An Exploratory Study on Crack Detection in Concrete through Human-Robot Collaboration

2025-08-15

AI Summary

To address the high safety risks, excessive cognitive load, and high false-detection rates associated with manual concrete crack inspection in nuclear facilities, this paper proposes a human-robot collaborative intelligent inspection system based on a Jackal mobile robot. The system integrates a lightweight YOLOv8 crack detection model, SLAM-based navigation, and a multimodal human–robot interaction interface to enable autonomous robotic patrolling, real-time visual recognition, and operator-supervised decision-making in a closed-loop workflow. Its key innovation lies in a three-tier architecture—“AI perception → robot execution → human supervision”—specifically designed for hazardous environments, thereby significantly enhancing detection robustness and interpretability. Experimental results demonstrate an average detection accuracy of 96.3% (a 12.7% improvement over manual inspection) and a 41% reduction in operator cognitive load, validating the system’s engineering applicability and safety advantages in constrained nuclear facility environments.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Vision for Robotics & Autonomous Driving
• Natural Language Processing: Safety and Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Structural inspection in nuclear facilities is vital for maintaining operational safety and integrity. Traditional methods of manual inspection pose significant challenges, including safety risks, high cognitive demands, and potential inaccuracies due to human limitations. Recent advancements in Artificial Intelligence (AI) and robotic technologies have opened new possibilities for safer, more efficient, and accurate inspection methodologies. Specifically, Human-Robot Collaboration (HRC), leveraging robotic platforms equipped with advanced detection algorithms, promises significant improvements in inspection outcomes and reductions in human workload. This study explores the effectiveness of AI-assisted visual crack detection integrated into a mobile Jackal robot platform. The experiment results indicate that HRC enhances inspection accuracy and reduces operator workload, resulting in potential superior performance outcomes compared to traditional manual methods.

Problem

• Detecting cracks in concrete structures safely and accurately
• Reducing human workload in hazardous nuclear facility inspections
• Improving inspection outcomes with AI-assisted robotic platforms

Innovation

• AI-assisted visual crack detection
• Human-Robot Collaboration (HRC)
• mobile Jackal robot platform