A great deal of research in recent years has focused on robot learning. In many applications, guarantees that specifications are satisfied throughout the learning process are paramount. For the safety specification, we present a controller synthesis technique based on the computation of reachable sets, using optimal control and game theory. In the first part of the talk, we review these methods and their application to collision avoidance and avionics design in air traffic management systems, and networks of unmanned aerial vehicles. In the second part, we present a toolbox of methods combining reachability with data-driven techniques inspired by machine learning, to enable performance improvement while maintaining safety. We will illustrate these “safe learning” methods on a quadrotor UAV experimental platform which we have at Berkeley, including demonstrations of motion planning around people.
Claire Tomlin is the Charles A. Desoer Chair of of the College of Engineering and a professor in EECS at the University of California, Berkely. She was an Assistant, Associate, and Full Professor in Aeronautics and Astronautics at Stanford from 1998 to 2007, and in 2005 joined Berkeley. Claire works in the area of control theory and hybrid systems, with applications to air traffic management, UAV systems, energy, robotics, and systems biology. She is a MacArthur Foundation Fellow (2006), an IEEE Fellow (2010), and in 2017 was awarded the IEEE Transportation Technologies Award.