Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Evaluating Magic Leap 2 Tool Tracking for AR Sensor Guidance in Industrial Inspections

Christian Masuhr, Julian Koch, Thorsten Schüppstuhl

TL;DR

This paper delivers the first comprehensive, robot-assisted benchmark of the Magic Leap 2 controller for industrial AR tool tracking, using EN ISO 9283-aligned static and dynamic tests with OptiTrack ground truth. It demonstrates sub-2 mm dynamic accuracy under favorable frontal viewing but reveals a systematic, angle-dependent failure mode that can produce large gross errors despite high confidence, highlighting a key safety concern for AR-guided leakage inspections. The study provides a transferable methodology and a robust baseline for evaluating ML2 in sensor-guided industrial tasks, while also identifying practical limitations such as non-configurable energy-saving behavior and limited 6-DoF analysis. The findings inform necessary mitigations, including fail-safe mechanisms, real-time post-processing, and broader validation to bridge toward real-world deployment in hydrogen-inspection workflows.

Abstract

Rigorous evaluation of commercial Augmented Reality (AR) hardware is crucial, yet public benchmarks for tool tracking on modern Head-Mounted Displays (HMDs) are limited. This paper addresses this gap by systematically assessing the Magic Leap 2 (ML2) controllers tracking performance. Using a robotic arm for repeatable motion (EN ISO 9283) and an optical tracking system as ground truth, our protocol evaluates static and dynamic performance under various conditions, including realistic paths from a hydrogen leak inspection use case. The results provide a quantitative baseline of the ML2 controller's accuracy and repeatability and present a robust, transferable evaluation methodology. The findings provide a basis to assess the controllers suitability for the inspection use case and similar industrial sensor-based AR guidance tasks.

Evaluating Magic Leap 2 Tool Tracking for AR Sensor Guidance in Industrial Inspections

TL;DR

This paper delivers the first comprehensive, robot-assisted benchmark of the Magic Leap 2 controller for industrial AR tool tracking, using EN ISO 9283-aligned static and dynamic tests with OptiTrack ground truth. It demonstrates sub-2 mm dynamic accuracy under favorable frontal viewing but reveals a systematic, angle-dependent failure mode that can produce large gross errors despite high confidence, highlighting a key safety concern for AR-guided leakage inspections. The study provides a transferable methodology and a robust baseline for evaluating ML2 in sensor-guided industrial tasks, while also identifying practical limitations such as non-configurable energy-saving behavior and limited 6-DoF analysis. The findings inform necessary mitigations, including fail-safe mechanisms, real-time post-processing, and broader validation to bridge toward real-world deployment in hydrogen-inspection workflows.

Abstract

Rigorous evaluation of commercial Augmented Reality (AR) hardware is crucial, yet public benchmarks for tool tracking on modern Head-Mounted Displays (HMDs) are limited. This paper addresses this gap by systematically assessing the Magic Leap 2 (ML2) controllers tracking performance. Using a robotic arm for repeatable motion (EN ISO 9283) and an optical tracking system as ground truth, our protocol evaluates static and dynamic performance under various conditions, including realistic paths from a hydrogen leak inspection use case. The results provide a quantitative baseline of the ML2 controller's accuracy and repeatability and present a robust, transferable evaluation methodology. The findings provide a basis to assess the controllers suitability for the inspection use case and similar industrial sensor-based AR guidance tasks.

Paper Structure

This paper contains 25 sections, 7 figures, 4 tables.

Table of Contents

  1. Introduction
  2. STATE OF THE ART
  3. Tool Tracking Technologies for AR in Industrial Settings
  4. Accuracy Analysis of Tool Tracking Systems
  5. METHODOLOGIES
  6. Use-Case of an AR-Assisted Leakage Inspection
  7. Rationale for Technology Selection
  8. Experimental Methodology
  9. Hardware and Experimental Setup
  10. Coordinate System Alignment and Data Capture
  11. Accuracy and Repeatability Tests:
  12. Metrics and Data Evaluation
  13. RESULTS
  14. Static Tracking Accuracy
  15. Dynamic Tracking Accuracy
  16. ...and 10 more sections

Figures (7)

  • Figure 1: Overview of AR assisted leakage inspection.
  • Figure 2: Electrolyzer leakage inspection.
  • Figure 3: ML2 with tripod mount (1); ML2 controller attached to UR10e robot (2); Camera capture of the running data capture application (3).
  • Figure 4: Part of the camera configuration of the used Optitrack system (1); Hardware setup for the ML2 tool tracking accuracy analysis on an instrument panel (2).
  • Figure 5: Poses and trajectories for experiment.
  • ...and 2 more figures