October 22, 2010

Anderson & Anderson: Robot Be Good

Michael and Susan Anderson have published an article on Machine Ethics (ME) in the October issue of Scientific American. In the article, Robot Be Good: A Call for Ethical Autonomous Machines, they introduce both ME and their recent work programming ethical principles in Nao, a humanoid robot which was developed by the French company Aldebaran Robotics.

Their findings in brief:
  • Robots that make autonomous decisions, such as those being designed to assist the elderly, may face ethical dilemmas even in seemingly everyday situations.
  • One way to ensure ethical behavior in robots that interact with humans is to program general ethical principles into them and let them use those principles to make decisions on a case-by-case basis.
  • Artificial-intelligence techniques can produce the principles themselves by abstracting them from specific cases of ethically acceptable behavior using logic.
  • The authors have followed this approach and for the first time programmed a robot to act based on an ethical principle.

1 comment:

ZarPaulus said...

Simply programming a set of rules into robots may work for a while, but only if they're less intelligent than a human and are incapable of networking with one another (don't want a Geth rebellion). But with AI's that have human-level complexity or above you would probably have to give them compassion, which might be difficult as you could program it to recognize emotional responses and a list of proper responses and create a sociopath.