Robotic Inspection and Data Analytics to Localize and Visualize the Structural Defects of Concrete Infrastructure

摘要

This paper presents an innovative robotic inspection system designed to enhance the detection and analysis of structural defects in concrete infrastructure. The proposed inspection system is comprised of three modules: a robotic data collection module, a visual inspection module, and a subsurface mapping module. The robotic data collection module features an omnidirectional robotic platform, designed to move sideways without spinning. It is equipped with Ground Penetrating Radar (GPR) and RGB-D cameras, facilitating systematic data collection across construction sites. The visual inspection module employs a learning-based method, InspectionNet++, to analyze the frames for surface defects such as cracks, spalls, and stains, providing high accuracy and metric measurements of the defects. The subsurface mapping module processes the GPR data to detect and visualize hidden defects, creating a comprehensive map that correlates these with visible surface anomalies. Field tests demonstrate the system’s ability to automate construction structural inspection with improved efficiency and precision. Additionally, the customized visualization software is introduced to enable intuitive and interactive exploration of the detected defects within a unified interface. By automating data collection and enhancing defect detection through learning algorithms, the system not only speeds up the inspection process but also increases the reliability of infrastructure evaluations, supporting more informed maintenance decisions. Note to Practitioners—This paper introduces a robotic solution for inspection and condition assessment of concrete infrastructure. The system uses an omnidirectional robot equipped with GPR and RGB-D cameras to automatically collect data across construction sites. By harnessing vision-based positioning technology, our system empowers the robot to scan the ground surface in free motion pattern. This eliminates the need for time-consuming grid line setup traditionally required for manual GPR data collection. Our approach combines multi-sensor data analytics with advanced software, which enables the detection and visualization of both surface defects (cracks, spalls, stains) and subsurface anomalies. For practitioners, this automated approach offers several key benefits over manual inspections: increased inspection speed and coverage, rapid data collection enabled by robotic free motion, higher detection accuracy, quantitative defect measurements, and unified visualization correlating surface/subsurface conditions. This system has the potential to revolutionize infrastructure assessment practices. By facilitating more frequent and reliable inspections with minimal human intervention, it paves the way for proactive maintenance and ensures the sustainability of critical infrastructure. A current limitation is the relatively small training dataset for visual inspection, which may affect generalizability across diverse concrete structures. Future work aims to expand the dataset, improve irrelevant feature filtering, and utilize other NDE sensors (e.g., impact echo) for infrastructure inspection.