Continuous Hybrid Localization in Environments with Physical and Temporal Sensor Occlusions

Abstract

The proliferation of more affordable sensors technologies has enabled the development of a variety of localization modalities and fusion techniques for pose estimation. Utilizing multiple localization techniques provides a more accurate pose estimate as well as a more robust solution reducing the risk associated with a lack of data for any given sensor due to occlusion(s) which here refers to the unavailability of a sensor's data due to signal loss from physical attenuation, distance, low bandwidth, sensor limitations, or sensor failure. In large complex environments the impact of occlusions cannot be known a priori - temporally or spatially. Here, we present a novel heuristic-based GNSS carrier noise re-initialization framework to manage transitions between localization modalities. Disturbance rejection is used to eliminate discrete filter jitter and manage the competing interests of competing state estimate data sources. The hybrid localization method is evaluated in a relevant environment and shown to be more effective than each individual localization modality.