SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for May
-
An Open Platform for Robotics Research
Mon, May 04, 2009
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Time: 3 PM - 3:50 PMLocation: SSL 150Title: An Open Platform for Robotics Research
Speakers: Steve Cousins and Brian Gerkey
Host: Maja J MataricAbstract:
Personal Robotics research and development are accelerating. A growing community of Open Source developers is creating a platform called ROS that anyone can build on to make the breakthroughs that will lead to new applications. Willow Garage is building a personal robot platform, PR2, which has two arms, a mobile base, and a rich sensor suite. This talk will review the current status of ROS and PR2, and discuss opportunities to join the ROS Open Source community.Speaker Bios:
Steve Cousins is the President and CEO of Willow Garage. Before Willow, Steve was a senior manager at IBM's Almaden Research Center. He has been on the senior staff of the Palo Alto Research Center (PARC), and a researcher at Interval Research Corporation. Steve holds a PhD in CS from Stanford University, and Bachelor's and Master's degrees from Washington University.
Brian Gerkey is the Director of Open Source Development at Willow Garage. Before Willow, Brian was a computer scientist in the SRI Artificial Intelligence Center, and a postdoctoral scholar in the Stanford Artificial Intelligence Lab. Brian holds PhD and MS degrees in computer science from USC, and a BSE degree in computer engineering from Tulane University.
Location: Seaver Science Library (SSL) - 150
Audiences: Everyone Is Invited
Contact: CS Front Desk
-
CS Colloq: Nirupama Bulusu
Tue, May 19, 2009 @ 11:00 AM - 12:30 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Time: 11 AM - 12:30 PMLocation: SAL 222Talk title: Resource-efficient Audiovisual Sensing
Speaker: Prof. Nirupama Bulusu(Portland State University)
Host: Prof. Ramesh GovindanAbstract:
Animal calls, street signs, car honks, etc. The physical world is permeated with sounds and images that can be captured and analyzed using audiovisual sensor networks. Both sensing modalities feature high sampling rates or large sample sizes making them challenging to implement on embedded platforms with sharply limited energy, bandwidth and processing resources.In this talk, I will first show how we have built resource-efficient audiovisual sensing applications on embedded platforms. Application-specific system architectures and compressive sensing algorithms reduce the amount of data sampled and transmitted at each sensor. I will present three real world case studies: cane-toad monitoring; PetrolWatch, a fuel price collection
application; and noise pollution monitoring.Second, many image sensing applications require accurate camera position and orientation in 3D space. Currently, the most accurate camera localization method requires the resource-intensive task of detecting and matching several feature points visible in frames taken from each camera, which is unreasonable for resource constrained sensors. I will describe the
design and evaluation of a highly accurate, robust, efficient, distributed 3D localization system suitable for embedded image sensors that significantly reduces the costs of the point correspondence problem, by using a special 3D target.This talk describes joint work with colleagues at Portland State University, and the University of New South Wales.Bio:
Nirupama Bulusu received the B.Tech degree from Indian Institute of Technology (IIT), Madras, India in 1997, the M.S degree from the University of Southern California in 2000 and the Ph.D degree from the University of California Los Angeles (UCLA) in 2002, all in computer science. Since 2004, she has been an Assistant Professor of Computer Science at Portland State
University. Her research interests lie in sensor networks, with an emphasis on environmental and urban sensing applications. She is a recipient of the NSF CAREER award.
Location: Henry Salvatori Computer Science Center (SAL) - 222
Audiences: Everyone Is Invited
Contact: CS Front Desk
-
Empirical Game-Theoretic Analysis for Practical Strategic Reasoning
Tue, May 26, 2009 @ 10:30 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Michael Wellman (University of Michigan)Host: Prof.Milind TambeAbstract:
The games agents play--in markets, conflicts, or most other contexts--often defy strict game-theoretic analysis. Games may be unmanageably large (combinatorial or infinite state or action spaces), and present severely imperfect information, which could be further complicated by partial dynamic revelation. Moreover, the game may be specified procedurally, for instance by a simulator, rather than in an explicit game form.With colleagues and students over the past few years, I have been developing a body of techniques for strategic analysis, adopting the game-theoretic framework but employing it in domains where direct "model-and-solve" cannot apply. This empirical game-theoretic methodology embraces simulation, approximation, statistics and learning, and search. Applications to canonical market games, for example, yields improved bidding strategies for simultaneous ascending auctions and continuous double auctions. Simulation-based studies of rich trading scenarios further demonstrate the value of empirical methods for extending the scope of game-theoretic analysis.Brief bio:
Michael Wellman received a PhD from the Massachusetts Institute of Technology in 1988 for his work in qualitative probabilistic reasoning and decision-theoretic planning. From 1988 to 1992, Wellman conducted research in these areas at the USAF's Wright Laboratory. For the past 15+ years, his research has focused on computational market mechanisms for distributed decision making and electronic commerce. As Chief Market Technologist for TradingDynamics, Inc. (now part of Ariba), he designed configurable auction technology for dynamic business-to-business commerce. Wellman previously served as Chair of the ACM Special Interest Group on Electronic Commerce (SIGecom), and as Executive Editor of the Journal of Artificial Intelligence Research. He is a Fellow of theAssociation for the Advancement of Artificial Intelligence and the Association for Computing Machinery.
Location: Seaver Science Library (SSL) - 150
Audiences: Everyone Is Invited
Contact: CS Front Desk
