Sunday, January 22, 2012

Time for robots to get real

Drop the gimmicks, focus on practical problem-solving, and robotics can change the world

FROM robotic slug-killers to dancing humanoids, there's a lot of media buzz around robots. But the roboticists behind such ventures need a serious reality check.

As a founder of iRobot Corporation, based in Bedford, Massachusetts, and CEO of robotics start-up CyPhy Works, it's clear to me that merely engineering "cool" robots does little to advance the field. If robotics is to succeed like computing, what matters is making practical robots that do jobs well and affordably - factors that tend to get lost as people fascinate over the latest autonomous party pieces.

The importance of focusing on practicality struck us during iRobot's formative years in the 1990s, when we were engineering robots as toys, oil-well surveyors and commercial cleaners for industry-leading firms. Why? Companies would only pay good money for practical designs that performed reliably.

Roboticists who don't focus on practicality, ruggedness and cost are kidding themselves. Simply put, people don't want outlandish machines in their homes. Before iRobot introduced the Roomba vacuuming robot in 2002, focus groups imagined it would look like the Terminator pushing a vacuum cleaner - and told us they would not accept such machines in their homes. But when we showed them that Roomba was small, light and friendly, they loved it.

Another benefit of practicality was seen last year, when iRobot's military robots, originally deployed in Afghanistan to defuse improvised explosive devices, proved very useful to the human teams dealing with the nuclear emergency at the Fukushima Daiichi power plant in Japan. As a result, many in Japan have questioned the nation's research focus on singing, running and dancing humanoid robots. It looks like change is afoot there.

This is to be welcomed because at this point, attempting to duplicate human intelligence or the human form robotically is a wrong-headed approach. We already have about 7 billion humans on the planet and we are really good at what we do. To sell humanoid robots they would have to be better than people - and that is just not realistic yet.

Software standardisation, around the Robot Operating System and Linux, for instance, will help developers focus on the practical. This is a tremendous move because engineers, particularly in research universities, won't have to start coding from the ground up to build their own robots. Instead, their challenge will be to build software packages small enough to run on affordable processors, and robots that avoid the common embarrassment of being wimpy and underpowered with limited usage time.

By focusing on bringing robots to market, innovators will be able to put the industry firmly on the commercially viable, world-changing track it deserves.

If you would like to reuse any content from New Scientist, either in print or online, please contact the syndication department first for permission. New Scientist does not own rights to photos, but there are a variety of licensing options available for use of articles and graphics we own the copyright to.

Have your say

Only subscribers may leave comments on this article. Please log in.

Only personal subscribers may leave comments on this article

Subscribe now to comment.

All comments should respect the New Scientist House Rules. If you think a particular comment breaks these rules then please use the "Report" link in that comment to report it to us.

If you are having a technical problem posting a comment, please contact technical support.

Source: http://feeds.newscientist.com/c/749/f/10897/s/1c04f48d/l/0L0Snewscientist0N0Carticle0Cmg213284850B80A0A0Etime0Efor0Erobots0Eto0Eget0Ereal0Bhtml0DDCMP0FOTC0Erss0Gnsref0Fonline0Enews/story01.htm

sand dollar sand dollar just dance 3 just dance 3 cliff lee cliff lee the raven

No comments:

Post a Comment

Note: Only a member of this blog may post a comment.