Technology Category
Intelligent Robots: Multimodal Perception & Sensor FusionNatural Language Processing: Safety and RobustnessPhilosophy and Ethics of AI: Safety, Robustness & Trustworthiness
Building Information Models to Robot-Ready Site Digital Twins (BIM2RDT): An Agentic AI Safety-First Framework
🤖 AI Summary
This study addresses the limitation of static BIM in enabling safe, autonomous robotic operations on construction sites by proposing a safety-centric agent-based AI framework that transforms BIM into a dynamic, executable site-level digital twin (DT). Methodologically: (1) it introduces semantic-gravity–integrated ICP (SG-ICP), a novel point cloud registration algorithm incorporating large language model–derived object orientation priors and gravity constraints, significantly improving registration accuracy under occlusion; (2) it establishes an IFC-standard–compliant safety event mapping mechanism that fuses BIM geometric-semantic data, IoT activity streams, and robot vision inputs to enable real-time risk alerts (e.g., arm vibration). Experiments show SG-ICP reduces RMSE by 64.3%–88.3% over conventional ICP; the system reliably triggers safety threshold alerts and markedly improves compliance with ISO 5349-1 hand-transmitted vibration standards.
Technology Category
Application Category
📝 Abstract
The adoption of cyber-physical systems and jobsite intelligence that connects design models, real-time site sensing, and autonomous field operations can dramatically enhance digital management in the construction industry. This paper introduces BIM2RDT (Building Information Models to Robot-Ready Site Digital Twins), an agentic artificial intelligence (AI) framework designed to transform static Building Information Modeling (BIM) into dynamic, robot-ready digital twins (DTs) that prioritize safety during execution. The framework bridges the gap between pre-existing BIM data and real-time site conditions by integrating three key data streams: geometric and semantic information from BIM models, activity data from IoT sensor networks, and visual-spatial data collected by robots during site traversal. The methodology introduces Semantic-Gravity ICP (SG-ICP), a point cloud registration algorithm that leverages large language model (LLM) reasoning. Unlike traditional methods, SG-ICP utilizes an LLM to infer object-specific, plausible orientation priors based on BIM semantics, improving alignment accuracy by avoiding convergence on local minima. This creates a feedback loop where robot-collected data updates the DT, which in turn optimizes paths for missions. The framework employs YOLOE object detection and Shi-Tomasi corner detection to identify and track construction elements while using BIM geometry as a priori maps. The framework also integrates real-time Hand-Arm Vibration (HAV) monitoring, mapping sensor-detected safety events to the digital twin using IFC standards for intervention. Experiments demonstrate SG-ICP's superiority over standard ICP, achieving RMSE reductions of 64.3%--88.3% in alignment across scenarios with occluded features, ensuring plausible orientations. HAV integration triggers warnings upon exceeding exposure limits, enhancing compliance with ISO 5349-1.
Problem
Research questions and friction points this paper is trying to address.
Transforming static BIM models into dynamic robot-ready digital twins
Bridging BIM data with real-time site conditions using multi-source data
Ensuring safety in autonomous construction operations through AI monitoring
Innovation
Methods, ideas, or system contributions that make the work stand out.
Agentic AI framework transforms BIM into robot-ready digital twins
SG-ICP algorithm uses LLM reasoning for improved point cloud alignment
Integrates real-time safety monitoring with BIM via IFC standards
🔎 Similar Papers
No similar papers found.
