The Robot Autonomy and Interactive Learning (RAIL) research lab focuses on the development of robotic systems that operate effectively in complex human environments, adapt to user preferences and learn from user input.  Directed by Prof. Sonia Chernova, the lab’s research spans adjustable autonomy, semantic reasoning, human-robot interaction and cloud robotics, particularly as applied to robot learning from demonstration (LfD) — the development of algorithms that enable a robot to learn new tasks with the aid of demonstrations or instructions performed by a human teacher.  The following article and book provide an overview of the intersection of these research areas:

  • Argall$^dagger$, Brenna, Chernova$^dagger$, Sonia, Veloso, Manuela, Browning, Brett: A survey of robot learning from demonstration. In: Robotics and Autonomous Systems, 57 (5), pp. 469–483, 2009, (($^dagger$ Equal contribution by first two co-authors.)).
  • Chernova, Sonia, Thomaz, Andrea: Robot Learning from Human Teachers. Morgan & Claypool Publishers, 2014.

See the Projects and Publications pages for an in-depth view of our recent work.