Robotic
Person Following Using
Fuzzy Control and Image Segmentation |
Watch
a demonstration of Robotic Person Following:
Person Following To download, right click on the link, and choose save link as..
Following_small To download, right click on the link, and choose save link as..
Mobile
robots can assist a person in performing a variety of tasks.
These include, for example, carrying a person’s tools,
delivering parts. A rover assistant can aid an astronaut in
his extra-vehicular activities by carrying tools and rock
samples, supplying backup communications, providing life support
equipment, acquiring and analyzing geological samples, and
maintaining position data relative to the main spacecraft.
Figure
1. Block diagram of the person following system
One
of the major requirements of such robotic assistants
is the ability to track and follow a moving person through
a non-predetermined and unstructured environment.
This
project has developed a scheme for a mobile robots to
follow a person in reasonably complex dynamic environments.
The scheme consists of an image processing technique
for person identification, and a fuzzy controller for
following the person. The identification process utilizes
image color, shape characteristics and a region growing
technique.
|
Figure
2.Mobile robot and the mounted camera
|
The fuzzy
logic controller receives image data such as the mass, center
of mass and their rates of change to produce steering and
speed commands for the robot. A behavior control strategy
is also incorporated to cope with several situations, such
as hazard, that are not accounted for in the fuzzy controller.
Descriptions of the software/hardware as well as experimental
setup and results are provided to demonstrate the feasibility
of the scheme
Figure
3. Images taken by the robot’s camera during
several
experiments in different locations along the tour route.
The person being followed has dark shirt and light pants
|
