COLLOQUIUM Department of Computer Science and Engineering University of South Carolina Computing Motions for Healthcare Robots Ron Alterovitz Department of Computer Science The University of North Carolina at Chapel Hill Date: November 18, 2011 Time: 1430-1530 (2:30pm-3:30pm) Place: Swearingen 2A27 Abstract Emerging robots have the potential to improve healthcare delivery, from enabling surgical procedures that are beyond current clinical capabilities to autonomously assisting people with daily tasks in their homes. In this talk, we will discuss new algorithms to enable medical and assistive robots to safely and autonomously operate inside people's bodies or homes. These algorithms must compensate for uncertainty due to variability in humans and the environment, consider deformations of soft tissues, guarantee safety, and integrate human expertise into the planning process. We will begin by discussing two new medical devices: steerable needles and tentacle-like robots. These devices are capable of bending around anatomical obstacles to perform procedures at difficult-to-reach sites inside the human body without requiring open surgery. We are developing motion planning and control algorithms that combine sampling-based motion planning, medical image analysis, physically-based simulation, and optimal control theory to maximize the probability of successfully accomplishing a procedure. We are applying these new devices and algorithms to new, safer diagnostic and therapeutic procedures, for lung and brain cancer, that are not possible using existing instruments. We will also introduce demonstration-guided motion planning (DGMP), a new framework for autonomous robotic assistance with daily tasks. In this new framework, a human expert uses kinesthetic demonstrations to teach a personal robot to perform an assistive task, and the robot is then capable of performing that task autonomously in new environments with never-before-seen obstacles. Ron Alterovitz is an Assistant Professor of Computer Science at the University of North Carolina at Chapel Hill. His research focuses on addressing the fundamental algorithmic challenges required to enable robots to safely and autonomously complete tasks for medical and assistive applications. Dr. Alterovitz earned his B.S. with Honors from Caltech in 2001 and completed his Ph.D. at the University of California, Berkeley in 2006. He was selected for an NIH Postdoctoral Fellowship and conducted research at the UCSF Comprehensive Cancer Center. He also spent a year with the Robotics and AI group at LAAS-CNRS (National Center for Scientific Research) in Toulouse, France. Dr. Alterovitz has co-authored a book on Motion Planning in Medicine, was awarded a patent for a medical device, and has presented his work in journals and conferences sponsored by robotics, engineering, and medical associations including IEEE, ACM, the American Association of Physicists in Medicine, and the American Brachytherapy Society. He is the recipient of an NIH Ruth L. Kirschstein National Research Service Award, an IEEE/RSJ IROS Best Paper Finalist award, an IEEE ICRA Best Medical Robotics Paper Finalist award, and the Computer Science Department's Excellence in Teaching Award.