Research Analyzer
← Back ICRA 2026

Real-Time Localization Scoring for Challenging Industrial Environments

Abdurrahman Yilmaz, Umut Dumandag, Aydin Cagatay Sari, Ismail Hakki Savci, Hakan Temeltas

PDF

AI summary

Key figure (auto-extracted from paper)
A real-time localization scoring architecture quantifies positioning confidence to enable lifelong, adaptive navigation for autonomous mobile robots in dynamic industrial environments.
Autonomous Mobile Robots Real-Time Localization Localization Confidence Industrial Automation Map Reconciliation Particle Filter

Problem

Autonomous mobile robots struggle to maintain reliable localization in dynamic industrial environments due to changing layouts, sensor interference, and unpredictable obstacles, while existing confidence estimation methods lack the adaptability needed for real-world factory settings.

Approach

The authors developed a real-time scoring architecture that combines particle filter weight analysis, distribution covariance, and map-measurement consistency to generate a continuous confidence metric for robot positioning.

Key results

  • A scalable real-time localization scoring framework that dynamically evaluates positioning confidence
  • Real-time detection of localization failures triggering automatic map reconciliation and sensor adjustments
  • Successful validation through extensive field tests in an operational automotive production factory
  • Enhanced navigation adaptability and traffic coordination in highly dynamic industrial settings

Why it matters

It enables reliable, lifelong operation of autonomous mobile robots in complex factories, preventing costly production disruptions and improving efficiency for industrial automation stakeholders.

Abstract

Autonomous Mobile Robots (AMRs) are revolutionizing industries by enhancing flexibility and efficiency, particularly in dynamic environments such as automotive manufacturing. These en- vironments pose challenges due to their constantly changing layouts, unpredictable obstacles, and varying conditions, which impact the performance of localization systems. This paper presents a novel real-time localization scoring architecture to address these challenges by quantifying the confidence in a robot’s positioning system. The proposed Localization Score improves map reconciliation, man- ages sensor interference, adapts navigation strategies, and enhances traffic coordination. Extensive experimental studies, including real-world deployment in an operational automotive production factory, demonstrate the robustness, accuracy, and adaptability of the developed Localization Score algorithm. The results showcase its potential to significantly enhance the operational efficiency and reliability of AMRs in industrial settings.

Index terms

Localization Autonomous Vehicle Navigation SLAM

Related papers