Toyota AI Seminar: Mapping in the MAGIC 2010 robotics competition

In this talk, I'll describe how our team of 14 robots, winners of the
MAGIC 2010 competition, shared and combined data to produce a
consistent global map. Central challenges included inaccurate
dead-reckoning information, limited communications, moving and lethal
obstacles, and the need for robustness in a wide variety of indoor and
outdoor environments. Offsetting these, a human operator was allowed
to assist the robots. This created new challenges, however, including
interface design and operator workload management. We'll describe
several interesting failures of our system and how, in one case, the
operator was able to recover, and in the other, how a complete
recovery proved impossible.
Edwin Olson is an assistant professor at the University of Michigan
with research interests in robot autonomy, perception, and
learning. In 2010, he led Team Michigan to first place in the MAGIC
2010 robotics competition. He received his PhD, M.Eng., and B.S. from
MIT, where he was also a core member of MIT's DARPA Urban Challenge
team.