Original Source Here
6. AI can repair itself when needed.
Cornell University came out with a study in 2006 that discussed their newest robotic creation: The Starfish. Without any programming or a rigid set of instructions, the researchers decided to let the robot discover itself instead. The Starfish would try out a move, such as the flailing of a limb like an infant would, and would subsequently access the consequences. In the robot’s case, it uses gyroscopes to see how the move tilted its central body. Although one stretch of the limbs would tall it what its body looks like and how it interacts, the feedback narrows the space of possibilities.
“It begins by building a series of computer models of how its parts might be arranged, at first just putting them together in random arrangements. Then it develops commands it might send to its motors to test the models. A key step, the researchers said, is that it selects the commands most likely to produce different results depending on which model is correct. It executes the commands and revises its models based on the results. It repeats this cycle 15 times, then attempts to move forward.
The result is usually an ungainly but functional gait; the most effective so far is a sort of inchworm motion in which the robot alternately moves its legs and body forward.
Once the robot reaches that point, the experimenters remove part of one leg. When the robot can’t move forward, it again builds and tests 16 simulations to develop a new gait.”
This exact ‘trick’ is what allows the skateboarding and surfboarding dogs to master their craft. By babbling with their bodies, they try out various moves, postures, positions, and balances, and they access the results.
Trending AI/ML Article Identified & Digested via Granola by Ramsey Elbasheer; a Machine-Driven RSS Bot