|
Team
Work
Manuela
Veloso takes the latter approach in her research, working
to build robots that can do the same things as humans and
animals, but not necessarily via the same processes. Which
is not to say Veloso's work is not inspired by human intelligence.
 |
 |
|
Veloso
and Alan Alda at the RoboCup Competition.
|
|
"One
of the things that drove me to A.I. was the way humans adapt
to situations, learn, train and perform better with experience,"
says Veloso. "Then I focused on trying to build A.I. systems
that would be capable of having the three main components
of humans."
Veloso's
trinity is comprised of: perception, the ability to know your
surroundings and your position in them; cognition, the ability
to make decisions based on the information perceived; and
action, the ability to execute those decisions through motion.
Deep in the midst of the Cold War, the U.S. government
poured funding into A.I. projects.
|
To
Veloso, the soccer-playing robots are the ultimate experiment.
They can be hardwired to understand certain parameters, such
as the dimensions of the field, but they also need to process
information about their teammates and opponents in real time.
That task requires nearly instantaneous perception, cognition
and action. "If
we can handle robotic soccer," says Veloso, "imagine how much
intelligence we are building into these little robots." Which
raises the question, what use is a smart, little, soccer-playing
robot?
 |
|
|
Robots
must be able to perceive, "think" and act - all almost
instantaneously to win a soccer match.
|
|
"I
have a hard time even inventing what humans need teams for
other than sports," says Veloso, though she is actually full
of examples. Teams of robots, she says, could wage war, execute
dangerous search and rescue operations, pick produce in the
most efficient way, explore other planets, or even play games
against teams of humans just for fun. 
-
- - - - - - - - - - -
4
pages: | 1 | 2 | 3
| 4 |
|
