Traditional manual crack inspection methods often face limitations in terms of efficiency, safety, and consistency. To overcome these issues, a new approach based on autonomous robotic systems has gained attention, combining robotics, artificial intelligence, and advanced sensing technologies. However, most existing reviews focus on individual components in isolation and fail to present a complete picture of how these systems work together. This study focuses on robotic crack detection and proposes a structured framework that connects three core modules: the physical platform (robots and sensors), the cognitive core (crack detection algorithms), and autonomous action (navigation and planning). We analyze key technologies, their interactions, and the challenges involved in real-world implementation. The aim is to provide a clear roadmap of current progress and future directions, helping researchers and engineers better understand the field and develop smart, deployable systems for infrastructure crack inspection.

Crack detection in mobile inspection scenarios is constrained by both the extremely slender geometry of crack targets and the real-time inference requirements on edge devices, which expose systematic limitations of general-purpose object detectors. This paper proposes YOLO-Crack, a closed-loop solution that couples geometry-statistics-driven module design with end-to-end edge deployment validation. On the algorithmic side, we first quantify crack geometric properties and then introduce (i) a crack-aware cross-dimensional fusion attention (CFCA) module to strengthen feature representations, (ii) a dual-path feature enhancement module (DFEM) to preserve fine details during upsampling, and (iii) an empirical smooth quality window adjustment with shape consistency regularization to stabilize bounding-box regression for slender cracks. Experiments on the Crack500 dataset show that YOLO-Crack achieves 78.8% precision, 51.4% recall, and 65.7% mAP@0.5, improving over the YOLOv11n baseline by 4.2, 1.7, and 2.9 percentage points, respectively. On the engineering side, we deploy YOLO-Crack on a Jetson Orin NX mobile robot platform and evaluate it in a real ROS pipeline; the measured end-to-end throughput reaches 25.5 FPS, meeting real-time video processing requirements. The proposed framework provides a practical reference workflow for edge vision tasks, from geometry analysis to engineering verification.