UTCS Colloquium/AI: Edgar Koerner/Honda Research Institute Europe ASIMO Revisited--The Quest for Intelligence ACES 2.402 Tuesday November 27 2007 2:00 p.m.

Contact Name: 
Jenna Whitney
Date: 
Nov 27, 2007 2:00pm - 3:00pm

There is a sign up schedule for this event:
htt

p://www.cs.utexas.edu/department/webevent/utcs/events/cgi/list_events.cgi
Type of Talk: UTCS Colloquium/AI

Speaker/Affiliation: Edgar

Koerner Honda Research Institute Europe

Host: Dana Ballard

Talk Title: ASIMO Revisited--The Quest for Intelligence

Talk Abstra

ct:
Having largely succeeded in the development of humanoid mobility and
the
adaptation of humanoid robots to the human environment providing t

hose
artifacts with capabilities for autonomous interaction with its env

ironment
challenges our current understanding of intelligence. Still th

e brain is the
only one existing system that is capable of generating i

ntelligent behavior
in real world and real time. Therefore understandi

ng how the brain works
may provide us with an idea of what are the esse

ntial principles behind that
marvelous performance we admire.

In

our approach to understand essential characteristics of processing in thebrain we follow an ‘analysis by synthesis’ philosophy.

We believe not special local processing algorithms and dynamics but how <

br>the brain organizes processing is the key to enable that marvelous perfo

rm- ance and robustness in sensory understanding and creating smart behavio

r
in an unpredictable environment which is still unparalleled by any t

echnical
system. Therefore the major focus of our approach is on the gl

obal and local
control in the brain that enables autonomous learning and
the self-organization
of knowledge representation. We target the contro

l architecture of brain-like
intelligent systems at microscopic mesosco

pic and macroscopic level in
parallel whereby special emphasis is put o

n the utilization of insights from
phylogenetic and ontogenetic developm

ent. Step by step we try to assemble
systems that interact with the envi

ronment and that provide us with the
necessary feedback on the role of a

rchitectural constraints and dynamics of
the brain.

Finally to a

ddress the global control architecture we integrate visual and
auditory
recognition with autonomous behavior generation on ASIMO for a
step by

step development of individual cognitive capabilities based on the
pract

ical experience in interacting with the real world.