Subscribe / Unsubscribe Enewsletters | Login | Register

Pencil Banner

A good robot is hard to find -- or build

Sharon Gaudin | June 16, 2014
In the first two days of the NASA robotics challenge this week, every team failed.

Another team from West Virginia actually found an object and was able to pick it up. However, the robot didn't recognize that it had captured the objected and dropped it. It tried again and again, dropping it each time. By the time the robot stopped trying, the object had been driven into the ground.

"It's a problem of sensor fusion," said Craig Putnam, an adjunct computer science professor and robotics instructor at WPI. "You have lots of different kinds of things you're sensing and you have to fuse that all together to get the big picture. There's vision, odometry, the tilt of the ground, colors and shapes.... It's just a really hard problem."

Because there are so many systems — like energy management, stability and sensor integration — in an autonomous robot, the teams behind them are generally made up of mechanical and electrical engineers, software programmers and vision systems experts.

It's the technical version of "it takes a village."

With apologies to the future world of the Jetsons, it's difficult to build a robot maid that will cheerily and efficiently clean the house without accidentally vacuuming up the cat. And that hasn't been lost on the robotics community.

At a recent MIT symposium, Rodney Brooks, co-founder of iRobot, a former MIT robotics professor and co-founder and CTO of Rethink Robotics, posed a rather divisive question: Why hasn't robotics changed the world yet?

Some of Brooks' fellow roboticists disagreed with him, saying that robotics have changed the world. The issue is that people expect a Terminator or RoboCop version of a robot — and they expect it sooner rather than later.

Alongside those lofty expectations comes Brook's own take on the situation: "Robotics is just really, really hard."

Team Survey's Little agrees with Brooks. But that doesn't mean he's discouraged.

As Little sagged a bit on a bench on the WPI campus after his robot's demonstration Thursday and mentioned how exhausted he was, he called the robot's unsuccessful run a good learning experience, noting it was the first time the machine had ever worked on a large course for two hours.

"This is a software problem and a sensor problem and a little bit of a hardware problem," he said. "And everything had to work.... It's hard, but it's not just hard. It's expensive."

Even so, Little said the group will be back next year to try again.

Ken Stafford, director of WPI's Robotics Resource Center and an associate professor of robotics, also remains hopeful.

Stafford excitedly explained that he saw one team competing this week that had equipped its robot with Saran plastic wrap, much like many people have in their kitchen drawers.


Previous Page  1  2  3  Next Page 

Sign up for CIO Asia eNewsletters.