September 10, 2010

Sneaky Robots

(Ivanhoe Newswire) -- Robots do whatever humans tell them to do, right?  Or is all a big lie?

Experts at the Georgia Institute of Technology say they've given robots the ability to be deceptive. 

"We have developed algorithms that allow a robot to determine whether it should deceive a human or other intelligent machine and we have designed techniques that help the robot select the best deceptive strategy to reduce its chance of being discovered," Ronald Arkin, a professor in the Georgia Tech School of Interactive Computing was quoted as saying.

In the future, robots capable of deception may be valuable for several different areas, including military research and search and rescue operations.  A search and rescue robot may need to deceive in order to calm or receive cooperation from a panicking victim.  Robots on the battlefield with the power of deception will be able to hid and mislead the enemy.

"Most social robots will probably rarely use deception, but it's still an important tool in the robot's interactive arsenal because robots that recognize the need for deception have advantages in terms of outcome compared to robots that do not recognize the need for deception," study co-author, Alan Wagner was quoted as saying.

For the study, researchers focused on the actions, beliefs and communications of a robot attempting to hide from another robot.  They taught the robot how to recognize a situation that warranted the use of deception.  Then the robot carried out a deceptive act by providing false communication to benefit itself.

However, there are ethical implications that need to be considered, according to the researchers.

"We understand that there are beneficial and deleterious aspects.  We strongly encourage discussion about the appropriateness of deceptive robots to determine what, if any, regulations or guidelines should constrain the development of these systems," said Arkin. 

SOURCE:  International Journal of Social Robots, September 2010.