Speaker/Affiliation: Peter Stone Ph.D. Departmen

t of Computer Sciences The University of Texas at Austin

When/Locat

ion: 10/9/2006 12:00 PM SEA 4.244

Title of Talk: Robust Autonomous
Color Learning on a Mobile Robot

Abstract: The scientific community
is slowly but surely working towards the creation of fully autonomous mobi

le robots capable of interacting with the proverbial real world. To operate
in the real world autonomous robots are predominantly dependent on sensor

y information but the ability to accurately sense the complex world is stil

l missing. Visual input in the form of color images from a camera should

be an excellent and rich source of such information considering the signif

icant amount of progress made in machine vision. But color and images in g

eneral have been used sparingly on mobile robots where people have mostly
focused their attention on other sensors such as tactile sensors sonar an

d laser.
This talk presents the challenges raised and solutions introduc

ed in our efforts to create a robust color-based visual system for the Son

y Aibo robot. We enable the robot to learn its color map autonomously and

demonstrate a degree of illumination invariance under changing lighting con

ditions. Our contributions are fully implemented and operate in real time

within the limited processing resources available onboard the robot. The s

ystem has been deployed in periodic robot soccer competitions enabling tea

ms of four Aibo robots to play soccer as a part of the international RoboCu

p initiative.