Print This Page

College of Engineering

A&A Seminar on Autonomous Systems
WhenFriday, Sep 13, 2019, 4 – 5 p.m.
Campus locationGuggenheim Hall (GUG)
Campus room305
Event typesLectures/Seminars

PhD candidate Sylvia Herbert, UC Berkeley

"Safe and Efficient Control of Autonomous Systems Inspired by Cognitive Science"

Humans are remarkably adept at operating in open environments, especially when compared to modern robots and autonomous systems.  In this talk I will discuss my work on adapting human decision-making frameworks from cognitive science to robot algorithms to mimic human strengths in real-time, safe path planning. In particular, humans are talented at (a) planning using simple and efficient mental models with knowledge of how these simple plans map to safety constraints on their true dynamics, and (b) switching between “Fast” and “Slow” modes of planning based on feasibility and computational burden.

We adapt these techniques to autonomous systems using the framework FaSTrack: Fast and Safe Tracking, which "robustifies” real-time planning algorithms (e.g. rapidly-exploring random trees, model-predictive control) in a priori unknown environments by employing game theory and reachability analysis. Equipped with this precomputation, systems can use fast and simple online planning algorithms while ensuring safety with respect to the high-dimensional system.  Moreover, these precomputed safety constraints allow for intelligent switching between fast and slow planning methods.  I will show these methods applied to a quadcoptor in a motion capture room planning in real time to navigate around a priori unknown obstacles and humans.

Sylvia Herbert is a PhD candidate in Electrical Engineering and Computer Science at UC Berkeley. She works with Professor Claire Tomlin in the Hybrid Systems Lab and the Berkeley Artificial Intelligence Research (BAIR) Group. 

Her research interests are in developing theoretically sound techniques for efficiently guaranteeing safe control based on available models of systems and given information about environments. These techniques should be able to quickly adapt to unexpected changes and new information in the autonomous system or the environment.  More information on her research interests can be seen at

Printed: Tuesday, November 12, 2019 at 4:53 PM PST