Presenter: Gunter Niemeyer (Homepage)

Event Dates:
  Friday December 10, 2010 from 11:00am to 12:00pm

From the very beginning of robotics and telerobotics, we have envisioned using a robot to be our presence at a second location. This includes seeing what the robot sees, feeling what the robot feels. And it is still true today - operators sooner or later want to feel the remote world. Traditional wisdom suggests feeding back sensor information to the user as directly as possible, making the system as transparent as possible. Yet this has always left us in a tight bind between performance and stability.

Presenter's Biography:

Dr. Günter Niemeyer is a senior research scientist at Willow Garage Inc. and a consulting professor of Mechanical Engineering at Stanford University. His research examines physical human-robotic interactions and interaction dynamics, force sensitivity and feedback, teleoperation with and without communication delays, and haptic interfaces. This involves efforts ranging from realtime motor and robot control to user interface design. Dr. Niemeyer received his M.S. and Ph.D. from MIT in the areas of adaptive robot control and bilateral teleoperation, introducing the concept of wave variables. He also held a postdoctoral research position at MIT developing surgical robotics. In 1997 he joined Intuitive Surgical Inc., where he helped create the daVinci Minimally Invasive Surgical System. This telerobotic system enables surgeons to perform complex procedures through small (5 to 10mm) incisions using an immersive interface and is in use at hundreds of hospitals worldwide. He joined the Stanford faculty in the Fall of 2001, directing the Telerobotics Lab and teaching dynamics, controls, and telerobotics. He has been a member of the Willow Garage research group since 2009.

Presenter: Pietro Perona (Homepage)

Event Dates:
  Friday November 19, 2010 from 11:00am to 12:00pm

The web is not yet perfect: while text is easily searched and organized, pictures (the vast majority of the bits that one can find online) are still digital dark matter. In order to see how one could make pictures first-class citizens of the web, I explore the idea of Visipedia, a visual interface for Wikipedia that is able to answer visual queries and enables experts to contribute and organize visual knowledge. Five distinct groups of humans would interact through Visipedia: users, experts, editors, visual workers, and machine vision scientists.

Presenter's Biography:

Dr. Pietro Perona is the Allen E. Puckett Professor of Electrical Engineering at Caltech. He directs Computation and Neural Systems (www.cns.caltech.edu), a PhD program centered on the study of biological brains and intelligent machines. Professor Perona's research centers on vision. He has contributed to the theory of partial differential equations for image processing and boundary formation, and to modeling the early visual system's function. He is currently interested in visual categories and visual recognition.Dr. Perona's research interests also include Computer Vision: recognition, navigation, human-computer interfaces, texture analysis, multiresolution image analysis, diffusions and Human Vision: perception of shape-from-shading, perception of texture and models of early vision.

Thursday October 28, 2010

Mechanical engineer Katherine Kuchenbecker tells a story about one of the most compelling videos she’s ever seen about the sense of touch.....

Wednesday October 27, 2010

 

Engineering professor invited to appear on Colbert Report

 

This week, a Penn professor helped Stephen Colbert in his quest to “keep fear alive.”

Presenter: Sangbae Kim (Homepage)

Event Dates:
  Friday October 29, 2010 from 11:00am to 12:00pm

Mobile robot designers are increasingly searching for inspirations and design cues from biological models. Biomechanics research of animals provides an invaluable source of ideas for legged robot design but the process of implementation involves great complexity. The direct implementation of biological features and morphology often becomes ineffective and misleads engineers due to various reasons.

Presenter's Biography:

Sangbae Kim is Assistant Professor of Mechanical Engineering and the director of Biomimetic Robotics Lab at MIT. His research focuses on bio-inspired robotic system design based on biotensegrity structure, composite structure manufacturing, and legged system control. His design approaches highlight the importance of understanding the difference between biological systems and counterparts of engineering systems by careful observations and embodiment of the principles. Kim’s achievement on bio-inspired robot development includes the world‘s first directional adhesive based on gecko lizards, and a climbing robot, Stickybot, that utilizes the directional adhesives to climb smooth surfaces. He received the Best Paper Award for the IEEE Transactions on Robotics 2008 and the Best Student Paper Award at IEEE International Conference on Robotics and Automation 2007. His bio-inspired climbing robot was selected as one of the best inventions in Time magazine in 2006 and also featured in more than 100 media exposures including Forbes magazine, Wired Science, the History Channel, and the Discovery Channel. Kim received his B.S. in Mechanical engineering from Yonsei University, Seoul, South Korea. He earned his Ph.D. in M.E. from Stanford University, in 2008 and joined MIT in 2009.

Presenter: Drew Bagnell (Homepage)

Event Dates:
  Friday October 22, 2010 from 11:00am to 12:00pm

Programming robots is hard. While demonstrating a desired behavior may be easy, designing a system that behaves this way is often difficult, time consuming, and ultimately expensive. Machine learning promises to enable "programming by demonstration" for developing high-performance robotic systems. Unfortunately, many approaches that utilize the classical tools of supervised learning fail to meet the needs of imitation learning.


Presenter's Biography:

J. Andrew (Drew) Bagnell is an Associate Professor in the Robotics Institute and Machine Learning Departments at Carnegie Mellon University. He received his PhD from Carnegie Mellon in 2004. Bagnell's research focuses on the intersection of  machine learning with computer vision, optimal control, and robotics. His interests in machine learning range from algorithmic and theoretical development to delivering fielded learning-based systems.

Tuesday October 12, 2010

Popular Science magazine has named Penn Engineering’s Katherine Kuchenbecker to its annual “Brilliant 10” list of the country’s top young scientists to watch.

Presenter: Marcia O'Malley (Homepage)

Event Dates:
  Friday November 5, 2010 from 11:00am to 12:00pm

Our lab has been designing and building exoskeleton-based therapeutic robots for stroke and spinal cord injury rehabilitation, and testing these devices, along with modified commercial devices, in the clinical domain for the past five years. In this talk, I will present an overview of our efforts to date. I will highlight the design and implementation of the RiceWrist device for upper extremity rehabilitation. Then, I will discuss robotic measures of motor impairment and how these measures can be used to ensure clinical relevance of robotic rehabilitation systems.

Presenter's Biography:

Marcia O’Malley is an Associate Professor in the Mechanical Engineering and Materials Science Department at Rice University, and is a co-founder of Houston Medical Robotics.  She holds a joint appointment in Computer Science at Rice, and is an Adjunct Assistant Professor in Physical Medicine and Rehabilitation at Baylor College of Medicine. At Rice, her research interests focus on the issues that arise when humans physically interact with robotic systems. One thrust of her lab is the design of haptic feedback and shared control between robotic devices and their human users for training and rehabilitation in virtual environments. Psychophysical studies provide insight into the effect of haptic cues on human motor adaptation, skill acquisition, and the restoration of motor coordination. Another area of interest is nanorobotic manipulation with haptic feedback, and the use of vision-based sensing for control of robotic manipulators and the generation of force feedback to the operator.  She has also explored the use of haptic devices for teaching the fundamentals of dynamic systems and control in the mechanical engineering curriculum.  In 2008, she received the George R. Brown Award for Superior Teaching at Rice University. O’Malley is a 2004 Office of Naval Research Young Investigator and the recipient of the NSF CAREER Award in 2005. Additionally, she is chair of the IEEE Technical Committee on Haptics. She serves as an Associate Editor for the IEEE Transactions on Haptics and the ASME/IEEE Transactions on Mechatronics.

Monday September 13, 2010

Joe Romano, a PhD student from the Penn Haptics Group, spent the summer at Willow Garage enabling the PR2 to perform fine motor control with its grippers using tactile information, as well as understand a variety of other tactile cues. Joe's approach attempts to recreate the same sensory information that humans use when completing similar tasks.

Tuesday September 21, 2010

The GRASP (General Robotics, Automation, Sensing, and Perception) lab, upstairs at the University of Pennsylvania's Engineering School, is in the million-hits club at YouTube this summer, as videos of its book-sized quadro-rotor flying robots have been promoted as gadgets that can, as Gizmodo.com cheerfully put it, "fly in your window and kill you as you sleep.".......