Fusing vision-based bearing measurements and motion to localize pairs of robots

Abstract

Abstract — This paper presents a method to cooperatively localize pairs of robots fusing bearing-only information provided by a camera and the motion of the vehicles. The algorithm uses the robots as landmarks to estimate the relative location between the platforms. Bearings are obtained directly from the camera, as opposed to measuring depths which would require knowledge or reconstruction of the world structure. We present the general recursive Bayes estimator and three different implementations based on an extended Kalman filter, a particle filter and a combination of both techniques. We have compared the performance of the different implementations using real data acquired with two platforms, one equipped with an omnidirectional camera, and simulated data.