Return to Session B2 Next Abstract

Session B2: Human-Machine Symbiosis

Dr. Meeko Oishi, University of New Mexico: Formal Assurances for Control of Human-in-the-loop Systems

Location: Hibiscus B
Date/Time: Tuesday, Sep. 17, 8:30 a.m.

Providing formal assurances in human-in-the-loop systems requires reasoning about the mutual adaptation between the human and the automation. However, models of human action that are both accurate and computable are a significant challenge. Further, such models may be dependent upon variables that are measurable only indirectly, such as trust, workload, and attention. We describe the development of new tools in data-driven reachability analysis that enable model-free prediction and control. We employ kernel methods that exploit properties of reproducing kernel Hilbert spaces, to enable efficient computation of stochastic reachability probability measures that are convergent in probability.

Biography:
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 an Associate Professor of Electrical and Computer Engineering at the University of New Mexico. Her research interests include hybrid dynamical systems, 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 UNM Regents’ Lectureship, the NSF CAREER Award, the UNM Teaching Fellowship, the Peter Wall Institute Early Career Scholar 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.



Return to Session B2 Next Abstract