Vision-Based Orientation Detection of Humanoid Soccer Robots

Knowing the positions of the other players on a football pitch is a crucial aspect for playing successfully. However, knowing not only the position but also the orientation of another player provides certain tactical advantages. In this paper, we present a vision-based approach for determining the orientation of humanoid NAO robots over short and medium distances. It is based on the idea of analyzing the alignment of other robots' foot sides. In a series of experiments, we demonstrate that the approach is able to perform robust and precise orientation detection in different scenarios.