Abstract: Medical robotic systems are entering the hospital more and more, especially in the field of image guided surgery and radiology. A peculiarity of these medical robotic systems is the necessary interaction with the patients and with the medical staff. For example, teleoperated surgical robots are used as assistant in minimally invasive surgery to hold the instruments inside the patient or interventional radiology robotic systems are used to move imaging devices around the patient. The control of theses medical robotic systems is very often vision based and requires taking into account the interactions with the patient as well as the doctor in the case of teleoperated systems. Model based control algorithms very often find their limit, e.g., when there are interactions with the patient body, when there is a human operator in the loop, when the instruments are difficult to model, or to analyze in real time medical image feedback. Learning algorithms can be shown to be useful in these situations and outperform model-based techniques. Several practical examples will be presented.
Bio: Michel de Mathelin received the Electr. Eng. degree from Louvain University, Louvain-La-Neuve, Belgium, in 1987 and the M.S. and Ph.D. degrees in electrical and computer engineering from the Carnegie Mellon University, Pittsburgh, PA, in 1988 and 1993, respectively. During 1991-1992, he was a Research Scientist in the Department of Electrical Engineering, Polytechnic School of the Royal Military Academy, Brussels, Belgium. In 1993, he became Assistant Professor at Strasbourg University, France. Since 1999, he has been Professor at Télécom Physique Strasbourg, University of Strasbourg. He has been the head of the Automation, Vision and Robotics research group (60 people) from 2000 to 2012. Since 2013, he is the Director of the ICube Laboratory (UMR CNRS-UNISTRA 7357) with more than 650 people in the area of Engineering and Computer Science with a strong focus on biomedical and environmental engineering. In 2017, he became vice-president for technology transfer of the University os Strasbourg. Michel de Mathelin has been Associate Editor of the IEEE Control System Technology Journal from 2003 to 2011. His current research interests include medical robotics, visual servoing, adaptive and robust control. He has co-authored more than 200 international refereed journal and conference papers. With his co-authors, he received the ICRA 2004 Best Vision Paper Award, the 2005 King-Sun Fu Memorial Best IEEE Transactions on Robotics Paper Award. He holds 8 patents and is co-founder of Axilum Robotics, a startup in medical robotics. Dr. Mathelin is a fellow of the Belgian American Educational Foundation.
