A good robot is hard to find -- or build

As competitive research teams stumble at NASA challenge, a look at the struggle behind robotics

1 2 Page 2
Page 2 of 2

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.

NASA, which needs its rovers on Mars to keep any soil or rock samples separate from each other so they don't become contaminated, required the challenge teams at WPI to do the same.

That's where the Saran wrap came into play. If the machine has been able to collect anything on the challenge course, it would have been ready.

That, said Stafford, was a great idea from a group of people thinking creatively about a problem.

"Creating is taking things that exist and using them differently," said Stafford. "It's not about winning this challenge. It's about getting what NASA needs done."

Many of the teams that failed their early challenges are expected to try again on Saturday if the weather holds.

Sharon Gaudin covers the Internet and Web 2.0, emerging technologies, and desktop and laptop chips for Computerworld. Follow Sharon on Twitter at  @sgaudin, on Google+ or subscribe to Sharon's RSS feed . Her email address is sgaudin@computerworld.com.

See more by Sharon Gaudin on Computerworld.com.

Copyright © 2014 IDG Communications, Inc.

1 2 Page 2
Page 2 of 2
Bing’s AI chatbot came to work for me. I had to fire it.
Shop Tech Products at Amazon