|
[DPRG] Are representations what makes Can Can hard? and Odometry
Subject: [DPRG] Are representations what makes Can Can hard? and Odometry
From: John Swindle
swindle at compuserve.com
Date: Fri Dec 8 02:14:51 CST 2006
I've been hanging around DPRG stuff for several years, hearing
about odometry, knowing that I don't do it myself when I walk
around in a dark room, and wondering why it was necessary for
robots. That is, I wondered why is it not sufficient to do
navigation based on sensor input that is constantly updated. It
wasn't until DPA was talking to Will about calibrating odometry
that I read a good-enough reason for doing odometry: Researchers
concluded that it is far easier to get good behavior using
odometry than it is by trying to use representation and sensors.
Without eyes, ears, and sacrificial skin on our toes, people
would use odometry, too. When people and dogs explore, they
return to the home that looks right, not to the home that was so
many paces away. When your dog gets lost, look on the front porch
of the neighborhood house that looks like yours. (Or wherever the
best food is.)
John Swindle
More information about the DPRG mailing list
|
