robots lie Options

[Divergent Realit...]

http://discovermagazine.com/2008/jan/robot...earn-how-to-lie

Robots 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 fittest—those 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 nature—foraging with uncertainty,” Floreano says. “You have to find food, but you don’t 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 communicate—lighting up, in three out of four colonies, to alert the others when they’d 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 nature—an animal that emits a cry when it sees a predator; it gets eaten, and the others get away—but I never expected to see this in robots.”

[Spectatrix]

Awesome!

[impala454]

Interesting project (as far as robots communicating and such), but the results would seem pretty obvious. It's all still simple code, not some "evolved" machine. Notice they don't tell you what these "gene" pieces of code do.

1 "find the best way to get power".
2 "if other robots suck power there will be less for me".
3 "if I signal other robots away, there will be more power left for me",
4 go to #1

With the #1s no doubt being the different "gene"s they were talking about, with something like "Find the best way to get the most power to the most robots".

The rule of computers and machines is and always will be: They do exactly what you program them to do. If there's an "anomoly" or "mutation", it's because of an unforseen bug in the code (whether intentional or unintentional). Unlike the movies, bugs in code do not result in some superintelligent machine bent on destroying the human race. It's this way whether its a PIC with 50 lines of code or a supercomputer with 100 million lines of code.

[chook]

what i'd expect, but it shows weighted tendency for survival and not choices.