Effective localization of humanoid with fish-eye lens using field line detection

Abstract

This paper presents a real-time technique for efficient localization of a humanoid robot in a soccer field using a fish-eye lens. We propose a novel method that uses node merging to provide a robust and an accurate estimate of positions of the intersection points in the field lines. The distances to these points are calculated using Inverse Perspective Mapping and fed to the particle filter for the purpose of localization. The proposed algorithms have been implemented and tested on the humanoid robot platform AcYut, being developed at the Centre for Robotics and Intelligent Systems (CRIS), BITS Pilani.