f
f
ic
ien
c
y
to
p
ath
p
lan
[
7
]
.
Fu
r
th
er
,
th
e
l
o
ca
tio
n
d
eter
m
in
a
tio
n
[
o
f
m
o
b
ile
r
o
b
o
ts
is
th
e
cr
itical
p
o
in
t
o
f
ef
f
icie
n
c
y
to
f
i
n
d
th
e
s
h
o
r
test
e
s
ca
p
in
g
p
ath
i
n
f
ir
e
s
ce
n
e.
R
FID
[
1
2
]
is
th
e
g
o
o
d
s
o
lu
tio
n
f
o
r
lo
ca
tio
n
d
eter
m
i
n
atio
n
o
f
i
n
d
o
o
r
r
o
b
o
t.
Fin
all
y
,
ex
p
er
i
m
e
n
tal
r
e
s
u
lt
s
s
h
o
w
u
p
th
e
h
i
g
h
r
eliab
il
it
y
an
d
e
f
f
icien
c
y
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
5.
CO
NCLU
SI
O
N
W
e
h
av
e
d
es
ig
n
ed
t
h
e
s
ec
u
r
it
y
s
y
s
te
m
f
o
r
d
etec
ti
n
g
f
ir
e
s
o
u
r
ce
s
a
n
d
p
lan
n
i
n
g
a
s
a
f
e
esc
ap
in
g
p
at
h
.
W
e
u
s
ed
t
h
e
Ga
u
s
s
ia
n
2
D
d
is
c
r
ete
m
as
s
f
u
n
ct
io
n
to
ca
lc
u
late
th
e
d
a
n
g
er
v
al
u
es
f
o
r
all
p
o
in
ts
o
n
th
e
p
latf
o
r
m
.
T
h
e
te
m
p
er
atu
r
e
o
f
t
h
e
f
ir
e
s
o
u
r
ce
is
u
n
i
f
o
r
m
l
y
d
esce
n
d
ed
f
r
o
m
t
h
e
ce
n
ter
o
f
t
h
e
f
ir
e
to
it
s
o
u
t
s
id
e
s
u
r
r
o
u
n
d
in
g
s
.
J
o
in
t
p
r
o
b
ab
ilit
y
is
u
s
ed
to
ca
lc
u
late
t
h
e
n
e
w
d
an
g
er
v
a
lu
e
s
o
f
i
n
ter
ac
ti
n
g
n
o
d
es
f
o
r
d
o
u
b
le
f
i
r
e
ev
en
t
s
.
I
n
o
r
d
er
to
s
av
e
p
eo
p
le,
w
e
f
i
n
d
th
e
s
h
o
r
tes
t
p
ath
as
s
o
o
n
as
p
o
s
s
ib
le
b
y
u
s
i
n
g
a
n
A*
s
ea
r
c
h
in
g
alg
o
r
ith
m
.
A
l
s
o
,
s
in
ce
d
a
n
g
er
v
alu
e
s
ar
e
d
ir
ec
tl
y
p
r
o
p
o
r
tio
n
al
to
th
e
air
-
f
u
e
l
r
atio
an
d
th
e
i
n
cr
ea
s
i
n
g
te
m
p
er
atu
r
e
r
ate
w
it
h
d
is
tan
c
e,
w
h
ic
h
m
ea
n
s
t
h
a
t
t
h
e
s
af
e
s
t
escap
i
n
g
p
ath
is
to
f
i
n
d
t
h
e
p
at
h
w
it
h
m
o
s
t
o
x
y
g
en
a
n
d
lo
w
est
te
m
p
er
at
u
r
es.
Ou
r
tr
ea
t
m
en
t
r
ef
lecte
d
a
n
af
f
o
r
d
ab
le
s
o
lu
tio
n
to
t
h
e
p
o
ten
tial
q
u
a
n
ti
ties
o
f
ef
f
icien
c
y
w
it
h
o
u
t
co
m
p
le
x
c
o
m
p
u
ti
n
g
.
Fro
m
e
x
p
er
i
m
e
n
tal
r
esu
lts
,
it
is
v
er
i
f
ied
th
e
s
y
s
te
m
h
a
v
i
n
g
s
u
f
f
icien
t
ef
f
icien
c
y
a
n
d
ex
ce
lle
n
t r
eliab
ilit
y
.
RE
F
E
R
E
NC
E
S
[1
]
D.
L.
Ha
ll
,
J.
A
.
L
li
n
a
s,
A
n
In
tr
o
d
u
c
t
io
n
t
o
M
u
lt
i
-
S
e
n
so
r
Da
ta
F
u
sio
n
,
Pr
o
c
e
e
d
in
g
o
f
t
h
e
IEE
E
,
1
9
9
8
;
6
(1
);
5
3
7
-
5
4
0
.
[2
]
Z.
L
iu
,
J.
M
a
k
a
r,
A
.
K.
Ki
m
,
“
D
e
v
e
lo
p
m
e
n
t
o
f
F
ire
De
tec
ti
o
n
S
y
ste
m
s
in
th
e
In
telli
g
e
n
t
B
u
il
d
in
g
”
,
Au
BE
’
0
1
1
2
th
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
A
u
t
o
ma
ti
c
Fi
re
De
tec
ti
o
n
.
Ga
it
h
e
rs
b
u
rg
,
M
D.,
U.S
.
A
.
2
0
0
1
;
5
6
1
-
5
7
3
.
[3
]
P
.
S
o
n
sa
le,
R.
G
a
w
a
s,
S
.
P
ise
,
A
.
Ka
ld
a
te,
“
In
telli
g
e
n
t
F
ire
Ex
ti
n
g
u
ish
e
r
S
y
ste
m
”
,
IOS
R
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
(
IOS
R
-
J
CE)
.
2
0
1
4
;
1
6
(1
)
V
e
r.
V
III;
5
9
-
6
1
.
[4
]
L.
Zh
a
n
g
,
G
.
F
.
W
a
n
g
,
“
De
sig
n
a
n
d
Im
p
lem
e
n
tatio
n
o
f
A
u
to
m
a
ti
c
F
ire
A
lar
m
S
y
ste
m
b
a
se
d
o
n
W
irele
ss
S
e
n
so
r
Ne
tw
o
rk
s
”
,
Pro
c
e
e
d
in
g
s
o
f
th
e
2
0
0
9
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
o
n
In
fo
rm
a
ti
o
n
Pro
c
e
ss
in
g
(
IS
IP’
0
9
),
Hu
a
n
g
sh
a
n
,
P.
R.
C
h
in
a
.
2
0
0
9
;
4
1
0
-
4
1
3
.
[5
]
L
.
Ca
lav
ia,
C.
Ba
lad
ró
n
,
J.
M
.
Ag
u
iar,
B.
Ca
rro
,
A
n
to
n
i
o
S
.
E,
”
A
S
e
m
a
n
ti
c
A
u
to
n
o
m
o
u
s
V
id
e
o
S
u
rv
e
il
lan
c
e
S
y
st
e
m
f
o
r
De
n
se
Ca
m
e
ra
Ne
t
w
o
rk
s in
S
m
a
rt
Cit
ies
”
.
S
e
n
so
rs
.
2
0
1
2
;
1
2
;
1
0
4
0
7
-
1
0
4
2
9
.
[6
]
X.
G
.
W
a
n
g
,
S
.
M
.
L
o
,
H.
P
.
Z
h
a
n
g
,
W
.
W
a
n
g
,
“
A
No
v
e
l
Co
n
c
e
p
tu
a
l
F
ire
Ha
z
a
rd
Ra
n
k
in
g
Distr
ib
u
ti
o
n
S
y
ste
m
b
a
se
d
o
n
M
u
lt
ise
n
so
ry
T
e
c
h
n
o
lo
g
y
”
,
Pro
c
e
d
ia
E
n
g
i
n
e
e
rin
g
.
2
0
1
4
;
7
1
;
5
6
7
-
5
7
6
.
[7
]
J.
Ya
n
g
,
Y.
Z
h
u
a
n
g
,
“
T
o
w
a
rd
Be
h
a
v
io
r
Co
n
tr
o
l
f
o
r
Ev
o
l
u
ti
o
n
a
ry
Ro
b
o
t
Ba
se
d
o
n
RL
w
it
h
ENN
”
,
IA
ES
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
R
o
b
o
ti
c
s
a
n
d
A
u
to
m
a
ti
o
n
(
IJ
RA
).
2
0
1
2
;
1
(
1
);
3
1
-
4
8
.
[8
]
S.
H.
Ch
ia,
J.
H.
G
u
o
,
B.
Y.
L
i
,
K.
L
.
S
u
,
“
T
e
a
m
M
o
b
il
e
Ro
b
o
ts
Ba
s
e
d
In
telli
g
e
n
t
S
e
c
u
rit
y
S
y
s
tem
”
.
Ap
p
li
e
d
M
a
th
e
ma
ti
c
s
&
In
fo
rm
a
ti
o
n
S
c
ien
c
e
s
.
2
0
1
3
;
7
(2
L
);
4
3
5
-
4
4
0
.
[9
]
Y.
Y.
T
in
g
,
H.
S
.
W
a
n
g
.
“
De
v
e
lo
p
m
e
n
t
o
f
th
e
F
ire
Esc
a
p
in
g
P
a
t
h
s
f
o
r
M
u
lt
i
p
le
F
ire
S
o
u
rc
e
s
”
,
ICIC
Exp
re
ss
L
e
tt
e
rs
,
2
0
1
4
;
5
(
1
);
2
3
2
-
2
3
8
.
[1
0
]
J.
H.
G
u
o
,
K
.
L
.
S
u
,
B.
Y.
L
i,
“
P
r
o
g
ra
m
m
in
g
o
f
th
e
F
ire
Esc
a
p
i
n
g
P
a
th
s
Us
in
g
Ba
y
e
sia
n
Esti
m
a
ted
A
lg
o
rit
h
m
.
2
0
1
4
”
,
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m
o
n
C
o
mp
u
ter
Co
n
s
u
me
r a
n
d
C
o
n
t
ro
l
.
2
0
1
4
;
1
2
7
1
-
1
2
7
4
.
[1
1
]
O.
Ba
c
h
ir,
A.
-
F
.
Zo
u
b
ir,
“
A
d
a
p
ti
v
e
Ne
u
ro
F
u
z
z
y
In
f
e
re
n
c
e
S
y
ste
m
Ba
se
d
Co
n
tro
l
o
f
p
u
m
a
6
0
0
Ro
b
o
t
M
a
n
ip
u
lato
r
”
,
I
AE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
).
2
0
1
2
;
2
(1
);
9
0
-
9
7
.
[1
2
]
W
.
W
e
i,
K
,
“
Cu
rra
n
.
In
d
o
o
r
R
o
b
o
t
L
o
c
a
li
z
a
ti
o
n
w
it
h
A
c
ti
v
e
RF
ID
”
,
IAE
S
I
n
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
R
o
b
o
ti
c
s
a
n
d
Au
to
m
a
ti
o
n
(
IJ
RA
),
2
0
1
2
;
1
(3
);
1
3
7
-
1
4
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N:
2
0
89
-
4856
I
J
R
A
Vo
l.
6
,
No
.
1
,
Ma
r
ch
2
0
1
7
:
2
1
–
30
30
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Y
in
g
-
Y
a
o
T
in
g
re
c
e
i
v
e
d
th
e
B.
S
.
a
n
d
M
.
S
.
d
e
g
re
e
s
in
th
e
in
stit
u
t
e
o
f
In
f
o
r
m
a
ti
o
n
En
g
in
e
e
rin
g
f
ro
m
T
a
m
Ka
n
g
Un
iv
e
rsit
y
in
1
9
88
a
n
d
1
9
9
3
re
sp
e
c
ti
v
e
l
y
.
F
ro
m
2
0
0
7
,
s
h
e
stu
d
ied
i
n
t
h
e
in
st
it
u
te
o
f
En
g
in
e
e
rin
g
S
c
ie
n
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
o
f
Na
ti
o
n
a
l
Ka
o
h
siu
n
g
F
irst
Un
iv
e
rsit
y
o
f
S
c
ien
c
e
o
f
T
e
c
h
n
o
lo
g
y
,
T
a
i
w
a
n
.
He
r
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts in
c
lu
d
e
r
o
b
o
ti
c
s
a
n
d
f
ire d
e
tec
ti
o
n
sy
ste
m
s.
Hu
a
n
-
S
h
e
n
g
W
a
n
g
w
a
s
b
o
rn
in
T
a
iwa
n
in
1
9
6
5
.
He
re
c
e
iv
e
d
th
e
P
h
.
D.
d
e
g
re
e
f
ro
m
th
e
G
e
o
rg
ia
In
stit
u
te
o
f
T
e
c
h
n
o
l
o
g
y
in
1
9
9
8
.
In
2
0
0
2
,
h
e
j
o
i
n
e
d
t
h
e
f
a
c
u
lt
y
o
f
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
a
n
d
Co
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
a
t
th
e
Na
ti
o
n
a
l
Ka
o
h
siu
n
g
F
i
rst
Un
iv
e
rsit
y
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
Tai
w
a
n
.
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
im
a
g
e
d
a
ta
c
o
m
p
re
ss
io
n
a
n
d
w
a
v
e
l
e
t
tran
sf
o
r
m
a
ti
o
n
.
Ko
-
L
a
n
S
u
re
c
e
iv
e
d
th
e
B.
S
.
a
n
d
M
.
S
.
d
e
g
re
e
s
in
a
u
to
m
a
ti
c
c
o
n
tro
l
e
n
g
in
e
e
ri
n
g
f
ro
m
F
e
n
g
-
Ch
ia
Un
iv
e
rsit
y
,
S
e
a
t
w
e
n
,
T
a
i
w
a
n
,
R.
O.
C.
,
a
n
d
re
c
e
iv
e
d
t
h
e
P
H.D.
d
e
g
re
e
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
a
t
Na
ti
o
n
a
l
Ch
u
n
g
-
C
h
e
n
g
Un
iv
e
rsity
,
Ch
ia
-
Yi,
T
a
i
wa
n
,
R.
O.
C
.
,
He
is
c
u
rre
n
tl
y
a
tea
c
h
e
r
in
th
e
De
p
a
rt
m
e
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Na
ti
o
n
a
l
Yu
n
li
n
Un
iv
e
rsity
o
f
S
c
ien
c
e
&
T
e
c
h
n
o
lo
g
y
.
His res
e
a
rc
h
in
tere
sts in
c
lu
d
e
m
u
lt
i
-
se
n
so
r
f
u
sio
n
a
n
d
ro
b
o
ti
c
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.