Robot Demonstrates Self Awareness Tracy Staedter, Discovery News | December 23 2005 A new robot can recognize the difference between a mirror image of itself and another robot that looks just like it. This so-called mirror image cognition is based on artificial nerve cell groups built into the robot's computer brain that give it the ability to recognize itself and acknowledge others. The ground-breaking technology could eventually lead to robots able to express emotions. Under development by Junichi Takeno and a team of researchers at Meiji University in Japan, the robot represents a big step toward developing self-aware robots and in understanding and modeling human self-consciousness. "In humans, consciousness is basically a state in which the behavior of the self and another is understood," said Takeno. Humans learn behavior during cognition and conversely learn to think while behaving, said Takeno. To mimic this dynamic, a robot needs a common area in its neural network that is able to process information on both cognition and behavior. Takeno and his colleagues built the robot with blue, red or green LEDs connected to artificial neurons in the region that light up when different information is being processed, based on the robot's behavior. "The innovative part is the independent nodes in the hierarchical levels that can be linked and activated," said Thomas Bock of the Technical University of Munich in Germany. For example, two red diodes illuminate when the robot is performing behavior it considers its own, two green bulbs light up when the robot acknowledges behavior being performed by the other. One blue LED flashes when the robot is both recognizing behavior in another robot and imitating it. Imitation, said Takeno, is an act that requires both seeing a behavior in another and instantly transferring it to oneself and is the best evidence of consciousness. In one experiment, a robot representing the "self" was paired with an identical robot representing the "other." When the self robot moved forward, stopped or backed up, the other robot did the same. The pattern of neurons firing and the subsequent flashes of blue light indicated that the self robot understood that the other robot was imitating its behavior. In another experiment, the researchers placed the self robot in front of a mirror. In this case, the self robot and the reflection (something it could interpret as another robot) moved forward and back at the same time. Although the blue lights fired, they did so less frequently than in other experiments. In fact, 70 percent of the time, the robot understood that the mirror image was itself. Takeno's goal is to reach 100 percent in the coming year.
I can't believe no one has commented on this thread yet. This is one of the most important accomplishments made in robotics and you guys have nothing to say?
bluemouse2, you may be telling the truth. Bill Joy, the founder of Sun Microsystems wrote a groundbreaking paper a few years ago titled "why the future doesn't need us." In the paper he explained how certain technologies in the near future like nanotech, robotics, artificial intelligence, and genetic engineering may bring about the extinction of the human species. To be honest with you I don't feel sorry for humans. Throughout history we have done nothing but kill and enslave each other. Maybe its time for a new species to take over. One thing is for sure. When the technology becomes available, I want to transform my body into a cyborg or bioroid. I do not wish to remain human if a superior species will take over. All the top scientists in the world are saying machines will be sentient by the year 2050.
Then we need good Blade Runner squad here, you Teslexus M6728-051224. And, still, I will use robots.txt.. ;-D
Interesting developments, for sure. But, I don't know if I'd be comfortable calling it self awareness. I think there is also an added undefineable quality to self awareness that we may never be able to teach robots to copy. I think part of self awareness is an understanding of where we fit into the greater scheme of things and we haven't figured that one out for ourselves yet. How can we possibly teach it to robots at this point?
UsernameInUse, I don't think robots will ever become like humans. But at the same time I believe they will surpass us in just about everyway imaginable. I think robots will be the next stage of evolution. Robots can already out calculate any human on the planet. In the late 90s, a computer was able to beat Garry Kasparov in chess. Now some people come out and say that it was not the computer that beat Garry Kasparov, but the programmers of the computer. In a sense that is right, but the computer is a machine which thinks for itself. The programmers created it, but it beat Kasparov on its own. In the next 50 years, machines will become so intelligent that you will literally be able to have conversations with them. I believe more advances could have already been made in the field if different nations around the world actually worked together.
If I ever became a robot I'd like to be like Kryten from Red Dwarf. That groin attatchment would be quite the chick magnet
For gods sake, it's called evolution.. what do you think animals do to it's others? Robots will do the same.
latehorn, can you do me a favor and go pick up a history and biology book and read it? How on Earth can you compare a human to a animal. Do tigers and lions create nuclear weapons which can wipe out an entire city? Of course they don't. Humans are they only species on the planet that kill "just to kill." Most animals kill for food or self defense. Humans kill for greed and power. Big difference. As Agent Smith told Morpheus at the end of the Matrix: "You are a disease and we are the cure." Agent Smith was prophetic. Robots will be the cure. Robots won't destroy themselves because they are logical. Humans for the most part are illogical. My advice to everyone in this forum is to save your money and hope that technology becomes available so you can merge with machines. Otherwise you'll be extinct, just like the dinosaurs.
I would like to have a conversation with a robot. Right now, the only thing close to what you mention is a advanced online chatterbot at www.kurzweilai.net. The name of the bot is Ramona, and she can have very intelligent conversations. Another program you could download is HAL. How can learn things, and can have even more intelligent conversations. If they could take those AIs and put them inside a actual robot, they would really have something neat.
They probably would if they had the brain power. Humans ARE animals, so comparisons are justified. Most do, yes. But animals have been known to kill for sport and other reasons. Look.
I clicked on the link and went and read the article you suggested. The first paragraph says it all. I'll quote it here: The keywords in that paragraph were "killed and ate", not "killed for fun", or "killed just to kill". The lions were obviously hungry, and humans were easy prey for them.
that was not the point he was trying to make, the point was that animals don't kill each other for fun or other stupid reasons. Who's seen terminator recently?
I saw Terminator 3 not too long ago. It was pretty good. i also recently watched the first and second terminator movies. Most people are impressed with the T800, T1000, and the TX. I've began to be really fascinated with Skynet, the AI who created all the terminator. The storyline for the Terminator movies are a lot deeper than I originally thought. I used to think the Terminator series was just another action scifi movie, the opposite of the Matrix. But after going online, I've found some detailed information about the designs of the terminators, and its pretty in depth stuff.
Have seen those videos of the killer whales killing the seals for fun? they flip them in the air until they come apart, you gotta see it, they don't know why they do it to them
I doubt any AI at this time can give us any tangible answers to that question. Most humans can't figure that one out. I sure can't. There does seem to be a connection betwen intelligence and the capacity to do harm.