Swiss scientists have continued their work on developing intelligent robots by evolving their behavior. Their robots have continued to evolve, learning how to navigate a maze, beginning to cooperate and share, and even developing complex predator-prey interactions.

Living creatures took millions of years to evolve from amphibians to four-legged mammals - with larger, more complex brains to match. Now an evolving robot has performed a similar trick in hours, thanks to a software "brain" that automatically grows in size and complexity as its physical body develops.

It has been the dream - and nightmare - of science fiction writers for decades. Now a team of engineers has conjured up a robot that can reproduce itself. The robot can self-replicate in much the same way that some living organisms are able to reproduce by cloning themselves.

In an experiment that sounds like a science-fiction film plot but is actually as close to real life as artificial intelligence can get, several dozen "predator" and "prey" robots will be released next month into a prepared habitat at the Magna Science Adventure Centre in Rotherham, South Yorkshire, in the north of England.

Robots are being let loose in a colony of machines in an attempt to find out whether they can learn from their experiences. The scientists behind this unusual experiment describe it as an evolutionary arms race for robots, with the machines struggling to collect energy.

Electronics engineers are giving birth to a new species of space probes that will adapt to harsh environments, heal themselves and even evolve into better, smarter machines.

The same trick an oyster uses to make mother-of-pearl may ultimately enable
researchers to ``grow\'\' ultra-miniaturized computer chips. The electrical pathways would be self-assembled like the delicate whorls of seashells, rather than etched by conventional manufacturing techniques, and would be only a fraction of the size of the smallest circuit components possible today.

At first glance, Darwin\'s ideas on evolution don\'t seem to have much to do
with computers. But if a line of computer code doesn\'t remind you at least
vaguely of a chromosome -- both are essentially stored information -- you
might want to look into the new field of evolvable hardware, where chips
redesign themselves for optimum efficiency. This is evolution with a silicon
flair.

The latest 'Handbook of Industrial Robotics' reports that the population of robots has doubled over the last decade.