The maintenance and inspection of sewer pipes are essential to urban infrastructure but remain predominantly manual, resource-intensive, and prone to human error. Advancements in artificial intelligence (AI) and computer vision offer significant potential to automate sewer inspections, improving reliability and reducing costs. However, the existing vision-based inspection robots fail to provide data quality sufficient for training reliable deep learning (DL) models. To address these limitations, we propose a novel multi-sensor robotic system coupled with a DL integration concept. Following a comprehensive review of the current 2D (image) and 3D (point cloud) sewage pipe inspection methods, we identify key limitations and propose a system incorporating a camera array, front camera, and LiDAR sensor to optimise surface capture and enhance data quality. Damage types are assigned to the sensor best suited for their detection and quantification, while tailored DL models are proposed for each sensor type to maximise performance. This approach enables the optimal detection and processing of relevant damage types, achieving higher accuracy for each compared to single-sensor systems.

Sewer infrastructure is vital for flood prevention, environmental protection, and public health. As part of sewer infrastructure, sewer systems are prone to degradation. Traditional maintenance methods for sewer systems are largely manual and reactive and rely on inconsistent data, leading to inefficient maintenance. The KaSyTwin research project addresses the urgent need for efficient and resilient sewer system management methods in Germany, aiming to develop a methodology for the semi-automated development and utilization of digital twins of sewer systems to enhance data availability and operational resilience. Using advanced multi-sensor robotic platforms equipped with scanning and imaging systems, i.e., laser scanners and cameras, as well as artificial intelligence (AI), the KaSyTwin research project focuses on generating digital twin-enabled representations of sewer systems in real time. As a project report, this work outlines the research framework and proposed methodologies in the KaSyTwin research project. Digital twins of sewer systems integrated with AI technologies are expected to facilitate proactive maintenance, resilience forecasting against extreme weather events, and real-time damage detection. Furthermore, the KaSyTwin research project aspires to advance the digital management of sewer systems, ensuring long-term functionality and public welfare via on-demand structural health monitoring and non-destructive testing.

This work explores the possibility of automating the aerial survey of bridges to generate high-resolution images necessary for digital damage inspection. High-quality unmanned aerial vehicle (UAV) based 3D reconstruction of bridges is an important step towards autonomous infrastructure inspection. However, the calculation of optimal camera poses remains challenging due to the complex structure of bridges and is therefore often conducted manually. This process is time-consuming and can lead to quality losses. Research in this field to automate this process is yet sparse and often requires high informative models of the bridge as the base for calculations, which are not given widely. Therefore, this paper proposes an automated camera pose calculation method solely based on an easily accessible polygon mesh of the bridge. For safe operation, point cloud data of the environment are used for automated ground detection and obstacle avoidance including vegetation. First, an initial set of camera poses is generated based on a voxelized mesh created in respect to the quality requirements for 3D reconstruction using defined camera specification. Thereafter, camera poses not fulfilling safety distances are removed and specific camera poses are added to increase local coverage quality. Evaluations of three bridges show that for diverse bridge types, near-complete coverage was achieved. Due to the low computational effort of the voxel approach, the runtime was kept to a minimum, even for large bridges. The subsequent algorithm is able to find alternative camera poses even in areas where the optimal pose could not be placed due to obstacles.