A particle‐filtering framework for integrity risk of GNSS‐camera sensor fusion

Abstract

Adopting a joint approach toward state estimation and integrity monitoring results in unbiased integrity monitoring unlike traditional approaches. So far, a joint approach was used in particle RAIM (Gupta & Gao, 2019) for GNSS measurements only. In our work, we extend Particle RAIM to a GNSS‐camera fused system for joint state estimation and integrity monitoring. To account for vision faults, we derived a probability distribution over position from camera images using map‐matching. We formulated a Kullback‐Leibler divergence (Kullback & Leibler, 1951) metric to assess the consistency of GNSS and camera measurements and mitigate faults during sensor fusion. Experimental validation on a real‐world data set shows that our algorithm produces less than 11 m position error and the integrity risk over bounds the probability of HMI with 0.11 failure rate for an 8 m alert limit in an urban scenario.

Urban Localization using Robust Filtering at Multiple Linearization Points

“…Particle filter, another type of Bayesian filter, captures multi-modal uncertainty over the state by tracking the distribution as a weighted collection of points in the state space [19]. In a recent work [20], a particle filtering framework was proposed for fusing GNSS with camera images and for characterizing the uncertainty in localization from sensor fusion. Similarly, in [21], images from a monocular camera were fused with low-cost GPS sensors and a map to provide high-accuracy localization.…”