TANGO-VIO: Triangulation-Aware Navigation with Guaranteed Feature-Observability for Visual-Inertial Odometry
2026-08-03 • Robotics
Robotics
AI summaryⓘ
The authors address a common problem in navigation systems that use cameras and motion sensors: it becomes hard to figure out exact 3D positions of points when the camera only rotates or when there's little change in viewing angle. They propose TANGO-VIO, a system that actively keeps track of how well these points can be seen and adjusts the movement to improve 3D position estimation. Their method uses a mathematical way to measure and ensure good conditions for triangulating features during navigation. They tested their approach in simulations and real drone flights, showing it works well and is practical for real-world use.
Visual-inertial odometryTriangulationFeature observabilityParallaxControl barrier functionLog-determinant metricState estimationBearing vectorsSoftware-in-the-loop simulationNavigation safety filter
Authors
Ege C. Altunkaya, Abdülbaki Şanlan, Emre Koyuncu, İbrahim Özkol
Abstract
In vision-aided navigation and visual-inertial odometry, the quality of triangulated three-dimensional feature positions is a fundamental prerequisite for state estimation accuracy. Triangulation becomes ill-conditioned or even impossible when a camera undergoes pure rotation without translation, or when the observed bearing vectors provide insufficient parallax. Even though visual-inertial odometry has been extensively studied, the active maintenance of feature-observability during navigation has not been sufficiently addressed in the literature. To address this gap, this study presents TANGO-VIO, a triangulation-aware navigation framework that embeds a log-determinant metric of the feature-wise stacked-bearing matrix into a control barrier function. In this proposed method, the observability guarantee is established in the feature-geometric sense by enforcing a lower bound on the aggregate triangulation-information metric through a nominal-direction-weighted minimum-deviation velocity correction. The proposed architecture is evaluated through software-inthe- loop simulations and real flight experiments. The results show improved triangulation conditioning under low-parallax motion, while the flight response closely reproduces the corresponding simulation behavior and confirms the practical realizability of the proposed safety filter. Supplementary materials are available on the project webpage.