Smarter, Harder, Space Robots

Perhaps next time NASA (or any other space agency) decides to launch a rover to another world, they may want to contact Hod Lipson, (assistant professor of mechanical and aerospace engineering for the Cornell Computational Synthesis Lab) for programming tips.

(Space Daily) Nothing can possibly go wrong … go wrong … go wrong …The truth behind the old joke is that most robots are programmed with a fairly rigid “model” of what they and the world around them are like. If a robot is damaged or its environment changes unexpectedly, it can’t adapt. [...]

“Most robots have a fixed model laboriously designed by human engineers,” Lipson explained. “We showed, for the first time, how the model can emerge within the robot. It makes robots adaptive at a new level, because they can be given a task without requiring a model. It opens the door to a new level of machine cognition and sheds light on the age-old question of machine consciousness, which is all about internal models.”

What was interesting was how that after the robots learned how to walk, researchers were able to take away a leg which forced the robot to relearn the process all over again. Robots like these will prove to be quite useful not only on Mars and outer space, but also on other hostile worlds such as Saturn’s Titan.

Note: If they become too smart, I may have to order a special bracelet supporting “the robot movement.”

Content Copyright 2006-2009 of Colony Worlds. All Rights Reserved.

Violators (and hosts) can be prosecuted under national and international laws.

Share on Tumblr