Exploration of actual sky polarization patterns: From influencing factor analyses to polarized light-aided navigation

Abstract

The polarized light scattered by the sunlight and atmosphere is a general natural property of the atmospheric space of Earth. This study is devoted to an exploration of actual sky polarization pattern-oriented navigation. For the polarized light-aided VINS (abbreviated ‘visual-inertial navigation system’), one of our major concerns is to prove the heading (orientation) reference stays stable under the actual complex atmospheric environments. The influencing factors that contribute to the variation of the polarization pattern symmetry have been taken into account. The analytic AOP (abbreviated ‘angle of polarization’) and DOP (abbreviated ‘degree of polarization’) maps and quantitative analyses that concern spectrum character, cloudage, and aerosol optical depth relevant to light scattering effects are simultaneously presented. Given the globally referenced heading, one intuitive way of modeling multi-sensor fusion is to use a graph structure. Following the pipeline design of VINS Fusion, a polarization imaging factor constraint (expressed by the polarization measurement residual-encoded edges) is added in the state estimator and the cost function to be minimized during optimization is formulated. Via campus road experiments on the built robot platform, our proposal is compared against VINS Fusion under different weather conditions, revealing that over the entire closed path, our polarized light-aided VINS achieves high rate of both locally and globally consistent estimates. To our best knowledge, this is the first work to illuminate the insights into a practical, polarization imager-integrated navigating application in which the localization results can be optically explained, evaluated, and optimized.