CIS Distinguished Speaker Series
Peter Allen, Ph.D.
Professor, Department of Computer Science
November 13, 2015
Time: 1:00 pm - 2:15 pm
Place: Trabant Theater
Next Generation Surgical Robotics and Deformable Object Recognition and Manipulation
Abstract: Single-port and NOTES surgery are emerging as important new thrusts in minimally invasive medicine. Both of these models require a new generation of robotic devices, sensors, controls and interfaces. In this talk, we first present an in-vivo stereoscopic camera system that can serve as the imaging component of such a platform. The system is equipped with pan/tilt axes and can be inserted through a single incision and mounted on the inside of the body. Second, we have built an Insertable Robotic Effector Platform (IREP) that combines the imaging device with two continuum robot snake-like arms, creating a single port robotic surgery platform. Finally, we will describe a Surgical Structured Light (SSL) system that can recover 3D models of in-vivo anatomy using standard laparoscopes. We will present results from ex-vivo, animal, and human experiments.
We will also present some recent work from our lab on an end-to-end robotic system that can be used to recognize, unfold, place flat, iron, and fold deformable objects such as shirts and pants. The system is based on predictive thin-shell models in simulation to understand the properties of physical clothing, and is shown to work on a variety of different garments.
Bio: Peter Allen is Professor of Computer Science at Columbia University where he heads the Columbia Robotics Laboratory. He received the A.B. degree from Brown University in Mathematics-Economics, the M.S. in Computer Science from the University of Oregon and the Ph.D. in Computer Science from the University of Pennsylvania, where he was the recipient of the CBS Foundation Fellowship, Army Research Office fellowship and the Rubinoff Award for innovative uses of computers. His current research interests include robotic grasping, 3-D vision and modeling, and medical robotics.