Information on
the Mobile Robotics
and
Shape Recognition
group at
CIM
The mobile robotics and shape recognition group is an informal
grouping of people and projects at the centre.
The group has at least three
mobile robots sporting a collection of sensors including sonar, video,
BIRIS, and infra-red reflectance, depending on the current experiments
in progress. The primary computing resources are linux boxes with
a substantial collection of SGI workstations,
some SUN sparc's, and a few other computing
devices integrated into the
general CIM computing environment.
This group is involved in issues of form representation and discovery.
This relates specifically to the
-
exploration and representation of
unknown environments using mobile robots,
- and the representation and
recognition of objects.
Key technical foci are the abstraction of shape models across scale,
the relationship between signals and symbolic descriptions.
Projects that we are preoccupied with
include:
robot pose estimation (i.e. localization),
place recognition, efficient exploration strategies, robot rendezvous,
multi-robot collaboration,
map representation, map merging and navigation.
A typical prosaic objective is to create a robot than
can learn your office layout over the weekend:
It is delivered on Friday, you open the box, leave it on the floor, and
go home. By Monday morning the robot would have explored the
office and would be able to carry out delivery and search tasks (``Get
my mail and find Mary and escort her to the conference room''). Better
yet, it should be able to do this during the week and understand the
dynamics of pedestrian traffic.
Other Information
A small amount of additional information, some
papers and some demo software from the mobile
robotics group
is available from the mostly-obsolete
FTP site.
Most information is currently being posted via the projects page (below).
Information is also available in the form of a Newton Book
for perusal using an Apple Newton device.
Click
here to obtain a "stuffit" archive of this book. (Note:
some of the terms above may be tradmarked by their respective owners.)
A brief abstract of some of our work on position estimation in different
contexts is also
available for download as a Newton book.
Outside Information Sources
This is a great source
of robot books kits, movies, and toys.
Dudek's
book on mobile robotics introduces and
examines many of the same issues
that the research group examines.
Robotics Internet Page at U. Mass.
There is an archive for several general
CIM Technical Reports.
Cambridge University Press.
MIT Press.
The IRIS and PRECARN funding organization page.
A very brief page pointing to this one.
For those that want a
minimal pointer (mainly for the benefit of web robots).
You can get more information
several current or recent research projects.
Several of these project descriptions have on-line publications
accompanying them.
Most work here
is carried out by graduate students, through faculty collaboration, or
in the context of undergraduate term projects, as well as by
occasional post-doctoral researchers.
This includes work on robot position estimation, navigation,
exploration, and multi-robot collaboration.
News or Adventures
Robotic Competitions
A team of McGill students was selected to participate in the
Legged Robot League of Robocup 2000 (and also RoboCup 1999).
They were one of only 9 teams selected world-wide in 1999 (3 more
were added in 2000). The team has
a website at this URL.
Students affiliated with the lab
entered the
1997 and 1998 American Association for
Artificial Intelligence
Mobile Robotics Competition,
and they won! This was a competition that dealt with getting a mobile
robot to recognize objects using simple computer vision, and do autonomous
navigation.
Workshop
People from the lab were involved in the first and second
IEEE Workshop on Perception for Mobile Agents 1999 and 2000
and well as the locally-held
Vision Interface 2000 and the
International Symposium on Robotics 2000.
Graduate students
If you want to apply to be a grad student working in this group, you can
get
further information from the school of computer science.
Note that CIM is not an "academic unit" and different faculty are
officially associated with different departments.
Movies
We have done work on robot-mounted range sensing and object
recognition.
A somewhat dated two-minute demo movie is
available in
quicktime format (7.4 Meg binhex encoded)
or in
MPEG format (3.1 Meg).
The quicktime version is a compressed MacBinary file. The
MPEG version has no audio track; a major disadvantage.
Be warned that to keep the size down, the movie has been severly
compressed and the quality isn't great (image size is 160x120 but it
should be played a double size on most machines).
Here's a brief
movie clip
of the McGill entry at the
AAAI 1997 mobile robot competition (it was the winner).
We also have a
MOVIE of how things were
going part way through the
development effort.
It shows the robots, some of the people, and explains
more-or-less how
things work. The movies are in
Apple QuickTime
format. The second runs 5 minutes, and is about 16 Meg
in size. That means to view it, you need a
QuickTime viewer
or
plugin from Apple Computer.
As far as I know, although this is the preeminent
format for digital video and multimedia content, it is only
freely available for
Mac OS, Win 3.1 or Win 95/NT.
A bibliography on mobile robotics, together with
entries on related research topics, can be
searched
on-line.
A slightly dated list of selected references
is
also
available in postscript form.
Submit your own
You are
invited to
submit additional entries
to be included
in the bibliography.
Usage
Usage info?
Note: this page is informally maintained
by
Professor Gregory Dudek and
Saul Simhon
from
the
School of Computer Science
and, as such, is not meant to be
representative of research at
the Centre for Intelligent Machines (CIM) or
McGill as a whole.
It's almost certainly not up-to-date.
