We present a time and energy optimal controller for a two-wheeled differentially driven robot. We call a mission the task of bringing the robot from an initial state to a desired f...
A visually-based evolvable control architecture for agents in interactive entertainment applications is presented. Agents process images of their local surroundings according to ev...
Fuzzy controllers are designed to work with knowledge in the form of linguistic control rules. But the translation of these linguistic rules into the framework of fuzzy set theory ...
There is a need for research on the scientific base and engineering requirements for building trustworthy systems in dynamic environments. To address this need, we study risk analy...
Abstract— A combination of backpropagation and neuroevolution is used to train a neural network visual controller for agents in the Quake II environment. The agents must learn to...