Developing an autonomous crack segmentation and exploration system for civil infrastructure

Identifying cracks is critical for the monitoring of civil infrastructure. To enhance inspection efficiency, a proposed autonomous crack segmentation and exploration system enables the agent to navigate itself without human operation, and the agent successfully captures more than 85% of cracks in the training dataset and achieves 82% crack coverage in the testing dataset.

In terms of computational resources, the proposed system enhances efficiency by 64% compared to conventional exhaustive search methods, demonstrating strong potential for practical deployment on UAVs and other edge devices.

Regular structural health inspections are a critical component of building safety assessment. However, traditional inspection methods remain highly labor-intensive. In recent years, numerous studies have demonstrated the effectiveness of unmanned aerial vehicles (UAVs) in this field, significantly improving inspection efficiency while reducing the risk of exposing personnel to hazardous environments such as bridges, wind turbine towers, and dams.

Despite these advances, UAV-based inspections still rely heavily on human involvement, including manual operation or pre-defined flight path planning. Such dependence inevitably introduces human error and can lead to blind spots in structural coverage, which poses challenges for both UAV control and path planning.

To address these issues, a new study, published in Automation in Construction, proposes a fully autonomous crack inspection framework shown in fig. 1. By leveraging deep reinforcement learning, the researchers trained an autonomous agent capable of adaptively following crack patterns to maximize inspection efficiency, while also learning to decide the appropriate stopping time to terminate the search in order to mitigate UAV battery usage.

Fig. 2 shows an example of surface cracks, and fig. 3 demonstrates that the trained agent is able to explore the existence of cracks and navigate itself without human operation, by using only partially observable states indicated in yellow boxes.

The proposed approach substantially reduces the time and labor costs associated with structural health monitoring, while enabling more frequent inspections. Ultimately, this contributes to earlier detection of potential structural problems and improved safety and durability of civil infrastructure.

“The proposed framework demonstrates how AI and UAV integration can transform structural health monitoring into a safer, faster, and more reliable process,” says Prof. Rih-Teng Wu, corresponding author of the study.