Sign In

Communications of the ACM

ACM TechNews

Eu Project Aims to Build Computers That Can Learn From ­S

man and robot


The European Union-funded COGNITO project is building a computer system that can observe people, learn how they do things, and help them carry out tasks. University of Bristol professor Andrew Calway's research team is developing advanced computer vision algorithms, which will be incorporated into on-body cameras that will be used to monitor human activities. Investigating the learning of human sensory-motor activities could help lead to the development of truly useful computers, says the Bristol team.

The data captured from the on-body sensor networks will assist the COGNITO project in both the learning of actions and using that knowledge in assistive systems based on augmented reality technology. Learning skilled assembly and manipulation tasks, often found in high-precision industries, will be a focus of the project.

"In Europe, where many industries from family-run to large corporations rely on highly skilled people, systems that assist in rapid training and quality control are essential," says Bristol's Walterio Mayol-Cuevas.

From University of Bristol
View Full Article


Abstracts Copyright © 2010 Information Inc., Bethesda, Maryland, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account