Taking inspiration from Darwin's theory of evolution, scientists from the
Sussex University, UK, have developed a technique for evolving designs
for neural network controlled robots
with greater self-sufficiency.
The approach is similar to the concept of natural selection - here computer programmes which allow a
degree of 'free choice' in the manoeuvres defined, and those that perform
best are selected to breed the next
generation robots. The researchers of
the university's Evolutionary Research
Group are employing Mr Chips - a
mobile robot with a head that holds a
laptop computer, and a body consisting of an array of processors, printed
circuit boards and antennae.
Special attention is being focussed
on the study of insects to understand the biological mechanisms
underlying intelligent activity on
which robotic movement could be
based. Says Dave Cliff, lecturer in the
Computer Science and Artificial
Intelligence department at the university, "The fact that generally few
nerve cells are involved in generating
behaviour in insects makes it more
practicable to model insect nervous
systems on currently available computers."
We are a voice to you; you have been a support to us. Together we build journalism that is independent, credible and fearless. You can further help us by making a donation. This will mean a lot for our ability to bring you news, perspectives and analysis from the ground so that we can make change together.
Comments are moderated and will be published only after the site moderator’s approval. Please use a genuine email ID and provide your name. Selected comments may also be used in the ‘Letters’ section of the Down To Earth print edition.