Lernverfahren für die Wahl sicherer Schrittpositionen


This work presents an approach for learning secure step positions, with the objective that the four-legged robot AMEE can safely walk in rough terrain. The autonomous task to be mastered is to identify features of the surrounding area. The suitability ofa step position will be learned by doing and analyzing the step characteristic so that floor sections can be evaluated for their running quality. Reinforcement Learning serves as framework of the machine learning method.