Dec 14, 2012
Those pesky science types at Georgia Tech just doomed us all by deciding it would be a great idea to teach robots how to deceive other robots. Naturally their work was sponsored by the military, because, you know, that kind of thing always turns out well for everyone.
Their first step was to teach the deceiving robot how to recognize a situation that warranted the use of deception. A situation had to satisfy two key conditions to warrant deception -- there must be conflict between the deceiving robot and the seeker, and the deceiver must benefit from the deception. Once a situation was deemed to warrant deception, the robot carried out a deceptive act by providing a false communication to benefit itself. The technique developed by the Georgia Tech researchers based a robot's deceptive action selection on its understanding of the individual robot it was attempting to deceive.It gets worse. The robots were effective at lying 100 percent of the time, according to BotJunkie:
To test out the deception programming, the researchers had their robots play hide and seek. The hiding robot had a choice of three hiding spots, each with a set of markers in front of it. Recognizing that the situation could benefit from a deceptive tactic, the hiding robot would knock down markers in front of one hiding spot, and then go find a different spot, avoiding the markers. This technique fooled the seeking robot 100% of the time, as long as the hiding robot was able to knock down the correct markers.You can read more about the whole thing on social robotics researcher Alan Wagner's site, if the robots haven't gotten to it first and altered all the records.