Self Aware Robot ?

Step towards conscious bots http://australianit.news.com.au/articles/0,7204,20792279^15321^^nbv^15306,00.html NOVEMBER 21, 2006

SCIENTISTS claim to have created an intelligent, four-legged robot that can sense damage to its body and, unaided, think of a way to recover. Cornell University researchers Hod Lipson and Victor Zykov, with Josh Bongard of the University of Vermont, made a robot that could observe its own motion through sensors built into its joints, and generated its own concept of itself, or at least its physical structure, in its internal computer. It used this internal model to figure out how to walk on its four legs and eight motorised joints. "In the beginning, the robot starts off and doesn't know what it looks like," Mr Lipson said last week. "You look at it, and you see that it's a four-legged machine, but the robot itself doesn't know that. All it knows is that it could be a snake, it could be a tree, it could have six legs." It used various movements of its joints, firstly to generate hypotheses and then to develop an accurate conception of itself, he said. They then tested its ability to adapt to injury by shortening one of its legs. "The robot knows something's wrong," Mr Lipson said. Animals compensate for injury by limping to favour an injured leg. Machines can be programmed to react to a problem in a certain way, but when damaged in unexpected ways they usually are doomed. This robot responded by generating a new concept of its structure, accurately sensing that it had been altered and coming up with a way to walk with a different gait to compensate for the injury. This robot's awareness of itself and ability to adapt on its own separates it from its mechanical brethren. "We don't think this is self-consciousness, which is a robot thinking about itself thinking, but I do think it is moving in the direction of consciousness," Mr Lipson said. Apart from contributing to a philosophical debate, the research has practical implications. "There is a need for planetary robotic rovers to be able to fix things on their own," Mr Bongard said. "Robots on other planets must be able to continue their missions without human intervention in the event that they are damaged and cannot communicate their problems back to Earth." Christoph Adami, of California's Keck Graduate Institute of Applied Life Sciences at Claremont, wrote a commentary Titled What do Robots Dream of? accompanying the research. Mr Adami described how a robot such as this might perform in unknown territory, exploring the landscape and then dreaming of new ways to overcome obstacles it had encountered. "Even though the robots seem to prefer to dream about themselves rather than electric sheep, they just may have unwittingly helped us understand what dreams are for," he said. Reminded of malicious robots and computers turning on their human masters in movies such as The Terminator and 2001: A Space Odyssey, Mr Lipson was not worried. "We just pull the plug out of the robot, that's all," he said. "There are more immediate things to worry about than to worry about that." Reuters The Australian