Automation in Construction

Researchers at National Taiwan University developed an AI system that recognizes construction activities at both the individual and crew levels using ordinary site videos. The approach reveals how teamwork shapes productivity and provides a foundation for future human-robot collaboration on construction sites.

Identifying cracks is critical for health monitoring of civil infrastructure. To enhance inspection efficiency, the proposed autonomous crack segmentation and exploration system enables the agent to navigate itself without human operation, and the agent successfully captures over 85% of cracks in the training dataset and achieves 82% crack coverage in the testing dataset. In terms of computational resources, proposed system enhances efficiency by 64% compared to conventional exhaustive search methods, demonstrating strong potential for practical deployment on UAVs and other edge devices.