Warning:

This page is provided for historical and archival purposes only. While
the seminar dates are correct, we offer no guarantee of informational
accuracy or link validity. Contact information for the speakers, hosts
and seminar committee are certainly out of date.

----------------------------------------------------------------------

The purpose of this study is the development of a system for
recognizing and tracking an object which is selected from multiple
objects that are unknown and randomly placed on a moving conveyor
belt, using a vision, infrared proximity and encoder sensors in the
feedback loop.

The system designed in this study is logically partitioned into
independent vision, infrared proximity sensors, robot, conveyor module
and monitoring programs permitting these system functions to be
distributed among two microcomputers and the robot controller for
parallel processing.

The visual information obtained from a camera-image processing unit
and an end-effector based proximity sensor outputs are incorporated in
a fuzzy-logic control algorithm to make a robot manipulator grasp an
object on a moving conveyor belt.  Because of the time delay caused by
the image processing and communication wi th the robot, the motion of
the moving target is predicted in advance and is used in the on-line
planning of the trajectory for the manipulator motion.  On the basis
of the predicted location of the object, the planner determines
on-line at each control sampling instant the desired trajectory point
(subgoal) for the con troller.  The subgoal points are tracked by
controlling the motion of the end-effector with an end-effector based
infrared proximity sensors and conveyor position encoder until
grasping occurs.

Laboratory experiments are presented to demonstrate the performance of
this system.