discovermagazine.com/2008...how-to-lie
Quote:
01.14.2008
80. Robots Evolve And Learn How to Lie
by Michael AbramsRobots can evolve to communicate with each other, to help, and even to deceive each other, according to Dario Floreano of the Laboratory of Intelligent Systems at the Swiss Federal Institute of Technology.
Floreano and his colleagues outfitted robots with light sensors, rings of blue light, and wheels and placed them in habitats furnished with glowing food sources and patches of poison that recharged or drained their batteries. Their neural circuitry was programmed with just 30 genes, elements of software code that determined how much they sensed light and how they responded when they did. The robots were initially programmed both to light up randomly and to move randomly when they sensed light.
To create the next generation of robots, Floreano recombined the genes of those that proved fittestthose that had managed to get the biggest charge out of the food source.
The resulting code (with a little mutation added in the form of a random change) was downloaded into the robots to make what were, in essence, offspring. Then they were released into their artificial habitat. We set up a situation common in natureforaging with uncertainty, Floreano says. You have to find food, but you dont know what food is; if you eat poison, you die. Four different types of colonies of robots were allowed to eat, reproduce, and expire.
By the 50th generation, the robots had learned to communicatelighting up, in three out of four colonies, to alert the others when theyd found food or poison. The fourth colony sometimes evolved cheater robots instead, which would light up to tell the others that the poison was food, while they themselves rolled over to the food source and chowed down without emitting so much as a blink.
Some robots, though, were veritable heroes. They signaled danger and died to save other robots. Sometimes, Floreano says, you see that in naturean animal that emits a cry when it sees a predator; it gets eaten, and the others get awaybut I never expected to see this in robots.
Fascinating, no? Although I have to admit I'm not sure it's a good idea to encourage robots to develop the ability to lie or deceive, at the same time it is heartening to see that robots can have as much variety as humans.
A robot who managed to lie and decieve AND die as a hero all rolled into one awesome package.
R.I.P, Dinobot.
R.I.P.
...what?! A Dinobot II, you say?!
R.I.P, Dinobot II.
R.I.P.
The robot apocalypse is right around the corner
Well, it may take a little longer for them to get to that point. After all, they are kinda limited to flashing their lights and moving around, not exactly a real threat yet.
If we just keep robots small and cute, they may never present a real threat.
The small and cute are the deadliest ^O-
If we just keep robots small and cute, they may never present a real threat.
Says the guy who would totally embrace the creation of Tachikoma robots
If we just keep robots small and cute, they may never present a real threat.
>> Tell that to the Monty Python rabbit -.-....
Yes I know its not a robot, but small and cute -.-....pure evil.
But Tachikomas are good guys! They would never become evil!
Mischievous, maybe. Curious, maybe. Able to stop a nuclear warhead with their own networked satellite, heck yeah. But not evil.
Stop a nuclear warhead with satellites? AH SPOILS ='(
So that's what they are up to at the ETH (the Swiss Federal Institute of Technology). And there I thought they would spend our tax money on something reasonable.
Some sort of real world variation of Asimov's Three Laws of Robotics may be on the horizon if the science has reached this level.
At least that'd take the sting out of his most famous legacy being fictional laws from a fictional civilisation, rather than his serious scientific work - the poor bloke went to his grave regretting that.