UNIVERSITY OF HERTFORDSHIRE
    COMPUTER SCIENCE RESEARCH COLLOQUIUM

"Fuzzy Rule-Based Systems for Autonomous Intelligent Agents"

          Prof. Tomoharu Nakashima
     (Osaka Prefecture University, Japan)


       9 November 2011 (Wednesday)
           Meeting Room C152

       Hatfield, College Lane Campus
               1-2  pm

       Everyone is Welcome to Attend

       Refreshments will be available


Abstract:

Fuzzy systems based on fuzzy if-then rules have been shown to be
effective especially in the field of control and classification.
Fuzzy systems can be constructed in various modes of learning
such as supervised learning, unsupervised learning,
and reinforcement leaning. One advantage of fuzzy systems
over non-fuzzy ones is that fuzzy systems can produce
non-linear mapping. Thus the fuzzy systems are able to
accomplish complex tasks that cannot be achieved
by non-fuzzy rule-based systems.
In this presentation, three fuzzy rule-based systems are shown
that are used for the decision making of the following autonomous
intelligent agents: a virtual futures trader, an autonomous car
controller, and a robotic footballer. Three learning methods of fuzzy
systems for developing autonomous intelligent agents are also shown.
Experimental results for these application domains are shown
with some movie demonstrations.
If the time permits, I would also like to show some other works
on the application of computational intelligence to robot soccer (Robocup).

-----------------------
http://cs-colloq.feis.herts.ac.uk/