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.
6
,
No
.
3
,
Sep
tem
b
er
201
7
,
p
p
.
20
0
~
20
6
I
SS
N:
2089
-
4856
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
r
a.
v
6
i3
.
p
p
20
0
-
20
6
200
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
Autono
m
o
us
Veh
icle Cont
ro
l Sys
te
m
a
s a
M
o
bile
Ro
bo
t
by
Artif
i
cia
l Neural
Netw
o
rk
Na
z
m
ul H
a
qu
e,
M
d H
a
s
na
t
Ria
z
De
p
a
rte
m
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
T
e
lec
o
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
,
No
a
k
h
a
li
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
Un
iv
e
r
sit
y
,
Ba
n
g
lad
e
sh
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
1
2
,
2
0
1
7
R
ev
i
s
ed
J
u
l
1
3
,
2
0
1
7
A
cc
ep
ted
J
u
l 2
7
,
2
0
1
7
In
th
is
p
a
p
e
r
w
e
h
a
v
e
p
re
se
n
ted
th
e
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
c
o
n
tro
ll
e
d
c
a
r
in
m
o
b
il
e
ro
b
o
ti
c
s
a
n
d
in
telli
g
e
n
t
c
a
r
s
y
ste
m
s.
T
h
e
m
o
ti
o
n
c
o
n
tro
l
a
rc
h
it
e
c
tu
re
o
f
th
e
ro
b
o
t
is
p
re
se
n
ted
w
it
h
a
n
im
p
o
rtan
c
e
o
n
th
e
su
p
p
o
rt
a
n
d
d
irec
ti
n
g
u
n
it
s.
T
h
is
u
se
s
n
e
u
ra
l
n
e
tw
o
rk
m
e
th
o
d
s
a
n
d
th
e
v
a
lu
e
s
f
u
n
d
a
m
e
n
tal
it
s
d
e
sig
n
is
d
ra
w
n
.
A
ro
b
u
st
n
e
u
ra
l
c
o
n
tro
l
sy
ste
m
u
sin
g
a
m
o
d
e
l
o
f
th
e
p
r
o
c
e
ss
is
a
lso
d
e
v
e
lo
p
e
d
.
K
ey
w
o
r
d
:
B
ac
k
p
r
o
p
ag
atio
n
alg
o
r
ith
m
Mo
b
ile
r
o
b
o
t
Neu
r
al
n
et
w
o
r
k
s
P
r
ed
ictio
n
f
r
o
m
e
x
p
er
ien
ce
Su
p
er
v
i
s
ed
lear
n
i
n
g
Co
p
y
rig
h
t
©
2017
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
:
Md
Hasn
at
R
iaz,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
T
elec
o
m
m
u
n
ica
tio
n
E
n
g
i
n
ee
r
i
n
g
,
No
ak
h
ali
Scien
ce
a
n
d
T
ec
h
n
o
l
o
g
y
,
Un
i
v
er
s
it
y
,
No
ak
h
ali
-
3
8
1
4
,
B
an
g
lad
e
s
h
.
E
m
ail: H
a
s
n
at.
r
iaz9
0
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
An
au
to
n
o
m
o
u
s
ca
r
is
a
s
elf
-
d
r
iv
i
n
g
ca
r
o
r
d
r
iv
er
-
f
r
ee
ca
r
w
h
ic
h
s
e
n
s
e
it
s
en
v
ir
o
n
m
e
n
t
an
d
ca
n
n
av
i
g
ate
w
it
h
o
u
t
h
u
m
a
n
in
p
u
t
.
A
u
to
n
o
m
o
u
s
v
e
h
icle
s
ar
e
ca
p
ab
le
o
f
s
en
s
in
g
th
eir
s
u
r
r
o
u
n
d
in
g
s
.
I
t
is
ca
p
ab
le
o
f
f
u
l
f
ill
in
g
t
h
e
h
u
m
a
n
tr
a
n
s
p
o
r
tatio
n
ca
p
ab
ilit
ies
a
s
li
k
e
as
t
h
e
tr
ad
iti
o
n
al
ca
r
.
I
t
in
ter
p
r
ets
s
e
n
s
o
r
y
in
f
o
r
m
atio
n
to
r
ec
o
g
n
ize
s
u
it
ab
le
n
av
i
g
atio
n
p
ath
s
,
as
w
e
ll
as
o
b
s
tacle
s
a
n
d
r
elev
a
n
t
s
ig
n
a
g
e.
B
ased
o
n
s
en
s
o
r
y
in
p
u
t
s
o
m
e
au
to
n
o
m
o
u
s
v
e
h
icles
u
p
d
ate
th
eir
m
a
p
s
.
I
t
allo
w
s
th
e
v
e
h
icle
s
to
k
ee
p
tr
ac
k
o
f
th
eir
p
o
s
itio
n
ev
e
n
w
h
e
n
co
n
d
itio
n
s
ch
an
g
e
o
r
w
h
en
t
h
e
y
e
n
ter
u
n
k
n
o
w
n
en
v
ir
o
n
m
e
n
ts
[
1
]
.
T
h
is
p
ap
er
w
e
h
a
v
e
p
r
esen
ted
a
s
el
f
-
d
r
iv
i
n
g
ca
r
t
h
at
w
o
u
ld
b
e
ab
le
to
d
r
iv
e
f
r
o
m
a
s
tar
t
lo
ca
tio
n
to
a
g
o
al
l
o
ca
tio
n
in
a
n
o
r
m
al
d
r
iv
in
g
en
v
ir
o
n
m
en
t.
T
o
ac
h
iev
e
th
e
g
o
al
a
s
m
all
r
o
b
o
t
ca
r
w
o
u
ld
f
in
d
th
e
p
at
h
to
th
e
d
esti
n
a
tio
n
an
d
d
r
iv
e
alo
n
g
t
h
e
p
ath
a
v
o
id
in
g
an
y
o
b
s
tacle
alo
n
g
t
h
e
w
a
y
.
R
esear
ch
er
s
ar
e
w
o
r
k
in
g
o
n
th
e
d
e
v
elo
p
m
e
n
t
o
f
t
h
e
tech
n
o
lo
g
y
o
f
a
u
to
m
atica
ll
y
d
r
i
v
en
v
eh
icle
s
f
r
o
m
t
h
e
ea
r
l
y
n
i
n
etee
n
h
u
n
d
r
ed
.
So
m
e
q
u
as
i
-
a
u
to
n
o
m
o
u
s
d
e
m
o
n
s
tr
a
tio
n
s
y
s
te
m
s
d
ate
b
ac
k
to
th
e
1
9
2
0
s
an
d
th
e
1
9
3
0
s
.
Sin
ce
th
e
1
9
8
0
s
,
wh
en
Me
r
ce
d
es
-
B
en
z
an
d
B
u
n
d
es
w
eh
r
U
n
i
v
er
s
it
y
M
u
n
ich
b
u
ilt
a
d
r
iv
er
les
s
ca
r
th
r
o
u
g
h
t
h
e
E
U
R
E
K
A
P
r
o
m
et
h
eu
s
P
r
o
j
ec
t.
Sig
n
if
ican
t
ad
v
a
n
ce
s
h
av
e
b
ee
n
m
ad
e
in
b
o
th
t
ec
h
n
o
lo
g
y
a
n
d
la
w
r
elev
an
t
to
au
to
n
o
m
o
u
s
ca
r
s
.
Ma
n
y
w
ell
-
k
n
o
w
n
co
m
p
a
n
ies
an
d
r
esear
ch
o
r
g
a
n
izatio
n
s
h
av
e
d
ev
elo
p
ed
w
o
r
k
i
n
g
p
r
o
to
t
y
p
e
a
u
to
n
o
m
o
u
s
v
e
h
icle
s
,
i
n
cl
u
d
in
g
Me
r
ce
d
e
s
-
B
en
z,
Gen
er
al
Mo
to
r
s
,
C
o
n
t
in
en
tal
Au
to
m
o
tiv
e
S
y
s
te
m
s
,
A
u
to
liv
I
n
c.
,
B
o
s
ch
,
Nis
s
a
n
,
T
o
y
o
ta,
A
u
d
i,
Vo
lv
o
,
Vis
lab
f
r
o
m
t
h
e
Un
iv
er
s
it
y
o
f
P
ar
m
a,
O
x
f
o
r
d
Un
i
v
er
s
it
y
an
d
Go
o
g
le.
I
n
2
0
1
0
,
f
o
u
r
d
r
iv
er
less
elec
tr
ic
v
an
s
w
as
s
u
cc
e
s
s
f
u
ll
y
d
r
i
v
en
8
0
0
0
m
ile
s
f
r
o
m
I
tal
y
to
C
h
i
n
a.
T
h
e
v
eh
ic
les
w
er
e
d
ev
elo
p
ed
in
a
r
esear
ch
p
r
o
j
ec
t
f
in
an
ce
d
b
y
E
u
r
o
p
ea
n
U
n
io
n
f
u
n
d
in
g
,
b
y
Vis
lab
o
f
th
e
Un
i
v
er
s
it
y
o
f
P
ar
m
a,
I
tal
y
.
I
n
J
u
l
y
2
0
1
3
Vis
lab
w
o
r
ld
p
r
e
m
ier
ed
B
R
A
iVE
.
I
t
m
o
v
ed
au
to
n
o
m
o
u
s
l
y
o
n
a
m
i
x
ed
tr
af
f
ic
r
o
u
te
o
p
en
to
p
u
b
lic
tr
af
f
ic.
A
s
o
f
2
0
1
3
,
f
o
u
r
U.
S.
s
tate
s
h
a
v
e
p
ass
ed
la
w
s
p
er
m
itti
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
RA
I
SS
N:
2089
-
4856
A
u
to
n
o
mo
u
s
V
eh
icle
C
o
n
tr
o
l
S
ystem
a
s
a
Mo
b
ile
R
o
b
o
t
b
y
A
r
tifi
cia
l Neu
r
a
l
N
etw
o
r
k
(
N
a
z
mu
l H
a
q
u
e
)
201
au
to
n
o
m
o
u
s
ca
r
s
:
Nev
ad
a,
F
l
o
r
id
a,
C
alif
o
r
n
ia,
a
n
d
Mic
h
i
g
a
n
.
I
n
E
u
r
o
p
e,
cities
i
n
B
elg
i
u
m
,
Fra
n
ce
,
I
tal
y
a
n
d
th
e
UK
ar
e
p
la
n
n
in
g
to
o
p
er
ate
tr
an
s
p
o
r
t
s
y
s
te
m
s
f
o
r
d
r
iv
er
l
ess
ca
r
s
.
A
l
s
o
in
E
u
r
o
p
e,
Ger
m
an
y
,
Net
h
er
la
n
d
s
,
an
d
Sp
ain
h
a
v
e
allo
w
ed
tes
tin
g
au
to
n
o
m
o
u
s
ca
r
i
n
tr
a
f
f
ic.
F
in
la
n
d
is
p
la
n
n
i
n
g
o
n
p
a
s
s
i
n
g
a
la
w
b
ef
o
r
e
y
ea
r
2
0
1
5
[
2
]
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
AL
VI
NN
s
y
s
te
m
ca
p
t
u
r
es
v
id
eo
f
r
a
m
e
s
a
n
d
p
ass
es
t
h
e
m
to
n
eu
r
al
n
et
w
o
r
k
s
w
h
ic
h
h
av
e
b
ee
n
tr
ain
ed
b
y
w
atch
in
g
a
h
u
m
a
n
d
r
iv
e
in
s
i
m
i
lar
en
v
ir
o
n
m
en
t
s
.
T
h
en
f
o
r
th
e
n
e
w
v
id
eo
f
r
a
m
e
th
e
tr
ain
ed
n
e
u
r
al
n
et
w
o
r
k
w
ill
p
r
ed
ict
h
o
w
to
s
t
ee
r
to
s
tay
o
n
th
e
r
o
ad
ah
ea
d
.
W
e
n
ee
d
ed
a
s
y
s
te
m
w
h
ic
h
co
u
ld
o
p
er
ate
in
tw
o
m
o
d
e
s
:
a.
R
ec
o
r
d
-
T
h
e
s
y
s
te
m
ca
p
tu
r
es
v
id
eo
f
r
a
m
es
a
n
d
th
e
co
n
tr
o
l
in
p
u
t
f
r
o
m
a
h
u
m
an
d
r
i
v
er
an
d
r
ec
o
r
d
s
th
e
m
f
o
r
later
u
s
e
to
tr
ain
t
h
e
n
e
u
r
al
n
et
w
o
r
k
.
b.
Dr
iv
e
-
C
o
n
tin
u
o
u
s
l
y
ca
p
t
u
r
es
v
id
eo
f
r
a
m
e
s
an
d
p
ass
es
t
h
e
m
to
a
tr
ain
ed
n
eu
r
al
n
et
w
o
r
k
w
h
ic
h
m
a
k
e
s
p
r
ed
ictio
n
s
ab
o
u
t h
o
w
to
d
r
iv
e.
2
.
1
.
Desig
n:
T
h
e
s
y
s
te
m
s
h
o
u
ld
b
e
ab
le
to
r
ec
o
r
d
v
id
eo
f
r
o
m
th
e
ca
r
.
T
h
en
it
s
h
o
u
ld
p
ass
t
h
e
f
r
a
m
es
t
o
a
n
eu
r
al
n
et
w
o
r
k
to
co
n
tr
o
l
t
h
e
ca
r
'
s
s
t
ee
r
in
g
.
T
o
d
o
th
is
w
e
ca
n
m
o
u
n
t
an
An
d
r
o
id
p
h
o
n
e
o
n
t
h
e
ca
r
to
g
at
h
er
v
id
eo
f
r
a
m
e
s
an
d
m
a
k
e
n
e
u
r
al
n
et
wo
r
k
p
r
ed
ictio
n
s
lo
ca
ll
y
o
n
th
e
d
ev
ice,
h
ac
k
i
n
g
th
e
ca
r
to
b
e
co
n
tr
o
lled
f
r
o
m
th
e
o
n
b
o
ar
d
p
h
o
n
e
u
s
in
g
a
n
A
r
d
u
in
o
b
ased
A
n
d
r
o
id
A
D
K
b
o
ar
d
,
w
it
h
d
at
a
r
ec
o
r
d
ed
a
n
d
tr
an
s
f
er
r
ed
to
a
co
m
p
u
ter
f
o
r
tr
ain
in
g
.
A
DK
b
o
ar
d
s
r
e
q
u
ir
e
en
o
u
g
h
ab
ilit
y
to
k
ee
p
th
e
p
h
o
n
e
p
o
w
er
ed
o
v
er
USB
an
d
th
e
w
ei
g
h
t
o
f
ad
d
itio
n
al
b
atter
ies
w
o
u
ld
m
ak
e
th
i
s
c
h
ea
p
an
d
ch
ee
r
f
u
l
ca
r
s
tr
u
g
g
le.
I
n
s
tea
d
,
I
h
av
e
c
h
o
s
e
n
a
d
esig
n
w
h
ic
h
b
ar
el
y
m
o
d
i
f
ied
an
y
o
f
th
e
co
m
p
o
n
en
t
s
in
v
o
l
v
ed
.
T
h
e
s
y
s
te
m
co
n
s
is
ts
o
f
:
a.
An
d
r
o
id
p
h
o
n
e
-
in
s
talled
o
n
t
h
e
ca
r
,
tak
e
s
v
id
eo
f
r
a
m
e
s
o
f
t
h
e
r
o
ad
ah
ea
d
u
s
i
n
g
it
s
b
u
ilt
-
in
ca
m
er
a
at
~1
5
f
p
s
.
A
n
ap
p
licatio
n
r
u
n
n
in
g
o
n
th
e
p
h
o
n
e
co
n
n
ec
t
s
to
a
s
er
v
er
r
u
n
n
in
g
o
n
a
lap
to
p
co
m
p
u
t
er
v
ia
w
i
f
i
an
d
s
tr
ea
m
s
1
7
6
x
1
4
4
g
r
ay
s
ca
le
v
i
d
eo
f
r
am
e
s
ac
r
o
s
s
t
h
e
co
n
n
ec
ti
o
n
.
b.
C
o
m
p
u
ter
-
"
Dr
iv
er
"
w
h
ic
h
is
a
litt
le
J
av
a
ap
p
licatio
n
ac
t
s
as
T
C
P
s
er
v
er
.
I
t
r
ec
eiv
e
s
s
t
r
ea
m
ed
i
m
a
g
e
f
r
a
m
e
s
f
r
o
m
t
h
e
p
h
o
n
e
a
n
d
a
u
s
er
i
n
ter
f
ac
e
al
lo
w
in
g
a
h
u
m
an
d
r
iv
er
to
co
n
t
r
o
l
th
e
ca
r
with
th
e
cu
r
s
o
r
k
e
y
s
o
r
m
o
u
s
e.
I
n
r
ec
o
r
d
m
o
d
e,
d
is
k
s
to
r
es
t
h
e
v
id
eo
f
r
a
m
es,
lab
eled
w
it
h
t
h
e
c
u
r
r
en
t
co
n
tr
o
l
i
n
p
u
t
co
m
in
g
f
r
o
m
t
h
e
h
u
m
an
d
r
iv
e
r
.
T
h
ese
lab
eled
f
r
a
m
e
s
ar
e
u
s
ed
to
tr
ain
th
e
n
e
u
r
al
n
et
w
o
r
k
s
in
a
s
ep
ar
ate
en
v
ir
o
n
m
e
n
t
o
n
t
h
e
co
m
p
u
t
er
.
T
r
ain
ed
p
ar
am
eter
s
ar
e
s
av
e
d
o
u
t
to
f
iles
w
h
ich
ar
e
in
t
u
r
n
r
ea
d
b
y
th
e
Dr
iv
er
ap
p
licatio
n
.
c.
A
r
d
u
i
n
o
U
n
o
-
i
s
a
m
icr
o
co
n
tr
o
ller
co
n
n
ec
ted
v
ia
USB
o
f
a
co
m
p
u
ter
an
d
s
i
m
u
late
k
e
y
p
r
ess
es
o
n
t
h
e
ca
r
'
s
r
ad
io
co
n
tr
o
ller
P
C
B
.
d.
T
h
e
Neu
r
al
Net
w
o
r
k
-
T
h
e
Neu
r
al
Net
w
o
r
k
ca
n
b
e
tr
ain
ed
u
s
i
n
g
a
n
o
ctav
e
p
r
o
g
r
am
[
3
]
.
T
h
e
b
elo
w
f
ig
u
r
e
p
r
esen
ts
t
h
e
ar
ch
itect
u
r
e
o
f
t
h
e
n
et
w
o
r
k
t
h
at
I
h
av
e
u
s
ed
.
Fig
u
r
es a
r
e
p
r
esen
ted
ce
n
ter
,
a
s
s
h
o
w
n
b
elo
w
a
n
d
cited
in
t
h
e
m
an
u
s
cr
ip
t.
Fig
u
r
e
1
.
Neu
r
al
n
et
w
o
r
k
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4856
IJ
RA
Vo
l.
6
,
No
.
3
,
Sep
tem
b
er
20
1
7
:
20
0
–
20
6
202
Fig
u
r
e
2
.
R
C
co
n
tr
o
ller
Fig
u
r
e
3
.
C
ar
m
o
d
el
C
o
n
tr
o
l B
it: C
o
n
tr
o
l B
y
te
s
ar
e
co
n
s
tr
u
cted
i
n
Hex
li
k
e
t
h
is
:
W
h
er
e
X
i
s
t
h
e
d
ir
ec
tio
n
a
n
d
Y
i
s
r
a
n
g
e
o
f
1
6
d
if
f
er
en
t
s
p
ee
d
.
T
h
e
s
p
ee
d
(
Y)
r
an
g
e
s
f
r
o
m
0
-
F
i
n
h
ex
ad
ec
i
m
al,
T
ab
le
1
s
h
o
w
s
th
e
d
if
f
er
en
t
d
r
iv
e
co
m
m
a
n
d
s
.
Fo
r
e
x
a
m
p
le:
I
f
y
o
u
w
an
t
to
d
r
iv
e
lef
t
p
r
ett
y
d
ar
n
q
u
ick
l
y
,
j
u
s
t
s
e
n
d
a
0
1
1
0
.
I
f
y
o
u
w
a
n
t
to
b
ac
k
u
p
to
t
h
e
r
i
g
h
t
s
lo
w
l
y
,
s
e
n
d
a
0
1
0
1
.
A
ll
co
m
m
an
d
s
ar
e
s
e
n
t
as
a
4
b
it.
T
ab
les ar
e
p
r
esen
ted
ce
n
ter
,
as sh
o
w
n
b
elo
w
an
d
cited
in
th
e
m
a
n
u
s
cr
ip
t.
T
ab
le
1
.
C
o
n
tr
o
l
B
it
C
o
d
e
M
o
v
e
0
0
0
0
S
t
o
p
0
1
0
0
S
t
r
a
i
g
h
t
/
F
o
r
w
a
r
d
1
0
0
0
S
t
r
a
i
g
h
t
/
B
a
c
k
w
a
r
d
0
0
1
0
L
e
f
t
/
N
o
D
r
i
v
e
0
0
0
1
R
i
g
h
t
/
N
o
D
r
i
v
e
0
1
1
0
L
e
f
t
/
F
o
r
w
a
r
d
0
1
0
1
R
i
g
h
t
/
F
o
r
w
a
r
d
1
0
1
0
L
e
f
t
/
B
a
c
k
w
a
r
d
1
0
0
1
R
i
g
h
t
/
B
a
c
k
w
a
r
d
2
.
4
.
Ro
a
d
M
o
del:
Her
e
th
e
r
o
ad
m
o
d
el
i
s
m
ad
e
o
f
B
ac
k
a
n
d
W
h
ite
P
ap
er
.
T
h
e
ed
g
e
an
d
co
r
n
er
i
s
d
esi
g
n
ed
p
er
f
ec
tl
y
an
d
m
a
k
e
s
u
r
e
t
h
e
ca
m
er
a
v
ie
w
a
n
g
le
is
p
er
f
ec
t.
A
l
m
o
s
t
an
y
k
in
d
o
f
s
h
ap
e
r
o
ad
ca
n
b
e
d
esig
n
f
o
r
th
i
s
Au
to
n
o
m
o
u
s
C
ar
.
Fi
g
u
r
es a
r
e
p
r
esen
ted
ce
n
ter
,
as s
h
o
w
n
b
el
o
w
an
d
cited
in
t
h
e
m
an
u
s
cr
ip
t.
Fig
u
r
e
4
.
R
o
ad
m
o
d
el
2
.
5
.
Dev
elo
p
m
e
nt
P
ha
s
e:
T
h
e
to
tal
d
ev
elo
p
m
e
n
t
p
r
o
ce
s
s
o
f
m
y
Sel
f
-
d
r
iv
i
n
g
I
-
r
ac
er
co
u
ld
b
e
d
iv
id
ed
in
to
4
p
h
ases
.
B
ased
o
n
th
e
4
p
h
ases
t
h
er
e
ar
e
4
p
r
o
to
t
y
p
e
s
:
a.
P
r
o
to
ty
p
e
1
:
T
o
w
ar
d
s
t
h
e
b
eg
i
n
n
i
n
g
o
f
t
h
e
p
r
o
j
ec
t
I
u
s
ed
a
to
tall
y
d
if
f
er
en
t
t
y
p
e
o
f
r
o
b
o
tic
ca
r
k
it
as
m
y
ca
r
.
I
t
w
a
s
a
li
n
e
f
o
llo
w
v
e
h
ic
le.
T
h
e
m
a
n
eu
v
er
in
g
s
y
s
te
m
w
a
s
to
tall
y
d
i
f
f
er
e
n
t
f
r
o
m
tr
ad
itio
n
al
ca
r
s
.
I
t
m
an
e
u
v
er
ed
li
k
e
a
r
a
n
k
,
s
o
it
co
u
ld
tu
r
n
to
a
n
y
d
ir
ec
tio
n
s
ta
y
in
g
in
th
e
s
a
m
e
p
o
s
it
io
n
.
L
at
er
I
m
o
v
ed
o
n
to
a
m
o
r
e
ca
r
li
k
e
r
o
b
o
tic
ca
r
k
it,
t
h
e
I
-
r
ac
er
.
Fig
u
r
es
ar
e
p
r
esen
ted
ce
n
ter
,
as
s
h
o
w
n
b
elo
w
a
n
d
cited
i
n
th
e
m
a
n
u
s
cr
ip
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
RA
I
SS
N:
2089
-
4856
A
u
to
n
o
mo
u
s
V
eh
icle
C
o
n
tr
o
l
S
ystem
a
s
a
Mo
b
ile
R
o
b
o
t
b
y
A
r
tifi
cia
l Neu
r
a
l
N
etw
o
r
k
(
N
a
z
mu
l H
a
q
u
e
)
203
Fig
u
r
e
5
.
P
r
o
t
o
ty
p
e
1
b.
P
r
o
to
ty
p
e
2
:
T
h
e
s
et
u
p
o
f
th
e
p
r
o
to
ty
p
e
ca
r
u
s
ed
in
th
is
r
es
ea
r
ch
is
q
u
ite
s
i
m
p
le.
I
n
t
h
e
e
ar
lier
s
etu
p
a
s
m
al
l
b
r
ea
d
b
o
ar
d
w
as
m
o
u
n
te
d
o
n
to
p
o
f
th
e
I
-
R
ac
er
.
T
h
e
b
r
ea
d
b
o
a
r
d
w
a
s
u
s
ed
as
a
p
lat
f
o
r
m
a
s
w
ell
a
s
a
m
ea
n
s
f
o
r
co
n
n
ec
tin
g
t
h
e
b
atter
y
an
d
m
o
to
r
s
w
it
h
w
ir
e
s
.
T
h
is
p
r
o
to
ty
p
e
w
as
u
s
ed
to
d
etec
t
o
b
s
tacle
s
o
n
th
e
p
ath
w
a
y
o
f
t
h
e
ca
r
.
c.
P
r
o
to
ty
p
e
3
:
I
n
th
e
later
s
etu
p
an
A
n
d
r
o
id
p
h
o
n
e
b
ec
au
s
e
o
f
th
e
av
ai
lab
ilit
y
o
f
th
e
i
n
te
g
r
at
ed
C
A
ME
R
A
,
Wi
-
Fi,
an
d
B
lu
e
to
o
th
an
d
v
ar
io
u
s
s
e
n
s
o
r
s
.
T
h
e
m
a
g
n
e
tic
f
i
eld
cr
ea
ted
f
r
o
m
t
h
e
m
a
g
n
ets
in
th
e
m
o
to
r
in
ter
f
er
ed
w
i
th
th
e
g
eo
m
ag
n
et
ic
f
ield
s
en
s
o
r
w
h
ich
r
e
s
u
l
ted
in
f
au
lt
y
co
m
p
as
s
r
e
ad
in
g
s
.
T
h
is
r
esu
lted
in
a
m
o
r
e
s
tab
le
co
m
p
ass
r
ea
d
in
g
.
d.
P
r
o
to
ty
p
e
4
:
T
h
e
d
ev
elo
p
m
e
n
t
o
f
t
h
i
s
p
h
a
s
e
i
s
b
asicall
y
t
h
e
co
m
b
in
at
io
n
o
f
P
r
o
to
ty
p
e
2
an
d
3
.
W
ith
a
f
e
w
d
esi
g
n
c
h
an
g
es
I
w
as
ab
l
e
to
m
o
u
n
t
b
o
th
t
h
e
o
b
s
tacle
d
etec
tio
n
m
o
d
u
le
a
n
d
th
e
m
ai
n
p
r
o
ce
s
s
in
g
m
o
d
u
le,
th
e
An
d
r
o
id
P
h
o
n
e,
o
n
to
p
o
f
th
e
s
m
all
c
h
ass
is
o
f
a
r
o
b
o
tic
ca
r
k
it,
th
e
I
-
r
ac
er
.
I
t
w
a
s
o
b
s
er
v
ed
th
at,
p
u
t
tin
g
t
h
e
p
h
o
n
e
o
n
to
p
o
f
th
e
ca
r
v
er
ticall
y
.
T
h
is
also
s
av
e
s
u
p
a
lo
t
o
f
s
p
ac
e
f
o
r
th
e
o
t
h
er
h
ar
d
w
ar
e,
li
k
e
th
e
r
asp
b
er
r
y
p
i
an
d
its
p
o
w
er
s
u
p
p
l
y
u
n
it,
w
h
ic
h
ar
e
also
p
lace
d
v
er
ticall
y
in
o
r
d
er
to
s
av
e
s
p
ac
e.
T
h
e
d
esig
n
o
u
tlo
o
k
is
as t
h
e
f
o
llo
w
in
g
i
m
ag
e
s
:
Fig
u
r
es a
r
e
p
r
esen
ted
ce
n
ter
,
a
s
s
h
o
w
n
b
elo
w
a
n
d
cited
in
t
h
e
m
an
u
s
cr
ip
t.
Fig
u
r
e
6
.
Nu
er
al
n
et
w
o
r
k
co
n
t
r
o
l c
ar
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4856
IJ
RA
Vo
l.
6
,
No
.
3
,
Sep
tem
b
er
20
1
7
:
20
0
–
20
6
204
Fig
u
r
e
7
.
P
r
o
ce
s
s
in
g
p
ip
elin
e
T
h
e
o
v
er
all
w
o
r
k
f
lo
w
o
f
th
e
s
elf
-
d
r
iv
e
n
ca
r
co
u
ld
b
e
r
ep
r
ese
n
ted
s
eq
u
e
n
tiall
y
li
k
e
th
is
:
a.
First t
h
e
co
m
p
u
ter
s
o
f
t
w
ar
e
is
o
p
en
.
b.
An
d
r
o
id
P
h
o
n
e
an
d
C
o
m
p
u
ter
is
co
n
n
ec
ted
w
i
th
I
P
A
d
d
r
ess
w
h
ic
h
is
A
p
p
s
I
n
p
u
t.
c.
T
h
e
ap
p
s
h
o
w
s
t
h
e
cu
r
r
en
t
p
o
s
itio
n
o
f
t
h
e
ca
r
b
y
i
ts
ca
m
er
a.
d.
T
h
e
ca
r
ca
n
r
ea
ch
its
d
esti
n
at
i
o
n
b
y
iter
atin
g
t
h
r
o
u
g
h
ea
c
h
n
o
d
e,
ev
en
tu
all
y
lead
i
n
g
to
t
h
e
d
esti
n
atio
n
.
e.
T
h
er
e
is
an
an
g
le
b
et
w
ee
n
t
w
o
co
o
r
d
in
ates.
T
h
is
is
ca
lled
th
e
‘
h
ea
d
i
n
g
’
.
f.
T
h
e
C
ar
also
h
as a
h
ea
d
i
n
g
.
I
t
is
th
e
d
ir
ec
tio
n
it i
s
g
o
i
n
g
o
n
.
g.
T
h
e
g
o
al
o
f
th
e
ca
r
is
to
tr
y
an
d
m
ai
n
tai
n
t
h
e
h
ea
d
i
n
g
b
et
w
ee
n
th
e
c
u
r
r
en
t p
o
s
itio
n
an
d
th
e
n
ex
t
n
o
d
e.
h.
W
h
ile
tr
av
eli
n
g
t
h
e
co
u
r
s
e,
if
th
e
ca
r
d
etec
ts
an
y
o
b
s
tacle
,
its
in
s
ta
n
t
r
esp
o
n
s
e
is
to
m
o
v
e
a
w
a
y
to
w
ar
d
s
th
e
n
e
x
t b
est d
ir
ec
tio
n
a
n
d
av
o
id
it.
i.
So
,
th
o
u
g
h
th
e
m
ain
g
o
al
is
to
r
ea
ch
th
e
d
esti
n
atio
n
,
ea
ch
n
o
d
e
ca
n
b
e
co
n
s
id
er
ed
a
cu
r
r
en
t
g
o
al.
Up
o
n
r
ea
ch
in
g
t
h
e
cu
r
r
en
t
g
o
al,
t
h
e
n
e
x
t
n
o
d
e
b
ec
o
m
es
t
h
e
g
o
al;
s
o
r
ec
u
r
s
iv
e
l
y
t
h
e
ca
r
iter
ate
s
t
h
r
o
u
g
h
ea
ch
cu
r
r
en
t g
o
al
to
t
h
e
f
i
n
al
g
o
al.
2
.
6
.
Ste
ps
:
1.
Fin
d
C
u
r
r
en
t
P
o
s
itio
n
‘
A’
:
T
h
e
g
lo
b
al
p
o
s
itio
n
o
f
th
e
ca
r
is
d
eter
m
i
n
ed
b
y
t
h
e
Glo
b
al
P
o
s
itio
n
in
g
S
y
s
te
m
(
GP
S)
o
f
th
e
An
d
r
o
id
P
h
o
n
e.
Go
o
g
le
Ma
p
is
u
s
ed
t
o
v
is
u
a
lize
th
e
p
o
s
itio
n
.
Go
o
g
le
Ma
p
s
A
P
I
V2
h
as
b
ee
n
u
s
ed
h
er
e.
T
h
e
cu
r
r
en
t
p
o
s
i
tio
n
is
a
co
o
r
d
in
a
te
co
n
s
is
ti
n
g
o
f
a
latit
u
d
e
a
n
d
a
lo
n
g
it
u
d
e
v
alu
e.
2.
Set
Desti
n
atio
n
‘
B
’
:
T
h
e
d
esti
n
atio
n
ca
n
b
e
s
et
f
r
o
m
th
e
u
s
er
in
ter
f
ac
e,
b
y
clic
k
i
n
g
o
n
a
p
o
in
t
o
n
th
e
m
ap
.
T
h
e
d
esti
n
atio
n
al
s
o
d
en
o
tes a
co
o
r
d
in
ate.
3.
Fin
d
P
ath
f
r
o
m
A
to
B
:
T
h
e
p
ath
f
r
o
m
A
to
B
is
d
et
er
m
i
n
ed
b
y
th
e
Go
o
g
le
D
ir
ec
tio
n
s
A
P
I
.
T
h
e
p
ath
f
r
o
m
A
to
B
is
ac
tu
a
ll
y
a
s
et
o
f
co
o
r
d
in
ates
th
at
f
o
r
m
a
li
n
e,
th
u
s
th
e
p
at
h
.
T
h
ese
co
o
r
d
i
n
ates
co
u
ld
b
e
co
n
s
id
er
ed
n
o
d
es.
4.
Dr
iv
e
f
r
o
m
A
to
B
(
C
o
n
tr
o
l)
: T
h
e
co
n
tr
o
l sy
s
te
m
co
u
ld
b
e
d
iv
id
ed
in
to
2
ca
teg
o
r
ies:
a)
Gl
o
b
al
C
o
n
tr
o
l:
Fig
u
r
e
8
,
th
e
p
r
io
r
ity
is
to
r
ea
ch
d
esti
n
at
io
n
.
So
,
th
e
ac
tio
n
s
tak
e
n
d
u
r
in
g
t
h
is
p
r
o
ce
s
s
f
o
cu
s
ed
o
n
ac
h
ie
v
i
n
g
th
at.
O
n
e
o
f
t
h
e
k
e
y
co
m
p
o
n
e
n
t
is
ca
lc
u
lat
in
g
t
h
e
h
ea
d
i
n
g
.
On
ce
t
h
e
p
ath
is
s
et,
th
e
ca
r
s
tar
ts
its
jo
u
r
n
e
y
f
r
o
m
th
e
f
ir
s
t
n
o
d
e,
w
h
ich
i
s
th
e
cu
r
r
en
t
lo
ca
tio
n
o
f
th
e
ca
r
.
T
h
e
im
m
ed
iate
n
e
x
t
n
o
d
e
is
t
h
e
cu
r
r
en
t
g
o
al
f
o
r
th
e
ca
r
.
T
h
e
h
ea
d
i
n
g
d
ir
ec
tio
n
b
et
w
ee
n
th
e
ca
r
’
s
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
RA
I
SS
N:
2089
-
4856
A
u
to
n
o
mo
u
s
V
eh
icle
C
o
n
tr
o
l
S
ystem
a
s
a
Mo
b
ile
R
o
b
o
t
b
y
A
r
tifi
cia
l Neu
r
a
l
N
etw
o
r
k
(
N
a
z
mu
l H
a
q
u
e
)
205
cu
r
r
en
t p
o
s
itio
n
a
n
d
th
e
cu
r
r
e
n
t
g
o
al
is
ca
lcu
lated
f
r
eq
u
en
tl
y
as
th
e
ca
r
m
o
v
es
to
w
ar
d
s
it.
T
h
is
is
i
ts
d
esire
d
h
ea
d
in
g
.
T
h
e
ca
r
h
a
s
i
ts
o
w
n
h
ea
d
in
g
d
ir
ec
tio
n
.
I
t
c
o
n
s
ta
n
tl
y
tr
ie
s
to
k
ee
p
it
s
o
w
n
h
ea
d
i
n
g
to
w
ar
d
s
t
h
e
d
es
ir
ed
h
ea
d
in
g
b
y
s
teer
in
g
to
w
ar
d
s
i
t.
I
f
it
i
s
d
r
iv
in
g
in
th
e
r
ig
h
t
d
ir
ec
tio
n
,
e
v
en
t
u
all
y
it
w
il
l
r
ea
ch
th
e
c
u
r
r
en
t
g
o
al.
On
ce
th
e
c
u
r
r
en
t
g
o
al
is
r
ea
c
h
ed
,
t
h
e
n
ex
t
n
o
d
e
b
ec
o
m
es
t
h
e
cu
r
r
en
t
g
o
al
an
d
th
e
ca
r
d
r
iv
es
to
w
ar
d
s
it.
T
h
is
w
a
y
all
n
o
d
es
ar
e
tr
av
er
s
ed
an
d
th
e
f
i
n
al
g
o
al
is
r
ea
ch
ed
.
Fig
u
r
es a
r
e
p
r
esen
ted
ce
n
ter
,
a
s
s
h
o
w
n
b
elo
w
a
n
d
cited
in
t
h
e
m
an
u
s
cr
ip
t.
Fig
u
r
e
9
t
h
e
s
teer
in
g
an
g
le
o
f
t
h
e
I
-
R
ac
er
is
f
ix
ed
,
t
h
e
ca
r
o
v
er
s
h
o
o
ts
.
Me
an
i
n
g
,
b
y
t
h
e
ti
m
e
it
r
ea
ch
es
t
h
e
d
esire
d
h
ea
d
i
n
g
a
n
g
le
a
n
d
s
tr
ai
g
h
ten
s
th
e
w
h
ee
ls
it
m
a
y
h
av
e
g
o
n
e
s
li
g
h
t
l
y
o
f
f
tr
ac
k
.
An
d
t
h
is
k
ee
p
s
h
ap
p
en
i
n
g
f
r
o
m
t
i
m
e
to
t
i
m
e,
m
a
k
i
n
g
t
h
e
c
ar
s
w
a
y
a
litt
le
le
f
t
a
n
d
r
i
g
h
t.
So
t
h
e
tr
av
eled
p
ath
is
n
’
t a
l
w
a
y
s
a
s
tr
aig
h
t li
k
e.
T
h
is
p
r
o
b
lem
co
u
ld
b
e
s
o
lv
ed
b
y
g
r
ad
u
all
y
d
ec
r
ea
s
in
g
t
h
e
s
teer
in
g
an
g
le
as
th
e
ca
r
’
s
h
ea
d
in
g
g
e
ts
clo
s
er
to
th
e
d
esire
d
h
ea
d
in
g
.
B
u
t
i
n
o
r
d
er
to
d
o
t
h
at
a
ca
r
o
f
w
h
ic
h
t
h
e
s
teer
i
n
g
w
h
ee
l c
a
n
b
e
co
n
tr
o
lled
b
y
t
h
e
d
eg
r
ee
i
s
n
ee
d
ed
.
Fig
u
r
e
8
.
Glo
b
al
co
n
tr
o
l
Fig
u
r
e
9
.
W
av
y
tr
ac
k
b)
L
o
ca
l
C
o
n
tr
o
l:
Du
r
in
g
t
h
e
L
o
ca
l
C
o
n
tr
o
l
p
h
ase,
th
e
ca
r
is
f
o
cu
s
ed
o
n
av
o
id
in
g
o
b
s
tacle
s
.
I
t
ca
n
o
v
er
r
id
e
th
e
Glo
b
al
co
n
tr
o
l
c
o
m
m
a
n
d
,
ev
e
n
i
f
it
m
ea
n
s
to
g
et
a
w
a
y
f
r
o
m
t
h
e
d
esti
n
ati
o
n
;
o
n
ce
o
b
s
tacle
av
o
id
ed
,
it
g
o
es
b
ac
k
to
co
u
r
s
e
o
f
Glo
b
al
co
n
tr
o
l.
T
h
e
lo
ca
l
co
n
tr
o
l
in
clu
d
es
t
h
e
Ob
s
tacle
Dete
ctio
n
S
y
s
te
m
.
2
.
7
.
Alg
o
rit
h
m
T
h
e
A
I
f
o
r
th
e
s
el
f
-
d
r
i
v
in
g
c
ar
w
a
s
i
m
p
le
m
e
n
ted
o
n
J
av
a
p
latf
o
r
m
.
An
a
n
d
r
o
id
ap
p
w
a
s
m
ad
e
to
in
ter
f
ac
e
b
et
w
ee
n
th
e
p
h
o
n
e
an
d
th
e
I
-
R
ac
er
.
T
h
e
d
r
iv
in
g
alg
o
r
ith
m
o
f
t
h
e
ca
r
ca
n
b
e
r
ep
r
esen
ted
b
y
t
h
e
f
o
llo
w
in
g
p
r
o
ce
s
s
i
n
g
p
ip
eli
n
e
an
d
f
lo
w
ch
ar
t
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
1
0
:
Fig
u
r
e
10.
A
lg
o
r
it
h
m
f
lo
w
c
h
a
r
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4856
IJ
RA
Vo
l.
6
,
No
.
3
,
Sep
tem
b
er
20
1
7
:
20
0
–
20
6
206
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
Sev
er
al
te
s
t
d
r
iv
e
s
h
a
v
e
b
ee
n
co
n
d
u
cted
to
f
i
n
d
t
h
e
o
u
tp
u
t
o
f
t
h
e
p
r
o
g
r
a
m
.
W
h
ich
led
to
a
lo
t
o
f
b
u
g
f
i
x
es.
T
h
e
o
u
tp
u
t
o
f
t
h
e
p
r
o
g
r
a
m
d
ep
en
d
ed
o
n
a
f
e
w
e
x
te
r
n
al
th
i
n
g
s
,
li
k
e
-
elec
tr
o
m
ag
n
etic
f
ield
f
r
o
m
t
h
e
m
o
to
r
o
f
t
h
e
I
-
R
ac
er
,
t
h
e
GP
S
s
i
g
n
al
q
u
a
lit
y
,
th
e
p
h
o
n
e
’
s
o
p
er
ato
r
s
ig
n
al.
B
ec
au
s
e
o
f
t
h
ese
t
h
in
g
th
e
o
u
tp
u
t
f
l
u
ctu
a
ted
f
r
o
m
ti
m
e
to
t
i
m
e,
ca
u
s
i
n
g
t
h
e
ca
r
to
d
r
iv
e
in
a
w
r
o
n
g
w
a
y
;
th
at
’
s
w
h
y
o
u
td
o
o
r
test
in
g
d
id
n
’
t
g
i
v
e
an
y
s
ati
s
f
ac
to
r
y
r
es
u
lt,
o
th
er
t
h
an
t
h
e
f
ac
t
t
h
at
f
o
r
t
h
e
in
i
tial
ti
m
e
w
h
ile
it
i
s
o
n
co
u
r
s
e,
th
e
ca
r
is
ab
le
to
s
teer
to
w
ar
d
s
t
h
e
d
esire
d
h
ea
d
in
g
k
ee
p
in
g
it o
n
tr
ac
k
.
A
n
d
t
h
e
w
a
v
y
tr
ac
k
w
as
n
o
ted
.
T
h
e
f
o
llo
w
in
g
i
m
a
g
e
s
h
o
w
s
t
h
e
i
n
ac
cu
r
ate
GP
S
r
ea
d
in
g
s
.
T
h
e
d
esire
d
p
ath
is
m
ar
k
ed
b
y
t
h
e
r
ed
lin
es.
T
h
e
o
r
an
g
e
m
ar
k
er
m
a
r
k
s
t
h
e
s
tar
ti
n
g
lo
ca
tio
n
,
an
d
th
e
b
lu
e
m
ar
k
er
m
ar
k
s
th
e
d
esti
n
atio
n
.
W
h
e
n
ma
n
u
all
y
tr
av
elled
d
o
w
n
th
e
p
ath
,
th
e
GP
S
s
i
g
n
als
f
l
u
ct
u
at
ed
a
lo
t.
T
h
e
g
r
ee
n
m
ar
k
er
s
s
h
o
w
t
h
e
GP
S
tr
ac
k
th
at
w
a
s
o
b
tain
ed
.
I
n
d
o
o
r
test
d
r
iv
es
h
av
e
a
ls
o
b
ee
n
co
n
d
u
c
ted
.
T
h
e
tar
g
et
w
as
to
test
th
e
o
b
s
tacle
d
etec
tio
n
f
u
n
ctio
n
alit
y
o
f
t
h
e
ca
r
.
I
t
w
as
ab
le
to
m
o
v
e
f
r
ee
l
y
i
n
d
o
o
r
s
,
av
o
id
in
g
o
b
s
tacle
s
,
ev
e
n
co
m
i
n
g
o
u
t o
f
co
r
n
er
s
.
T
h
o
u
g
h
f
i
x
ed
s
en
s
o
r
s
h
an
d
led
th
e
j
o
b
o
f
o
b
s
tacle
d
etec
tio
n
p
r
etty
w
el
l,
th
e
ca
r
s
till
h
ad
s
o
m
e
b
li
n
d
s
p
o
ts
.
T
h
e
to
tal
3
6
0
o
s
u
r
r
o
u
n
d
in
g
w
a
s
n
o
t
co
v
er
ed
.
T
h
is
ca
n
b
e
o
v
er
co
m
e
b
y
h
a
v
i
n
g
a
r
o
tat
in
g
s
o
n
ar
s
e
n
s
o
r
,
o
r
m
o
r
e
ex
p
e
n
s
i
v
e
s
en
s
o
r
s
t
h
at
ta
k
e
a
r
o
tatio
n
al
3
6
0
o
s
ca
n
o
f
t
h
e
e
n
v
ir
o
n
m
e
n
t.
Sto
r
in
g
th
i
s
s
u
r
r
o
u
n
d
i
n
g
in
f
o
r
m
atio
n
w
o
u
ld
h
elp
cr
ea
te
a
m
ap
o
f
th
e
e
n
v
ir
o
n
m
e
n
t
t
h
e
ca
r
is
in
,
th
u
s
p
r
o
v
id
e
b
etter
L
o
ca
lizatio
n
.
A
n
d
w
it
h
m
o
r
e
p
r
ec
is
e
s
en
s
i
n
g
o
f
th
e
v
elo
cit
y
an
d
d
is
p
lace
m
e
n
t
o
f
th
e
ca
r
’
s
m
o
v
e
m
en
t,
th
e
c
ar
co
u
ld
b
e
a
b
le
to
p
er
f
o
r
m
m
o
r
e
p
r
ec
is
e
d
r
iv
i
n
g
w
h
i
le
Glo
b
al
C
o
n
tr
o
l
i
s
u
n
ce
r
tain
.
Go
o
g
le
ca
r
u
s
es
a
v
er
y
ex
p
en
s
iv
e
L
id
ar
to
ac
h
iev
e
b
etter
L
o
ca
lizatio
n
.
I
t
s
en
s
es
t
h
e
s
u
r
r
o
u
n
d
in
g
a
n
d
s
t
o
r
es
all
t
h
e
d
ata
cr
ea
ti
n
g
a
m
a
p
.
So
,
th
e
n
ex
t
ti
m
e
th
e
ca
r
co
m
es d
o
w
n
t
h
e
s
a
m
e
r
o
ad
,
it k
n
o
w
s
h
o
w
to
r
ea
ct.
4.
CO
NCLU
SI
O
N
T
h
e
ai
m
o
f
m
y
w
o
r
k
w
as
to
d
esig
n
a
n
au
to
n
o
m
o
u
s
v
eh
ic
le
d
r
iv
in
g
s
y
s
te
m
,
to
d
ev
elo
p
th
e
ar
tif
icial
in
telli
g
e
n
ce
t
h
at
w
o
u
ld
b
e
ab
le
to
m
a
k
e
a
d
r
iv
er
less
au
to
m
o
b
ile
s
af
e
e
n
o
u
g
h
to
d
r
iv
e
o
n
th
e
r
o
ad
.
T
h
e
g
o
al
w
a
s
to
d
e
v
elo
p
a
p
r
o
g
r
a
m
th
a
t
w
o
u
ld
r
u
n
i
n
a
n
a
n
d
r
o
id
o
p
e
r
ated
en
v
ir
o
n
m
e
n
t
an
d
w
ill
b
e
ab
le
to
co
n
tr
o
l
t
h
e
v
eh
ic
le,
th
er
eb
y
ta
k
i
n
g
th
e
r
es
p
o
n
s
ib
ilit
ies
o
f
t
h
e
d
r
iv
er
,
p
r
o
v
id
in
g
a
m
o
r
e
m
an
a
g
e
ab
le
co
n
tr
o
l
o
v
er
it.
A
n
d
a
s
w
ar
m
o
f
th
e
s
e
au
to
n
o
m
o
u
s
v
eh
icles
co
u
ld
j
u
s
t
b
e
th
e
s
o
lu
ti
o
n
to
o
u
r
tr
af
f
ic
p
r
o
b
lem
s
an
d
tr
af
f
ic
j
a
m
,
r
ed
u
ce
th
e
n
u
m
b
er
o
f
r
o
ad
ac
cid
en
t
s
an
d
n
e
v
er
th
e
less
s
a
v
e
t
h
e
ti
m
e
th
at
p
eo
p
le
en
g
a
g
e
t
h
e
m
s
el
v
e
s
w
h
ile
d
r
iv
i
n
g
f
o
r
s
o
m
e
o
th
er
tas
k
.
RE
F
E
R
E
NC
E
S
[1
]
A
u
to
n
o
m
o
u
s
c
a
r.
(2
0
1
5
,
A
u
g
u
st
1
8
).
In
W
ik
ip
e
d
ia,
T
h
e
F
re
e
En
c
y
c
lo
p
e
d
i
a
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/en
.
w
ik
ip
e
d
ia.o
rg
/w
/i
n
d
e
x
.
p
h
p
?
t
it
le=
A
u
to
n
o
m
o
u
s_
c
a
r&
o
ld
i
d
=
6
7
6
6
9
6
2
2
5
[2
]
Histo
ry
o
f
a
u
to
n
o
m
o
u
s
c
a
r.
(2
0
1
5
,
A
u
g
u
st
6
).
In
W
i
k
ip
e
d
ia,
T
h
e
F
re
e
En
c
y
c
lo
p
e
d
ia.
Av
a
il
a
b
le:
h
tt
p
s:/
/en
.
w
ik
ip
e
d
ia.o
rg
/w
/i
n
d
e
x
.
p
h
p
?
t
it
le=
Histo
ry
_
o
f
_
a
u
to
n
o
m
o
u
s_
c
a
r&
o
ld
id
=
6
7
4
8
8
3
5
9
3
[3
]
Da
v
id
S
in
g
leto
n
(2
0
1
3
,
Ja
n
u
a
ry
1
1
).
Ho
w
I
b
u
il
t
a
n
e
u
ra
l
n
e
tw
o
rk
c
o
n
tro
ll
e
d
se
lf
-
d
riv
in
g
(RC)
c
a
r
.
Re
tri
e
v
e
f
ro
m
:
h
tt
p
:
//
b
l
o
g
.
d
a
v
id
si
n
g
leto
n
.
o
rg
/n
n
r
c
c
a
r
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Na
z
m
u
l
Ha
q
u
e
Un
d
e
rg
ra
d
u
a
te stu
d
e
n
t
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
T
e
lec
o
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
No
a
k
h
a
li
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
Un
iv
e
rsit
y
,
No
a
k
h
a
li
3
8
1
4
,
Ba
n
g
lad
e
sh
.
Em
a
il
:
n
a
z
m
u
l.
c
ste
0
7
@g
m
a
il
.
c
o
m
Ha
sn
a
t
Riaz
L
e
c
tu
re
r
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
T
e
lec
o
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
No
a
k
h
a
li
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
Un
iv
e
rsit
y
,
No
a
k
h
a
li
3
8
1
4
,
Ba
n
g
lad
e
sh
.
Em
a
il
:
h
a
sn
a
t.
riaz
9
0
@g
m
a
il
.
c
o
m
Evaluation Warning : The document was created with Spire.PDF for Python.