arXiv:0907.1839cs.NE
An Evolved Neural Controller for Bipdedal Walking with Dynamic Balance
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
Abstract
We successfully evolved a neural network controller that produces dynamic walking in a simulated bipedal robot with compliant actuators, a difficult control problem. The evolutionary evaluation uses a detailed software simulation of a physical robot. We describe: 1) a novel theoretical method to encourage populations to evolve "around" local optima, which employs multiple demes and fitness functions of progressively increasing difficulty, and 2) the novel genetic representation of the neural controller.
(shameless plug:) here's a paper I worked on where we used evolved neural networks to control a robot (simulated, hoping to reproduce on the real robot soon): http://arxiv.org/abs/0907.1839 I've been fascinated by this idea since before I saw Karl Sim's work. My take on it now…
danbmil99View on HNParent context