Sensory fusion helps machines sense their environment

Filed in archive Computing & Infotech on February 22, 2006

One of the most talked about long-term benefits of nanotechnology is its potential to augment human performance by integrating nanoscale computation and communication hardware into the human brain and body. Yesterday's post on RFID implants is just one example of how we're already heading down that road.

We should also consider the role of nanotechnology in making machines more human. Researchers at the University of Ulster and Trinity College, Dublin, for example, are trying to teach machines to sense their environments. Their goal is to look at human neural models of sight and touch and replicate them in silicon.

"The objective was to study sensory fusion in biological systems and then translate that knowledge into the creation of intelligent computational machines," says Martin McGinnity, coordinator of the SENSEMAKER project.

The experimental touch-sensor system, developed in Heidelberg and used by the SENSEMAKER partner Trinity College, Dublin, features an array of small, moveable spring-loaded pins. This enabled psychophysical experiments on touch and vision to be conducted on humans. The results from these experiments helped to inform the sensory fusion model.

And the same model that is helping machines sense their surroundings could one day help people sense them better as well. "This type of research teaches us a lot about how biological systems work," says Professor McGinnity, "and it could lead to new ways of treating people with sensory-related disabilities, though that kind of outcome will take a long time."