Loading Events

« All Events

  • This event has passed.

GRASP Special Seminar: Jeremy Gillula, University of California at Berkeley, “Guaranteeing Safe Online Machine Learning via Reachability Analysis”

January 16, 2014 @ 12:00 pm - 1:00 pm


 Reinforcement learning has proven itself to be a powerful technique in robotics, however it has rarely been employed to learn in a hardware-in-the-loop environment due to the fact that spurious training data could cause a robot to take an unsafe (and potentially catastrophic) action. We will present a method for overcoming this limitation known as Guaranteed Safe Online Learning via Reachability (GSOLR), in which the control outputs from the reinforcement learning algorithm are wrapped inside another controller based on reachability analysis that seeks to guarantee safety against worst-case disturbances.

After defining the relevant backwards reachability constructs and explaining how they can be calculated, we will formalize the concept of GSOLR and show how it can be used on a real-world target tracking problem, in which an observing quadrotor helicopter must keep a target ground vehicle with unknown (but bounded) dynamics inside its field of view at all times, while simultaneously attempting to build a motion model of the target.  Extensions to GSOLR will then be presented, which allow the safety of the system to automatically become neither too liberal nor too conservative, thus allowing the machine learning algorithm running in parallel the widest possible latitude while still guaranteeing system safety. These extensions will be demonstrated on the task of safely learning an altitude controller for a quadrotor helicopter.  These examples demonstrate the GSOLR framework’s robustness to errors in machine learning algorithms, and indicate its potential for allowing high-performance machine learning systems to be used in safety-critical situations in the future.


Jeremy Gillula is a postdoctoral scholar at the University of California at Berkeley. He obtained his masters and doctoral degrees from Stanford University, where his research focused on algorithms for guaranteeing safety for online learning methods applied to robotic systems. Prior to that, he did his undergraduate work at Caltech, where he was a key member of the school’s Desert DARPA Grand Challenge team, working on sensing systems and sensor fusion. In addition to robotics, he is also interested in the area of technology policy and law, particularly how to best regulate the burgeoning areas of autonomous ground and aerial vehicles.


January 16, 2014
12:00 pm - 1:00 pm
Event Category: