Invited Speakers
Meeko Oishi
Unknown, unstructured, or inscrutable: Designing CPS to accommodate human uncertainty
Human interaction with autonomous systems is pervasive in risk sensitive applications, such as transportation systems, manufacturing processes, and satellite systems. However, few tools exist for modeling, computation, and control that account for uncertainty in human perception, reasoning, and action. We describe challenges in 1) characterizing human heterogeneity in human-in-the-loop dynamical systems, and 2) controller design that is compatible with prioritized human decision making. For the former, we consider semi-automated driving scenarios, and employ kernel embeddings, a non-parametric learning technique, to assess distributional similarities. For the latter, we consider the problem of controller synthesis under infeasible constraints. We synthesize “blameless” controllers that satisfy a priori priorities amongst constraints, in a two-step optimization process, and describe the relationship between blameless and optimal control. Lastly, we explore computational techniques for probabilistic verification of human-in-the-loop systems through propagation of distributions through ReLU neural nets.
Bio: Meeko Oishi received the Ph.D. (2004) and M.S. (2000) in Mechanical Engineering from Stanford University (Ph.D. minor, Electrical Engineering), and a B.S.E. in Mechanical Engineering from Princeton University (1998). She is a Professor of Electrical and Computer Engineering at the University of New Mexico. Her research interests include human-in-the-loop control, stochastic optimal control, and autonomous systems. She previously held a faculty position at the University of British Columbia at Vancouver, and postdoctoral positions at Sandia National Laboratories and at the National Ecological Observatory Network. She is the recipient of the the NSF BRITE Fellowship, the UNM Regents’ Lectureship, the NSF CAREER Award, the Truman Postdoctoral Fellowship in National Security Science and Engineering, and the George Bienkowski Memorial Prize, Princeton University. She was a Visiting Researcher at AFRL Space Vehicles Directorate, and a Science and Technology Policy Fellow at The National Academies.
Hadas Kress-Gazit
Specifications and feedback for high-level tasks
In this talk I will describe how formal methods such as synthesis – automatically creating a system from a formal specification – can be leveraged to design and guarantee robot behavior, and provide feedback about things that might go wrong. I will describe different logical formalisms used to capture tasks and how we can use them to provide warnings to people both before and during robot deployment.
Bio: Hadas Kress-Gazit is the Geoffrey S.M. Hedrick Sr. Professor at the Sibley School of Mechanical and Aerospace Engineering at Cornell University. She received her Ph.D. in Electrical and Systems Engineering from the University of Pennsylvania in 2008 and has been at Cornell since 2009. Her research focuses on formal methods for robotics and automation and more specifically on synthesis for robotics – automatically creating verifiable robot controllers for complex high-level tasks. Her group explores different types of robotic systems including modular robots, soft robots and swarms and synthesizes (pun intended) ideas from different communities such as robotics, formal methods, control, hybrid systems and computational linguistics. She is an IEEE fellow and has received multiple awards for her research, teaching and advocacy for groups traditionally underrepresented in STEM. She lives in Ithaca with her partner and two kids.
Juan Wachs
Gore Robots: Teaching Robots work in Uncontrolled, Variable and Emergent Settings
Robots can already solve sophisticated problems ranging from playing games, autonomous driving, and dancing—given enough observational of data for training. The core of such success resides in efficient algorithms, compliant hardware and robust computing, all implemented using carefully curated data collected before the training phase. Thus, robots learn in a “sterile” domain, under clean, controlled and to some extent supervised environments. As the target domain changes, however, moving to more quotidian scenarios, robots struggle to perform well. It is hard to think of an autonomous car trained in Silicon Valley being able to successfully navigate the crowded streets of New Delhi. Ideally, we would like to see robots that can learn while immersed in a non-sterile setting, while trying, exploring, manipulating and probing the environment as a learning strategy. To address this hurdle, my work in the area of robotics and autonomous systems focuses on transferring skills and knowledge from controlled settings to the wild. In this talk, I emphasize strategies and techniques to address fundamental challenges in emergency medicine. Specifically, I will discuss work related to surgical assistants, telesurgery, and skill augmentation. While medicine is the main domain of the research discussed, the outcomes and findings are applicable to the range of field robotics. Progress in these directions will contribute to the public purpose of creating the knowledge for developing robots that are more accessible, effective and sensitive to social needs.
Bio: Dr. Juan Wachs is a Professor and Faculty Scholar in the Industrial Engineering School at Purdue University, Professor of Biomedical Engineering (by courtesy) and an Adjunct Associate Professor of Surgery at IU School of Medicine. He is currently serving at NSF as a Program Director for robotics and AI programs at CISE. He is also the director of the Intelligent Systems and Assistive Technologies (ISAT) Lab at Purdue, and he is affiliated with the Regenstrief Center for Healthcare Engineering. He completed postdoctoral training at the Naval Postgraduate School’s MOVES Institute under a National Research Council Fellowship from the National Academies of Sciences. Dr. Wachs received his B.Ed.Tech in Electrical Education in ORT Academic College, at the Hebrew University of Jerusalem campus. His M.Sc and Ph.D in Industrial Engineering and Management from the Ben-Gurion University of the Negev, Israel. He is the recipient of the 2013 Air Force Young Investigator Award, and the 2015 Helmsley Senior Scientist Fellow, and 2016 Fulbright U.S. Scholar, the James A. and Sharon M. Tompkins Rising Star Associate Professor, 2017, and an ACM Distinguished Speaker 2018. He is also the Associate Editor of IEEE Transactions in Human-Machine Systems, Frontiers in Robotics and AI.