Slashdot Mirror
Learning Robots
carnun writes "The NewScientist is reporting on a new snakelike robot that uses genetic algorithms to change its motion pattern so that it can still function after sustaining damage." Roland Piquepaille sends in a report about another "learning" robot, named Adam, which is designed to seek out and feed from "flowers".
I can understand if the robot was cut in half. If one end of the worm was removed from the other, at least one part would be able to carry on. Maybe both parts would be able to carry on, given that both had the ability to remember the code routines, and working processors to execute them. So in that case you have two worms that are now less than the whole, but would they know to what extent they had been damaged? In a war time environment, you would want the equipment to know the sevarity of the damage, as to allow it to adapt it's mission.
But more than that, lets asume that a rock falls on one end of the worm. does the worm then have the ability to 'disconnect' from the other end? I'll re read the story, but I don't see the benefit of this particular device. I can't see the benefit of this technology in any other application. I understand study for study's sake, and this might be a really early stage of something way more cool than it sounds, but I fail to see the point of a self correcting robot worm.
Oh well.