AIC Seminar Series
|Michael Bowling||University of Alberta||[Home Page]|
Notice: hosted by Neil Yorke-Smith
Date: 2008-02-26 at 16:00
Location: EJ228 (SRI E building) (Directions)
A map is a key component for a mobile robot or general AI agent. Maps
at their core allow an agent to answer three questions: (1) "where have
I been?" (2) "where am I now?" and (3) "how do I get where I want to
go?" A huge part of AI/robotics research assumes their existence, and
another large body of research tries to build them. But building maps
is time-consuming, manually intensive, and requires expert knowledge in
the form of detailed models of the agent's motion and sensor apparatus.
In this talk I will show how maps can be learned directly from an
agent's own subjective experience of sensations and actions, without any
models. I'll introduce a new algorithm, Action Respecting Embedding
(ARE), inspired by kernel-based dimensionality reduction techniques. ARE
extracts a low dimensional representation of data that also respects the
provided action labelling. The resulting subjective map explicitly
encodes the robot's trajectory (answering question one), and I'll show
how it can be used for both planning (question three) and localization
(question two). I'll then discuss some recent developments toward
scaling this technique to interesting sized data sets.
Michael Bowling is an associate professor at the University of
Alberta. He received his Ph.D. in 2003 from Carnegie Mellon
University in the area of artificial intelligence. His research
focuses on machine learning and robotics, and he is particularly
fascinated by the problem of how computers can learn to play games
through experience. He has participated extensively in the RoboCup
initiative, an international, autonomous, robot soccer competition.
In 1998, he was the leader of the Carnegie Mellon small-size robot
team, which won the RoboCup world championship. More recently, as
leader of the Computer Poker Research Group at the University of
Alberta, he has helped build some of the world’s strongest poker
playing programs. The programs have won international "bot"
competitions, as well as giving professional players stiff competition
in the First Man-Machine Poker Championship, which took place this
Please arrive at least 10 minutes early as you will need to sign in by
following instructions by the lobby phone at Building E. SRI is located
at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the parking
lots off Fourth Street. Detailed directions to SRI, as well as maps, are
available from the Visiting AIC web page.
There are two entrances to SRI International located on Ravenswood Ave.
Please check the Builing E entrance signage.
©2016 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493