Robust visual homing with landmark angles

Abstract

This paper presents a novel approach to visual homing for robot navigation on the ground plane, using only the angles of landmark points. We focus on a robust approach, leading to successful homing even in real, dynamic environments where significant numbers of landmark points are wrong or missing. Three homing algorithms are presented, two are shown to be provably convergent, and the other shown to converge empirically. Results from simulations under noise and robot homing in real environments are provided.