December 5, 2012
Researchers Create Deceptive Robots Using Squirrel Behavior
|Using the biological model of squirrels hiding thier nuts, an pretending to look in the wrong spot when another animal is nearby, Georgia Tech's Mobile Robot Lab, researchers have spent over a decade studying potential military uses for robotics.|
The research is available in the November/December 2012 edition of IEEE Intelligent Systems.
Arkin and his team of researchers studied biology, specifically research on squirrels that gather acorns and store them in specific locations. Subsequently the animals patrol their storage locations, routinely going back and forth to check on them. When another squirrel shows up, hoping to raid the hiding spots, the hoarding squirrel will change its behavior. Instead of checking on the true locations, it visits empty cache sites, trying to trick the other squirrel.
Arkin and his Ph.D. student Jaeeun Shim implemented the same strategy into a robotic model and demonstration. The deceptive behaviors worked. The deceiving robot lured the “predator” robots to the false locations, delaying the discovery of the protected resources.
“This application could be used by robots guarding ammunition or supplies on the battlefield,” said Arkin, a Regents Professor in Georgia Tech’s School of Interactive Computing. “If an enemy were present, the robot could change its patrolling strategies to deceive humans or another intelligent machine, buying time until reinforcements are able to arrive.”
Arkin and his student Justin Davis have also created a simulation and demo based on birds that might bluff their way to safety. In Israel, Arabian babblers in danger of being attacked will sometimes join other birds and harass their predator. This mobbing process causes such a commotion that the predator will eventually give up the attack and leave.
Arkin's team investigated whether a simulated babbler is more likely to survive if it fakes or feigns strength when it doesn't exist. The team’s simulations, based on biological models of dishonesty and the handicap principle, show that deception is the best strategy when the addition of deceitful agents pushes the size of the group to the minimum level required to frustrate the predator enough for it to flee. He says the reward for deceit in a few of the agents sometimes outweighs the risk of being caught.
“When these research ideas and results leak outside the military domain, significant ethical concerns can arise,” said Arkin. “We strongly encourage further discussion regarding the pursuit and application of research on deception for robots and intelligent machines.”
This isn’t the first time Arkin has worked in this field. In 2010, he and Georgia Tech Research Institute Research Engineer Alan Wagner studied how robots could use deceptive behavior to hide from humans or other intelligent machines.
SOURCE Georgia Tech
|By 33rd Square||Subscribe to 33rd Square|
Topics - AI , artificial intelligence , deception , Georgia Tech , military robot , robotics , robots , Ronald Arkin