Toward Assured and Resilient Autonomous Systems Operations

  • Date Wednesday, December 19, 2018  Time 11:00 AM
  • Speaker Dr. Nicola Bezzo, Assistant Professor at the University of Virginia (UVA)
  • Location Galois Inc., 421 SW 6th Ave. Suite 300, Portland, OR, USA, (3rd floor of the Commonwealth building)
  • Galois is pleased to host the following tech talk.
    These talks are open to the interested public--please join us!
    (There is no need to pre-register for the talk.)

    The presentation will not be live streamed.

Cyber-physical systems (CPS) and especially autonomous vehicles like drones and driverless cars are becoming increasingly popular thanks to their sophisticated hardware and software capabilities. As they find their way into our society, it becomes imperative to guarantee that they can always be safe even during unforeseen and unpredictable events. Unfortunately, at the moment there are no real solutions that can guarantee safety at runtime while an autonomous system explores, learns, plans and controls its actions through unknown, uncertain, and adversarial environments. It is thus necessary to develop theories for online motion planning and control of autonomous systems to guarantee resiliency and safety against unforeseen, unpredictable, and adversarial situations, hence to enable assured autonomous operations. To ensure resiliency, we need multidisciplinary approaches to provide state awareness, intelligence, control, safety, security, effective human-system interaction, robust communications, and reliable computation and operation.

In this talk, I will give an overview of my group’s recent work on run-time monitoring, planning, and resilient control of autonomous systems. I will first introduce our online reachability analysis technique and self-triggered scheduling approach to guarantee safety and liveness during autonomous systems operations in uncertain environments. I will then focus the rest of the talk on cyber-security issues in modern CPS demonstrating our model-based resilient state estimation, control, and recovery techniques to deal with sensor spoofing.

Nicola Bezzo is an Assistant Professor in Systems Engineering and Electrical and Computer Engineering at the University of Virginia (UVA). His research focuses on the development of assured and resilient techniques for autonomous cyber-physical systems. His research is supported by the Defense Advanced Research Projects Agency (DARPA), Office of Naval Research (ONR), and the National Science Foundation (NSF).

Prior to joining UVA, he was a Postdoctoral Researcher at the PRECISE Center, in the Department of Computer and Information Science at the University of Pennsylvania (UPenn) where he worked on topics related to robotics and cyber-physical systems security. He received a Ph.D. degree in Electrical and Computer Engineering from the University of New Mexico where he focused on the development of theories for motion planning of aerial and ground robotic systems under communication constraints. Prior to his Ph.D. he received both M.S. and B.S. degrees in Electrical Engineering with honors (summa cum laude) from Politecnico di Milano, Italy. Nicola was the recipient of the 2010 Gold Medal from the Politecnico School of Engineering and the 2011 Best Graduate Student Service Award from the University of New Mexico. He has received the 2016 Robotics and Automation Magazine Best Paper Award and the Best Paper Award at the 2014 CPSWeek International Conference on Cyber-Physical Systems.