New Robot Models (E)
Continuous progress in the field of robotics has made many tasks easier and safer for humans, but even the most advanced robots fail to perform the important basic social interactions associated with everyday human life. Now researchers at the Massachusetts Institute of Technology (MIT) have incorporated some of the social interactions, into a framework of robotics, enabling machines to understand what it means to help or hinder one another, and to learn to perform these social behaviours on their own. In a simulated environment, a robot watches its companion, guesses what task it wants to accomplish, and then helps or hinders this other robot based on its own goals. These new robot models can prove to be more efficient and effective in many areas including medicine, elderly care, analysis of psychosis etc. The research, supported by several institutions including the Centre for Brains, Minds and Machines, the National Science Foundation, will be showcased at the Conference on Robotic Learning in November, in London.
