Can Computers Be Aware Of Their Surroundings?

Electronics and computing engineers from the University of Ulster have teamed up with neuroscientists, physicists and biologists from across Europe to investigate the incorporation of the senses we humans take for granted into intelligent computer systems of the future.

The multi-disciplinary team concentrated on attempting to replicate in silicon the biological brain’s ability to capture data from the senses of touch and sight. In biological life forms, the brain can combine information from different senses to create a comprehensive representation of its surroundings.

For example, sight can identify a kiwi fruit but touch is required to tell if the fruit is ripe, unripe or over-ripe.

Professor Martin McGinnity, Professor of Intelligent Systems Engineering and Director of the Intelligent Systems Engineering Laboratory (ISEL) at the University’s Magee campus, said: “The objective was to study sensory fusion in biological systems and then translate that knowledge into the creation of intelligent computational machines”.

Professor McGinnity was the co-ordinator of the EU’s Future and Emerging Technologies-funded SENSEMAKER project which has now been completed. Other partners in the project included academics from Trinity College, Dublin, two CNRS laboratories in France and the University of Heidelberg in Germany.

He added: “The ultimate aim is to create machines which can capture information through sensory perception, process it in a way similar to the brain and then act intelligently on that information. The research will have practical application in a wide range of areas including robotics and industrial automation.

“The results of the research project are very promising – this is a very complex problem area but we have made some progress. We were able to create a theoretical model on how aspects of the process work and also to produce a demonstration system in hardware and software that merged vision and touch – albeit at a very basic level compared to that of living forms. We would hope that in the future we could create models that are more faithful to biology. Once we can get the models right we may be able to implement better, more realistic systems.”

He said intelligent systems need to adapt and react autonomously to their environment without reprogramming; they need to be able to react to changing circumstances in a manner that humans would describe as intelligent; for that they need a perception system that enables them to be aware of their surroundings.

But a greater understanding of biological sensory fusion, and how to implement it in artificial systems, could do potentially much more.

“This type of research teaches us a lot about how we can translate the principles of living biological systems into artificial computer systems; while the primary focus is to create intelligent computational systems, this field of research may also lead to new ways of treating people with sensory-related disabilities with more advanced prosthetics” said Professor McGinnity.

Two other projects will carry aspects of the scientists’ work further. The FACETS project, also funded by the EU thorough its Future Emerging Technologies programme, will continue to explore machine perception, focusing on vision. Meanwhile ISEL at the Magee Campus is actively engaged in a major proposal to create a Centre of Excellence in Intelligent Systems. The Centre will progress a range of research problems related to the creation of intelligent systems, including sensory fusion, learning, adaptation, self-organisation, the implementation of large-scale biological neural sub-systems in hardware and distributed computational intelligence.