Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Understanding Sensor Vulnerabilities in Industrial XR Tracking

Sourya Saha, Md. Nurul Absur

TL;DR

The paper investigates sensor vulnerabilities in industrial XR tracking by performing a controlled fault-injection study on a visual–inertial odometry pipeline. Using an XR-oriented setup (ILLIXR/OpenVINS) and the EuRoC dataset, it systematically varies fault type, timing, duration, and severity across camera and IMU modalities. A pronounced asymmetry emerges: visual degradations cause bounded, centimeter-scale pose errors, while inertial degradations induce drastic drift, from hundreds of meters to several kilometers, underscoring the critical importance of inertial reliability in real-world XR deployments. The findings advocate prioritizing inertial robustness and designing fault-tolerant strategies for XR systems, with practical implications for redundancy, fault detection, and adaptive fusion in industrial contexts.

Abstract

Extended Reality (XR) systems deployed in industrial and operational settings rely on Visual--Inertial Odometry (VIO) for continuous six-degree-of-freedom pose tracking, yet these environments often involve sensing conditions that deviate from ideal assumptions. Despite this, most VIO evaluations emphasize nominal sensor behavior, leaving the effects of sustained sensor degradation under operational conditions insufficiently understood. This paper presents a controlled empirical study of VIO behavior under degraded sensing, examining faults affecting visual and inertial modalities across a range of operating regimes. Through systematic fault injection and quantitative evaluation, we observe a pronounced asymmetry in fault impact where degradations affecting visual sensing typically lead to bounded pose errors on the order of centimeters, whereas degradations affecting inertial sensing can induce substantially larger trajectory deviations, in some cases reaching hundreds to thousands of meters. These observations motivate greater emphasis on inertial reliability in the evaluation and design of XR systems for real-life industrial settings.

Understanding Sensor Vulnerabilities in Industrial XR Tracking

TL;DR

The paper investigates sensor vulnerabilities in industrial XR tracking by performing a controlled fault-injection study on a visual–inertial odometry pipeline. Using an XR-oriented setup (ILLIXR/OpenVINS) and the EuRoC dataset, it systematically varies fault type, timing, duration, and severity across camera and IMU modalities. A pronounced asymmetry emerges: visual degradations cause bounded, centimeter-scale pose errors, while inertial degradations induce drastic drift, from hundreds of meters to several kilometers, underscoring the critical importance of inertial reliability in real-world XR deployments. The findings advocate prioritizing inertial robustness and designing fault-tolerant strategies for XR systems, with practical implications for redundancy, fault detection, and adaptive fusion in industrial contexts.

Abstract

Extended Reality (XR) systems deployed in industrial and operational settings rely on Visual--Inertial Odometry (VIO) for continuous six-degree-of-freedom pose tracking, yet these environments often involve sensing conditions that deviate from ideal assumptions. Despite this, most VIO evaluations emphasize nominal sensor behavior, leaving the effects of sustained sensor degradation under operational conditions insufficiently understood. This paper presents a controlled empirical study of VIO behavior under degraded sensing, examining faults affecting visual and inertial modalities across a range of operating regimes. Through systematic fault injection and quantitative evaluation, we observe a pronounced asymmetry in fault impact where degradations affecting visual sensing typically lead to bounded pose errors on the order of centimeters, whereas degradations affecting inertial sensing can induce substantially larger trajectory deviations, in some cases reaching hundreds to thousands of meters. These observations motivate greater emphasis on inertial reliability in the evaluation and design of XR systems for real-life industrial settings.
Paper Structure (22 sections, 4 equations, 15 figures, 1 table)

This paper contains 22 sections, 4 equations, 15 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Works
  3. Empirical Framework
  4. System Pipeline
  5. Fault Injection Mechanism
  6. Dataset and Reference Trajectory
  7. Evaluation Metrics
  8. Absolute Trajectory Error (ATE)
  9. Relative Pose Error (RPE)
  10. Experimental Configuration and Implementational Details
  11. Experimental Analysis
  12. Effect of Fault Injection Timing
  13. Camera Fault Timing
  14. IMU Fault Timing
  15. Effect of Camera Blackout Duration
  16. ...and 7 more sections

Figures (15)

  • Figure 1: Illustration of sensor fault behavior in XR VIO. (a) Conceptual pipeline showing fault points. (b) Pose error growth over time under sustained camera degradation. (c) Mean pose error as a function of IMU noise severity, highlighting pronounced error growth under severe inertial corruption.
  • Figure 2: System architecture of our empirical framework
  • Figure 3: Left ($\sigma=10$)
  • Figure 4: Left ($\sigma=50$)
  • Figure 5: Right ($\sigma=10$)
  • ...and 10 more figures