Conferences, Lectures, & Seminars
Events for January
-
Manifold Learning in Human-Robot Teams
Mon, Jan 05, 2009 @ 02:30 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Prof. Chad Jenkins, Brown University
Host: Prof. Maja MataricAbstract:
A principal goal of robotics is to realize embodied systems that are effective collaborators in human endeavors pursued in the physical world. Human-robot collaborations can occur in a variety of forms, including autonomous robotic assistants, mixed-initiative robot explorers, and augmentations of the human body. For these collaborations to be effective, human users must have the ability to realize their intended behavior into actual robot control policies. At run-time, robots should be able to manipulate an environment and engage in two-way communication in a manner suitable to their human users. Further, the tools for programming, communicating with, and manipulating using robots should be accessible to the diverse sets of technical abilities present in society. Towards the goal of effective human-robot collaboration, learning from demonstration (LfD) has emerged as a central theme of our work for the natural instruction of autonomous robots by human users. In robot LfD, desired cognitive functions for a robot (perception, decision making, or motion control) are implicit in human demonstration rather than explicitly coded in a computer program.In this talk, I will present our work into learning priors from human demonstration for robot perception and control using manifold-based dimension reduction. My specific focus will be the development and application of manifold learning algorithms to estimate subspace priors for spatial and time-series data generated by humans. I will discuss our approach to spatio-temporal dimension reduction in the context of manifold learning. Using manifold learning, results will be presented from learning priors for: 1) classifying tactile signatures to recognize successful grasps on the NASA Robonaut, 2) providing low-dimensional control spaces for neural prosthetics, 3) learning motion primitives from human movement data, and 4) extracting kinematic models and poses from multi-view video. Our approach to learning priors will be cast in our broader context for policy learning and computational models for communication in multi-robot multi-human systems.Biography:
Odest Chadwicke Jenkins, Ph.D., is an Assistant Professor of Computer Science at Brown University. Prof. Jenkins earned his B.S. in Computer Science and Mathematics at Alma College (1996), M.S. in Computer Science at Georgia Tech (1998), and Ph.D. in Computer Science at the University of Southern California (2003). He is a recipient of the Presidential Early Career Award for Scientists and Engineers (PECASE) for his work in physics-based human tracking. He has also received Young Investigator awards from the Office of Naval Research (ONR) for his research in learning dynamical primitives from human motion and the Air Force Office of Scientific Research (AFOSR) for his work in manifold learning and multi-robot coordination. His research addresses problems in robot learning and human-robot interaction, primarily focused on robot learning from demonstration, as well as topics in computer vision, machine learning, and computer animation.Location: Seaver Science Library (SSL) - 150
Audiences: Everyone Is Invited
Contact: CS Colloquia
-
A Comprehensive Approach to Macroprogramming
Tue, Jan 13, 2009 @ 11:00 AM - 12:30 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Prof. Kamin Whitehouse, University of Virginia
Host: Prof. Ramesh GovindanAbstract:
Networks of wireless, embedded devices are increasingly useful for interfacing with the physical world, and promise to revolutionize many areas of science and engineering. However, these systems are very complex and difficult to manage; building even a simple application entails several interacting tasks like distributed programming, resource management, and wireless networking. We are simplifying this process with a system called MacroLab that provides a Matlab-like interface that is natural for both sensing and control. With MacroLab, the developer writes a single, sequential program and the compiler automatically breaks it into smaller parts and distributes it throughout the network. MacroLab programs execute efficiently and are easy for most scientists and engineers to write. The key to MacroLab is the ability to perform whole-system optimization based on the program, the network topology, and resource availability. In current work, we are taking this approach to the next level by exploiting the holistic view offered by MacroLab to support macro-level testing, debugging, and analysis.Biography:
Prof. Whitehouse is an assistant professor at the University of Virginia whose research focuses on new technologies that bridge the gap between the virtual and physical worlds. Whitehouse received his MS and PhD in Computer Science from UC Berkeley. He received his BS in Electrical Engineering and his BA in Philosophy and Cognitive Science from Rutgers University.Location: Henry Salvatori Computer Science Center (SAL) - 222
Audiences: Everyone Is Invited
Contact: CS Colloquia
-
Animating Interactive Characters using Motion Capture and Simulation
Thu, Jan 15, 2009 @ 04:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Prof. Victor Zordan, University of Callifornia, Riverside
Host: Prof. Gerard MedioniAbstract:
Automatically creating humanlike animation for characters is difficult, especially in interactive applications such as video games and online environments where the characters must move realistically and respond to unpredicted events while also remaining controllable at a high level by the users of such virtual worlds. In this talk, I describe several techniques for generating realistic character motion using examples recorded from humans and physically based models, focusing primarily on controllable, responsive characters that combine dynamic simulation and recorded data. My research relies on human examples to dictate movement style and on simulation to create physically plausible motion that includes believable interactions with the environment and other simulated characters. Emphasis is placed on generating believable anticipated and unpredicted responses within a unified animation system that employs both motion capture and simulation as mechanisms for generating interactive humanlike motion.Biography:
Assistant Professor of Computer Science and Engineering at UC Riverside, Dr. Victor Zordan received his Ph.D. in computer science from Georgia Institute of Technology. Professor Zordan's research interests fall in several areas of computer animation including human motion, physically based modeling, interactive virtual environments, behavior control, and game interfaces. He has published numerous papers on control for human and humanlike characters, as well as on several other topics including anatomical modeling, procedural approaches, and video-based animation.Location: Seaver Science Library (SSL) - 150
Audiences: Everyone Is Invited
Contact: CS Colloquia
-
Geospatial Information Technology and Robotic Vision
Thu, Jan 22, 2009 @ 04:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Bingcai Zhang, BAE Systems, Engineering Fellow
Host: Prof. Cyrus ShahabiAbstract:
Geospatial information technology or 3D mapping is the technology that extracts most 3D geospatial data such as elevations and vector maps from digital images. In the last two decades, BAE Systems has developed advanced computer algorithms to automate 3D geospatial data extraction from digital images. These algorithms may be applicable to navigate a robot in urban environment and complex terrain. There are significant similarities between robot vision and 3D mapping, between human vision process and 3D image matching process. In this talk, I will discuss the challenges of this technology for both 3D mapping and robot navigation.I will show some practical examples in 3D images. I will also talk about opportunities of this technology in a world of global recession and aging population. I will bring in 3D glasses such that everyone has a chance to experience 3D imaging.Biography:
Dr. Zhang is an engineering fellow at BAE Systems, the premier global defense and aerospace company. He joined BAE Systems in September 1995 right out of University of Wisconsin-Madison, where he earned his Ph.D. in engineering college and MS in computer science. His research interests are: (1)geospatial information technology and 3D mapping; (2)robot vision and unmanned systems; and (3)3D geoweb search. He has held positions as chief architect, chief photogrammetrist, R&D manager, and engineering fellow with BAE Systems.Location: Seaver Science Library (SSL) - 150
Audiences: Everyone Is Invited
Contact: CS Colloquia
-
What should we learn from 25 years of the Internet: A DNS case study (CS Distinguished Lecture)
Thu, Jan 29, 2009 @ 04:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Paul Mockapetris, Chairman and Chief Scientist, Nominum Inc.
Host: Prof. Ramesh GovindanAbstract:
There are several "definitive" Internet histories, and there will be more. While there are many reasons to study history, this talk concentrates solely on finding lessons that will have value looking forward, and uses several examples from naming and DNS as its case study. While many argue that a clean slate is the best way forward, we beg to differ. We begin by looking at the general problem of extracting useful ideas from Internet history.The DNS case study has three foci. The first is the long and flexible "food chain" that comprises today's DNS industry and dataflow. The second is the roots and implications of securing the DNS infrastructure. Lastly we look at what it will take to vastly expand the role of naming in the Internet, either by DNS evolution or replacement.
Location: Seaver Science Library (SSL) - 150
Audiences: Everyone Is Invited
Contact: CS Colloquia
