Vision-Based Obstacle Avoidance

Click icon to
of Mobile add
Robot
picture
“The robot is going to lose. Not by much.
But when the final score is tallied, flesh
and blood is going to beat the damn
monster."
-Adam Smith
Problem
Statement
Problem of moving a robot through
unknown environment or any
rough terrain
has attracted much attention
over past two
decades.
Such problems have several
difficulties and complexities that
are unobserved, besides the
This research had been aimed to
develop a system that is able to
detect obstacles in a mobile robot's
path using a single camera as only
sensory input and to achieve the
target point in optimized manner.
For this reason, algorithm which
took total path length and safety
into account was developed.
Conventional
Approach
The earlier approaches utilized sensors
such as SONAR as a principle means to
identify the obstacles and approximate the
distance between the two. However, the
field range implemented under this
mechanism is constrained to several
restriction.
The graph depicts the range of the
sensors:
The sensor just detects colors at
the points they are aimed.

Also the sensors may be more

difficult to upgrade for new
products.
Approach
To control movement of robot from a starting to a
target point inside the site where obstacles can
obstruct the way of robot, real-time software-specially
tailored for this purpose-was necessary to develop.
To analyze and to process scene images captured by
a (vision) camera, camera was installed on the bot in
a way that it covered the path through which
sufficient image information could be delivered.
From sequentially captured
images that was manipulated
through image processing and
computer vision, the robo was
given effective decisions and
then it began planning the
desired routing path.
Image Processing
techniques
Read the image
Detect the Entire Cell
Dilate the image
Fill interior groups
Remove connected
objects on border
Smoothen the object
Lets have a better how the
system works..
Click icon to add
picture
Later when
the robo
approachesClick icon to add
picture
the obstacle it
has to make a
decision for
the path to
choose
The robo then
captures an
Click icon to add
image of the
obstacle picture
The image is then sent to the computer.
Click icon to add
The image is processed through various
picture
tools of MATLAB

The info retrieved from the image is

processed and a decision is made on
the path to choose.
Click icon to add
picture
Click icon to add
picture
Click icon to add
picture
Click icon to add
picture
Specifications
v Power of the camera: 1.3 Mega
pixels
v Bot size: 10”x4”x5”
v Bot weight: 4 lbs
v Range of Operation: 5 feet
v Software & Tools: Matlab 7.0,
Basic Stamp Editor.
Applications
Click icon to add
picture
Airplane
Navigation

Unmanned
Navigation
Defense and Military Air
Combats
Conclusion
A less computational
effort was necessary to
control movement of
robot with the ability of
obstacle and avoidance
detection
Thank You