End Notes
For the roboticist’s bookshelf.Hobart Everett literally wrote the book, Sensors for Mobile Robots, 52 on robotic sensors,
which provides both analytical details of sensors plus practical experience from
Everett’s many years with the Navy work on robots. He has built a series of mobile
robots called ROBART (a pun on Everett’s nickname, Bart); ROBART II has been in
continuous operation since 1982. Everett’s laboratory has to be one of the most ideally
situated in the world. It is in San Diego, overlooks the Pacific Ocean, and is adjacent
to a frequently used volleyball court.
Hans Moravec.
If Joe Engelberger is known as the father of industrial robotics, Hans Moravec is best
known as the father of AI robotics. He has also become a well-known author, arguing
for the inevitability of machine intelligence in controversial books such as Mind
Children94 and Robot: mere machine to transcendent mind. 96 His work with the Stanford
Cart was a catalyzing event in attracting attention to robotics after the years of
slow progress following Shakey. Documentaries will occasionally run edited footage
of the Stanford Cart navigating outdoors, avoiding obstacles. Since the cart traveled
in a stop-start fashion, with 15 minutes or so between updates, the location of
the shadows visibly change. Moravec’s office mate, Rodney Brooks, helped with the
recording.
Undergraduates and sonars.
It is interesting to note that the first serious analysis of the Polaroid sonars was done
by an undergraduate at MIT, Michael Drumheller. Drumheller’s paper, “Mobile Robot
Localization Using Sonar,” was eventually published in the IEEE Transactions on
Pattern Analysis and Machine Intelligence in 1987, and became a classic.
Ballard and Brown.
Dana Ballard and Chris Brown wrote the first textbook on computer vision, entitled
appropriately Computer Vision. Both have worked with robots, though Brown more
than Ballard. I met both of them at a workshop at a beach resort in Italy in early 1990.
I had just arrived from a harrowing bus ride from the airport and had to go past the
pool to my room in the hopes of recovering from jet lag before the meeting started in
the morning. As I walked past the pool, one of my friends said, “Oh, Chris Brown
is over there!” I immediately turned to look for what I thought would be an older,
dignified author wearing a suit and tie. Instead, I got soaked by a tall, youngishman
impishly doing a cannonball into the pool. From that day on, I never assumed that
textbook authors were dull and dignified.
The tallest roboticist.
Tom Henderson at the University of Utah was one of the founders of the concept of
logical sensors. Henderson is also the tallest known roboticist, and played basketball
in college for Louisiana State University.
Stereo with a single camera.
Ray Jarvis at Monash University in Austraila came up with a clever way of gathering
rectified stereo images from a single camera. He used a prism to project two slightly
different veiwpoints onto the lens of a camera, creating an image which had a different
image on each side. The algorithm knew which pixels belong to each image, so
there was no problem with processing.
USAR and Picking Up the Trash.
While picking up trash seems mundane, most people would agree that finding and
rescuing survivors of an earthquake is not. The two tasks have much in common,
as illustrated by the work of Jake Sprouse, and behaviors and schemas developed
in one domain can be transferred to another. Sprouse was a member of the Colorado
School ofMines’ 1995 IJCAI competition team. The same vision programhe wrote for
finding “red” was used to find “international orange.” Later, he extended the search
strategies to incorporate aspects of how insects forage for food. 108.
No comments:
Post a Comment