Mass Market Mobile Utility Robots by 2005
Hans Moravec
September 8, 1999
Abstract:
Freely-roaming robots that fetch, clean, guard and do other
work have been an elusive fantasy for decades. Industrial mobile
robots today have a very limited market because they work only on
prearranged routes and require expensive, time consuming installation.
A hundredfold increase in onboard computer power in the 1990s has
finally allowed research robots to map their own routes, and prowl
research building hallways and offices autonomously for days at a
time. Industrial applications demand months of trouble-free
operation, which can probably be achieved by replacing the
two-dimensional maps in the present research machines with
thousandfold-richer three-dimensional versions. Building and using 3D
maps in real time is just possible with 1,000 MIPS and very efficient
algorithms. The author is engaged in a three-year project to extend
an existing core of 3D sensing and mapping algorithms into a prototype
commercial demonstration. The likely first product is will be a
basketball-sized "navigation head" with a ring of stereoscopic
cameras, 1,000 MIPS, 3D and application-specific software for retrofit
to existing industrial transport and cleaning machines, that lets them
operate autonomously in new locations simply designated. The
follow-on business plan anticipates a growing industrial market to
support the development of mass-market products, starting with small
specialized automatic home vacuum cleaners around 2005, followed by
more capable home utility robots able to manipulate objects as well as
travel, and, sometime after 2010, a first generation of
broadly-capable "universal robots" able to perform many simple chores
defined by specific application programs.