Research Analyzer
← Back ICRA 2026

BIM-Informed Visual SLAM for Construction Monitoring

Asier Bikandi-Noya, Miguel Fernandez-Cortizas, Muhammad Shaheer, Ali Tourani, Holger Voos, Jose Luis Sanchez-Lopez

PDF

AI summary

Key figure (auto-extracted from paper)
Integrating Building Information Model (BIM) priors into visual SLAM significantly reduces trajectory drift and improves map accuracy for real-time construction site monitoring.
Visual SLAM BIM integration construction monitoring trajectory drift factor graph RGB-D sensing

Problem

Visual SLAM suffers from severe trajectory drift in construction environments due to repetitive layouts, textureless surfaces, and occlusions, making it unreliable for comparing as-built states with as-planned designs.

Approach

The system augments a visual SLAM backbone with BIM architectural priors by detecting walls, matching them to BIM counterparts, and enforcing these correspondences as uncertainty-aware geometric constraints in a factor graph back-end.

Key results

  • 25.23% average trajectory error reduction over baseline
  • 7.14% improvement in map point cloud accuracy
  • Robust to 30% missing BIM data and geometric deviations
  • Real-time operation at 23.3 FPS with minimal overhead

Why it matters

Enables reliable, real-time as-built versus as-planned construction monitoring using standard RGB-D sensors, directly benefiting construction automation and robotics.

Abstract

Monitoring construction sites requires comparing the as-planned design with the as-built state in real time. Visual SLAM offers a lightweight solution but is prone to trajectory drift in construction environments due to repetitive layouts, textureless surfaces, and occlusions. We augment an existing visual SLAM system with structural priors from the Building Information Model (BIM), associating detected walls with their BIM counterparts and including these correspondences as geometric constraints in the back-end optimization. The system operates in real time and is validated on multiple real construction sites, achieving 25.23% average trajectory error reduction and 7.14% map accuracy improvement over state- of-the-art baselines, with demonstrated resilience to incomplete BIM data and as-planned/as-built discrepancies.

Index terms

SLAM Robotics and Automation in Construction RGB-D Perception

Related papers