Protection Levels for Vision-Based Pose Estimation

2026-08-09

AI Summary

This work addresses the challenge of ensuring integrity under undetected faults in aerial visual navigation by proposing a probabilistic computer vision framework that extends the principles of Receiver Autonomous Integrity Monitoring (RAIM) to the nonlinear Perspective-n-Point (PnP) problem. For the first time, it derives computationally tractable protection levels for six-degree-of-freedom pose estimation. By integrating probabilistic modeling, nonlinear optimization, and integrity monitoring, the method enables end-to-end computation of integrity bounds. The approach is validated in representative runway scenarios, with experiments systematically quantifying the impacts of measurement redundancy, pixel noise, and runway distance on protection levels. These results provide a verifiable safety foundation for visual pose estimation to meet the stringent reliability requirements of aviation certification.

Abstract

Vision-based navigation complements Global Navigation Satellite Systems, but certification demands integrity guarantees that account for faulty measurements. Previous work presented a probabilistic computer vision pipeline for runway-based pose estimation with fault detection inspired by Receiver Autonomous Integrity Monitoring. This work extends that framework by deriving protection levels, which provide probabilistic bounds on pose error that remain valid under undetected faults. We present an algorithm for computing protection levels for the nonlinear Perspective-$n$-Point problem applied to an aviation setting. The algorithm covers all six degrees of freedom of the aircraft pose (position and orientation) directly. We analyze the effect of measurement redundancy, pixel-level prediction uncertainty, and runway distance on the resulting protection levels. To make the results tangible, we demonstrate tradeoffs in the protection levels on an illustrative runway example.

Problem

• protection levels
• vision-based pose estimation
• integrity
• fault detection
• Perspective-n-Point

Innovation

• Protection Levels
• Vision-based Pose Estimation
• Integrity Monitoring
• Perspective-n-Point
• Fault Detection