MICROCONTROLLER BASED NEURAL NETWORK

sciencediscussionAI and Robotics

Oct 20, 2013 (4 years and 24 days ago)

87 views

MICROCONTROLLER BASED NEURAL NETWORK
CONTROLLED LOW COST AUTONOMOUS VEHICLE


INTRODUCTION


Autonomous robots with mobile capability are finding their place in
numerous application fields. Some typical examples of these application fields are
factory automa
tion, service application, and hazardous environments such as
dangerous zones in nuclear power stations, space exploration, material handling in
hospital and security guarding. The key requirement for performing these tasks is
navigation. Navigation is the

ability of a mobile robot to reach the target safely
without human assistance. Thus the main issues that need to be addressed in
mobile robot navigation are reactive obstacle avoidance and target acquisition.
Vision based sensing for autonomous navigation

is a powerful and popular method
due to its ability to provide detailed information of environment which may not be
available using combinations of other types of
sensors

and has been addressed by
many researchers.


DESCRIPTION

Neural navigators perceive

their knowledge and skills from a demonstrating
action and also suffer from a very slow convergence process and lack of
generalization due to limited patterns to represent complicated environment.
However, neural networks that can be implemented with rela
tively modest
computer hardware could be very useful. Although the aforementioned techniques
successfully solve the robot navigational problem, there always remains a need of
lowering the system cost further without compromising much on its efficiency and
reliability.



The navigation task is subdivided into hurdle avoidance and goal seeking
tasks. Hurdle avoidance is achieved with the help of
one back ultrasonic sensor,
two front IR sensors & sonar sensor
. The range data from these sensors is fed to
inside

the microcontroller. Goal seeking behavior involves the data from
GPS
,
GPS receiver which is processed by another microcontroller.

In this project for the
demo purpose we are giving the goal as left, right, forward

commands because in
room environment th
ere will be small change
s

in the GPS location co ordinates
that robot may not consider it as different location

.

The main microcontroller
fetches the desired data and generates motion commands for robot. A GSM modem
is interfaced to the main controller fo
r selecting start and goal stations for robot
inside the university campus.

Neural network simulation will be done by using
MATLAB.

8051 architecture based AT89C52 microcontroller from ATMEL is used to
implement this project. Microcontroller acts as the he
art of this project, which
C
ontrols the whole system. It contains 256 RAM, 2k Flash, 2 Timers, 2 external
interrupts, 1 UART, 32 GPIO’s, ISP programming support etc. KEIL IDE is used
to program the microcontroller and the coding will be done using Embedded

C.



COMPONENTS USED

1.

Microcontroller
-

P89V51RD2


NxP.

2.

Alpha Numeric

LCD Display
.

3.

GSM Module.

4.

GPS.

5.

Ultrasonic Sensor.

6.

Sonar Sensor

7.

IR Sensor

8.

DC Motor
.

9.


L293 driver

10.

4052 Multiplexer



BLOCK DIAGRAM







SOFTWARES USED

1.

Embedded C

2.

Keil Compiler

3.

Flash Magi
c

4.

MATLAB