According to a new set of experiments, it would appear that robots have the ability to deceive other robots. The robots are equipped with artificial neural networks and programmed to find “food”. They eventually learned to conceal their visual signals from other robots to keep the food for themselves. 

The researchers outfitted robots with light sensors, rings of blue light, and wheels and placed them in habitats furnished with glowing “food sources” and patches of “poison” that recharged or drained their batteries.  The original bots simply roamed the surfaces, emitting light randomly. After each of the trials, in which they had to find as much food as possible, the researchers would copy the digital brain of the most successful machine, and insert it into the next generation of robots, alongside a few changes, so as to favor “evolution.”

Read how after a few generations some robots learned how to recognize flashing lights emitted by others as a clear indicator that food was nearby and how others learned to mute their signals so as not to draw the attention of other machines (PNAS)

This entry was posted on Wednesday, August 19th, 2009 at 8:27 am and is filed under Semantic. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.