Abstract:
SLAM is one of the most widely researched sub elds of robotics. An intuitive
understanding of the SLAM process can be conveyed though a hypothetical ex-
ample. Consider a simple mobile robot: a set of wheels connected to a motor and
a camera, complete with actuators-physical devices for controlling the speed and
direction of the unit. Now imagine the robot being used remotely by an operator
to map inaccessible places. The actuators allow the robot to move around, and
the camera provides enough visual information for the operator to understand
where surrounding objects are and how the robot is oriented in reference to them.
What the human operator is doing is an example of SLAM (Simultaneous Local-
ization and Mapping). Determining the location of objects in the environment is
an instance of mapping, and establishing the robot position with respect to these
objects is an example of localization. The SLAM sub eld of robotics attempts to
provide a way for robots to do SLAM autonomously. A solution to the SLAM
problem would allow a robot to make maps without any human assistance What
so ever. In this paper we proposed and implement a new technique to increase the
e ciency of SLAM using Kinect sensor.
Description:
Supervised by
Md. Kamrul Hasan Ph.D
Thesis Supervisor,
Assistant Professor,
Department of Computer Science and Engineering,
Islamic University of Technology.
Mr. Hasan Mahmud
Thesis Co-Supervisor,
Assistant Professor,
Department of Computer Science and Engineering,
Islamic University of Technology.
