Communications of the ACM
Pushing the Boundaries of Artificial Intelligence
Neuromorphics Lab director Max Versace (from left), Ben Chandler, Byron Galbraith, and Sean Lorenz with their prize robot (an IRobot Create model), whose robotic arm can be controlled by an EEG cap.
Credit: Cydney Scott
Boston University Neuromorphics Laboratory researchers are developing an artificial intelligence-based robotics technology that can sense, learn, and adapt.
The research is part of the lab's Modular Neural Exploring Traveling Agent (MoNETA) project, which is developing technology that would become the brains behind virtual and robotic agents that can learn on their own and interact with new environments.
"We want to eliminate, as much as possible, human intervention in deciding what the robot does," says lab director Massimiliano Versace.
MoNETA project researchers are developing algorithms that produce lifelike behavior without telling the program what to do. The researchers also are developing an operating system for the artificial brain, known as the Cog Ex Machina. The software for the Cog Ex Machina will run on a memristor, which the researchers say will enable hardware designers to build chips with unprecedented density that operate on very low power.
Meanwhile, Boston doctoral student Sean Lorenz is developing a method to interface the robot with an electroencephalogram cap. The target application is robotic devices that enable people with disabilities to interact with the world through a brain-machine interface.
From BU Today
View Full Article
Abstracts Copyright © 2012 Information Inc. 
, Bethesda, Maryland, USA
No entries found