Technology Category
Intelligent Robots: Multimodal Perception & Sensor FusionPlanning, Routing, and Scheduling: Activity and Plan RecognitionHumans and AI: Planning and Decision Support for Human-Machine Teams
BIM-Discrepancy-Driven Active Sensing for Risk-Aware UAV-UGV Navigation
🤖 AI Summary
To address the limitations of conventional UAV-UGV collaborative navigation in dynamic construction environments—namely, overreliance on static BIM models and insufficient real-time perception—this paper proposes a dynamic occupancy mapping method that tightly fuses BIM priors with multi-source LiDAR data in real time. We introduce a novel BIM-difference-driven active sensing mechanism, defining a corridor risk metric that integrates occupancy uncertainty, BIM deviation, and navigable clearance; this metric triggers risk-aware autonomous re-scanning. Evaluated on the PX4-Gazebo simulation platform and Robotec GPU LiDAR hardware, our approach reduces average corridor risk by 58% and map entropy by 43% compared to static BIM-based navigation, while consistently maintaining a safety margin ≥0.4 m. Moreover, it achieves equivalent uncertainty suppression within 50% of the mission time required by state-of-the-art exploration methods.
Technology Category
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
Developing risk-aware UAV-UGV navigation using BIM-discrepancy-driven active sensing
Overcoming limitations of static BIM priors through real-time LiDAR fusion
Reducing navigation uncertainty and corridor risk through adaptive re-scanning
Innovation
Methods, ideas, or system contributions that make the work stand out.
Fuses real-time LiDAR with BIM for dynamic mapping
Uses unified corridor-risk metric for safety assessment
Triggers autonomous UAV re-scanning when risk exceeds threshold
🔎 Similar Papers
No similar papers found.
