UMass
Robotics Team Explores Autonomous Segway
Federal
grant funds research into new applications for a balancing robot
AMHERST,
Mass. - Researchers at the University
of Massachusetts Amherst Computer Science Department are implementing
new sensors and computer control software to create an autonomous
Segway Human Transporter. The research is funded by a grant
to Professor Rod Grupen, computer science, from the Defense
Advanced Research Projects Agency (DARPA) through its Mobile
Autonomous Robot Software program. The Segway Human Transporter
(HT) balances itself using gyroscopes much the same way that
an inverted broomstick can be balanced on the palm of one's
hand. The Segway Robotic Mobility Platform (RMP) has been modified
by Segway for use as an autonomous robot platform.
The
UMass team is one of a dozen across the country working with
the modified Segways under the DARPA program to see what these
dynamically stable platforms can do. The goal is to develop
a sophisticated mobile platform that might be used in situations
where a human would be in danger, or where performance and mobility
are needed. At UMass, the team of researchers mounted a digital
camera and a distance-sensing laser system to the Segway for
use in guiding it around objects and towards goal locations
in an unkown environment.
The
Laboratory for Perceptual Robotics at UMass is using their RMP
to investigate its potential for high performance tracking tasks
- a kind of robotic "mule" that can follow human leaders
or just navigate its own way to rendevous points.
Oliver
Brock, assistant professor of computer science and a member
of the research team, says, "DARPA is considering applications
that equip these machines with mobile life support systems and
litters for transporting injured people from disaster areas
or battlefields. Our Segway is capable of a number of skills
necessary in order to transport injured people autonomously:
avoiding obstacles, detecting impassable terrain, finding new
routes, and following leaders." Such a device that might
take medics out of harm's way, towing army litters and perhaps
even Life Support for Trauma and Transport (LSTAT) medical systems
one day.
Andrew
H. Fagg, senior research scientist in computer science and another
member of the team, says the goal is to develop a versatile
autonomous platform for use in a variety of applications. "We
are working to extend these techniques to allow the robots to
automatically perform search-and-rescue tasks with limited human
interaction. This will allow many robots to be used to find
survivors in damaged buildings, giving human rescuers a good
sense of where help is needed and where the hazards are even
before they enter."
What's
next? The UMass team is considering putting robotic arms and
hands on the RMP platform to create high performance robots
that are the same physical scale as humans. "When robots
can occupy the same space as humans without being obtrusive,
can use our tools, stairways, and open doors, then we will see
a whole new array of applications. Robots will be capable of
collaborating with us, and learning over their entire life span.
Not only that, but what they have learned can be transplanted
into their successors," says Grupen. Robots like this may
one day be assistants around the home or the hospital, exploring
distant planets, or simply keeping people out of harm's way.
-30-
Project
Web site
Contact
Rod Grupen at 413/545-3280 or grupen@cs.umass.edu
Oliver Brock at 413/577-0334 or
Andrew H. Fagg at 413-545-2993 or fagg@cs.umass.edu
Email
this UMass News Release to a friend