'Curious' Robots -the Next Big Thing in Interplanetary Exploration

‘Curious’ robots with an innate sense of self are believed to be the next big thing in interplanetary exploration. The new ‘speedy’ design makes today’s robotic explorers seem like slugs slowing and inefficiently making their way across alien terrain.

Robotic explorers such as NASA's Spirit and Opportunity are real slowpokes. Hazard avoidance software allow them a mere 10 seconds of movement before they are required to hold still for 20 seconds while scanning the area ahead for pitfalls.

Now Josh Bongard of the University of Vermont, US, has designed a simulated rover that shows a new way to work much faster. This rover can virtually "imagine" itself and its immediate surroundings, causing it to head off to poke around in any areas that feeds its ‘curiosity’. This approach allows the bot to navigate uncharted territory relatively quickly without endangering itself.

Bongard created a rover that does not use sophisticated camera vision, but instead relies on just two tilt sensors to gain information about its world. His virtual rover first makes a single slow drive through an unknown area gathering as much tilt data as possible. Based on this information, it then builds 15 different simulations of its extended surroundings with itself at its current position. It makes "educated guesses" based on sensor data about the likely features in these the areas beyond its initial route.

The robot combines all 15 models and identifies the direction in which the models vary the most. It then drives off into this region and checks its models against new tilt data, providing more information for further, more accurate simulation building.

This combination of physical model building and "curiosity" allows the robot to explore at an ever faster rate. Although the simulated rover is basically blind, meaning it is prone to bumping into the odd rock or boulder, the same approach could be extended to robots with vision too.

"This behavior is similar to how babies explore and test their world, why they are always getting into trouble," says Hod Lipson, a roboticist at Cornell University in Ithaca, New York, US, who was not involved with the project.

Robots with greater "self-awareness" also represents an important step towards human-like intelligence, Bongard say, although he is quick to add that the simulated rover is not conscious. "For consciousness, you need to be able to think about thinking about yourself."

For now, that’s something no robot has been able to do—or at least not that anyone knows of!

The research was announced at the 9th European Conference on Artificial Life earlier this month.

Posted by Rebecca Sato

DepthX -Thinking Robot to Explore Jupiter's Moon Europa
10 Weird & Amazing Robot Facts

Links:

http://technology.newscientist.com/article/dn12674-selfaware-space-rovers-would-be-speedy-explorers.html
http://www.ecal2007.org/