Visual Measurement Integrity Monitoring for UAV Localization
This addresses the need for safety-critical visual localization in UAV missions, such as rescue operations, by introducing a method to assess integrity, which is incremental as it adapts an existing GNSS technique to a new domain.
The paper tackles the problem of ensuring reliable pose estimates for UAVs by proposing a novel approach to monitor the integrity of optimization-based visual localization, inspired by RAIM from GNSS, and demonstrates that it provides significantly more reliable error bounds than the commonly used 3σ method on the EuRoC dataset.
Unmanned aerial vehicles (UAVs) have increasingly been adopted for safety, security, and rescue missions, for which they need precise and reliable pose estimates relative to their environment. To ensure mission safety when relying on visual perception, it is essential to have an approach to assess the integrity of the visual localization solution. However, to the best of our knowledge, such an approach does not exist for optimization-based visual localization. Receiver autonomous integrity monitoring (RAIM) has been widely used in global navigation satellite systems (GNSS) applications such as automated aircraft landing. In this paper, we propose a novel approach inspired by RAIM to monitor the integrity of optimization-based visual localization and calculate the protection level of a state estimate, i.e. the largest possible translational error in each direction. We also propose a metric that quantitatively evaluates the performance of the error bounds. Finally, we validate the protection level using the EuRoC dataset and demonstrate that the proposed protection level provides a significantly more reliable bound than the commonly used $3σ$ method.