Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

BIM-Discrepancy-Driven Active Sensing for Risk-Aware UAV-UGV Navigation

Hesam Mojtahedi, Reza Akhavian

TL;DR

This work tackles autonomous navigation in dynamic construction environments by marrying BIM priors with real-time LiDAR sensing to maintain a probabilistic 2D occupancy map. It introduces a corridor-based risk metric that fuses occupancy uncertainty, BIM–map discrepancy, and clearance, and triggers UAV rescans only when needed to enable safe replanning. The approach demonstrates substantial reductions in corridor risk and map entropy while maintaining adequate clearance, and shows UAV-assisted updates can outperform frontier-based exploration in terms of mission time. By treating BIM as a soft, online prior and coupling it with active aerial sensing, the framework offers a scalable pathway for uncertainty-aware, cooperative UAV–UGV autonomy at construction sites.

Abstract

This paper presents a BIM-discrepancy-driven active sensing framework for cooperative navigation between unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) in dynamic construction environments. Traditional navigation approaches rely on static Building Information Modeling (BIM) priors or limited onboard perception. In contrast, our framework continuously fuses real-time LiDAR data from aerial and ground robots with BIM priors to maintain an evolving 2D occupancy map. We quantify navigation safety through a unified corridor-risk metric integrating occupancy uncertainty, BIM-map discrepancy, and clearance. When risk exceeds safety thresholds, the UAV autonomously re-scans affected regions to reduce uncertainty and enable safe replanning. Validation in PX4-Gazebo simulation with Robotec GPU LiDAR demonstrates that risk-triggered re-scanning reduces mean corridor risk by 58% and map entropy by 43% compared to static BIM navigation, while maintaining clearance margins above 0.4 m. Compared to frontier-based exploration, our approach achieves similar uncertainty reduction in half the mission time. These results demonstrate that integrating BIM priors with risk-adaptive aerial sensing enables scalable, uncertainty-aware autonomy for construction robotics.

BIM-Discrepancy-Driven Active Sensing for Risk-Aware UAV-UGV Navigation

TL;DR

This work tackles autonomous navigation in dynamic construction environments by marrying BIM priors with real-time LiDAR sensing to maintain a probabilistic 2D occupancy map. It introduces a corridor-based risk metric that fuses occupancy uncertainty, BIM–map discrepancy, and clearance, and triggers UAV rescans only when needed to enable safe replanning. The approach demonstrates substantial reductions in corridor risk and map entropy while maintaining adequate clearance, and shows UAV-assisted updates can outperform frontier-based exploration in terms of mission time. By treating BIM as a soft, online prior and coupling it with active aerial sensing, the framework offers a scalable pathway for uncertainty-aware, cooperative UAV–UGV autonomy at construction sites.

Abstract

This paper presents a BIM-discrepancy-driven active sensing framework for cooperative navigation between unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) in dynamic construction environments. Traditional navigation approaches rely on static Building Information Modeling (BIM) priors or limited onboard perception. In contrast, our framework continuously fuses real-time LiDAR data from aerial and ground robots with BIM priors to maintain an evolving 2D occupancy map. We quantify navigation safety through a unified corridor-risk metric integrating occupancy uncertainty, BIM-map discrepancy, and clearance. When risk exceeds safety thresholds, the UAV autonomously re-scans affected regions to reduce uncertainty and enable safe replanning. Validation in PX4-Gazebo simulation with Robotec GPU LiDAR demonstrates that risk-triggered re-scanning reduces mean corridor risk by 58% and map entropy by 43% compared to static BIM navigation, while maintaining clearance margins above 0.4 m. Compared to frontier-based exploration, our approach achieves similar uncertainty reduction in half the mission time. These results demonstrate that integrating BIM priors with risk-adaptive aerial sensing enables scalable, uncertainty-aware autonomy for construction robotics.

Paper Structure

This paper contains 42 sections, 13 equations, 2 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. Active Sensing and Frontier-Based Exploration
  4. Active SLAM and Planning Under Uncertainty
  5. 3D Mapping and Occupancy Representations
  6. UAV–UGV Cooperative Mapping
  7. BIM Integration and Prior-Guided Mapping
  8. Identified Gaps and Novelty
  9. Overview of the Developed Framework
  10. System Concept
  11. Corridor-Based Risk Assessment
  12. Risk-Triggered UAV Re-Scanning
  13. Summary of Workflow
  14. Methodology
  15. World and Mapping
  16. ...and 27 more sections

Figures (2)

  • Figure 1: System architecture of the proposed UAV–UGV autonomous navigation framework.
  • Figure 2: Simulation environment and BIM-based prior map. (a) Gazebo simulation environment representing the construction scene used for UAV--UGV experiments. (b) Corresponding 2D occupancy map generated from BIM.