ECE 6720 FUZZY CONTROL SYSTEMS
Fall 2008
Project Assignment #2
(Team Project)
Total: 80 pts. (20% of the course grade)
Due 6:30pm, Tuesday, November 25, 2008
Demonstrations are given in the CAE Lab
The objective of this project is to develop and verify by simulation some of the functions of an
automated assessment and training procedure provided by an Intelligent Decision Support
System (IDSS) for children with eye-hand coordination problem. A picture of the actual setup is
given in Figure 1.
Figure1: Actual setup of the PHANToM Robot
A simplified block diagram of the system is shown in Figure 2. For the sake of simplicity, a
variable (age) and the role of a supervisor person are eliminated. An automated assessment system
is expected to reduce the burden and the associated cost of having a trained professional present at
any assessment, or training session. The key block of the IDSS is based upon a fuzzy automaton.
By using qualitative (fuzzified) data from the previous test the system will make a decision on the
complexity of the next test to be performed. A set of assessment tests, commonly used by
occupational therapists, are chosen that include the use of force, inertia and viscosity effects.
Three different test trajectories are illustrated in Figure 3. The subject is supposed to move the ball
in the virtual environment (with the help of the PHANToM robot arm) along the desired trajectory.
The system then measures the Time Taken (to execute a given task from the start to the end point)
and the Accuracy (number of times the subject is out of the trajectory) and forwards them as inputs
to the IDSS. By utilizing the fuzzy automaton the IDSS will then determine the next task to be
executed by the subject.
The input measurements passed to the fuzzy automaton will be in fuzzified form as shown in
Figure 4. You are to develop a program in MATLAB that will read the fuzzified inputs for
Accuracy and Time Taken. It will then model the state transition of the fuzzy automaton using
the B Algorithm that has been discussed in class. In each state the program should generate a 12-
element output vector in which only that bit should set that identifies the present state of the
fuzzy automaton. Inputs Accuracy and Time Taken are measured on the scale of 0-100.
