cs.RONov 5, 2026

Not Losing Your Way: Mitigating Visual-Inertial Odometry Drift through On-Demand Visual Feature Creation

Authors: Simone D'Angelo, Gianmarco Corrado, Federico Esposito, Vincenzo Scognamiglio, Fabio Ruggiero

Organizations: PRISMA Lab, Department of Engineering and Information Technology, University of Naples Federico II, Naples, Italy. · KRUSH Labs B.V., Eindhoven, Netherlands.

Abstract

Visual-inertial odometry (VIO) can degrade during aerial inspection in repetitive or poorly textured environments. We propose an active environment-modification framework for unmanned aerial vehicles (UAVs) relying on cameras and an inertial measurement unit only, without prior maps or additional localization sensors. Inspired by the fairy tale of Tom Thumb, the UAV creates visual features on demand by releasing ground markers or marking walls through physical contact. An information-based indicator triggers interventions using temporal confirmation and hysteresis. Evaluation includes three simulated environments and a 900-run factorial campaign. Lower cruise speed and active marking are associated with reduced divergence, while accuracy among non-divergent runs depends on speed-strategy interactions. Corridor experiments, with five runs per configuration, use OptiTrack for flight control while VIO-based marking decisions remain active online. The combined framework reduces the reported position root mean square error by approximately 35% relative to baseline VIO, supporting active feature creation for drift mitigation.

Figures & tables

Explore similar work

CardsList
  1. Perception-Aware Autonomous Exploration in Feature-Limited Environments

    Mar 16, 2026Moji Shi, Rajitha de Silva, Hang Yu +2UAV NavigationUAV Trajectory Optimization

  2. Evaluation of Image Matching Methods for Visual Odometry on UAVs

    Aug 19, 2026Gašper Spagnolo, Luka Čehovin Zajc, Matej DobrevskiVisual OdometryImage Matching

  3. LBDU-VIO: Learned Bias Dynamics and Uncertainty for Visual-Inertial Odometry with Unreliable Vision

    Sep 30, 2026Qizhi Guo, Junning Lyu, Defu Lin +1Kalman FilteringVisual-Inertial Odometry