Efficient and Reliable Sensor Models for Humanoid Soccer Robot Self-Localization

Although the precise structure of the color-coded environment as well as different well-proven state estimation algorithms are known, self-localization in a humanoid soccer robot scenario remains a challenging task. Different problems arise, e. g., from an inaccurate proprioception, the sparsity of unique features, or the perception of false positives. In this paper, we present approaches for reliable and efficient feature extraction together with the features' incorporation into a robust state estimation process.