Wolfgang Hönig is a Ph.D. candidate in the ACT Lab at the University of
Southern California (USC). He holds a Diploma in Computer Science from the
Technical University Dresden, Germany and an M.S. in Computer Science
(Intelligent Robotics) from USC. His research focuses on enabling large teams
of physical robots to collaboratively solve real-world tasks, combining methods
from artificial intelligence and robotics.
We present methods for motion planning and motion execution that enable
hundreds of robots to operate in challenging, obstacle-rich environments like
warehouses,caves, and asteroid fields. For motion planning, our method combines
ideas from discrete planning and continuous optimization. For motion execution,
we create a link between planning and control, which enables robust and
persistent operationin dynamic environments. We demonstrate our method with
physical experiments onup to 49 robots.