The defect detection of printed circuit board (PCB) images faces challenges such as limited sample number, imbalanced sample types, and varying detection reliability. To address these issues, this article proposes an uncertainty-aware unsupervised detection model on PCB images, short for $\rm { U^{2}D^{2}}$ PCB. The proposed method uses two U-Net networks to serve as the reconstructive subnetwork and the discriminative subnetwork, respectively. The former one reconstructs defect-free PCB images from defective PCB images, while the latter segments the defects and evaluates the defects uncertainty with the concatenated inputs of the defective and reconstructed images. The $\mathbf { U^{2}D^{2}}$ PCB model is trained in an unsupervised manner with only defect-free images embedding with multiscale artificial defects. Experimental results on the public PCB defect dataset and DeepPCB dataset demonstrate the effectiveness of the proposed method. The mean average precision (mAP) is 99.29% on the PCB defect dataset, while it reaches 95.78% on the DeepPCB dataset. These results are competitive to those of state-of-the-art (SOTA) fully supervised methods. The findings of $\mathrm { U^{2}D^{2}}$ PCB highlight the potential significance of using unsupervised learning techniques for PCB defect detection.

To address the issue of current garbage cleanup vessels being limited to performing garbage cleaning operations in the ocean, without the capability of transferring the garbage from the ocean to the land, this paper presents a spiral-propulsion amphibious intelligent robot for land garbage cleaning and sea garbage cleaning. The design solution is as follows. A mechanical structure based on a spiral drum is proposed. The interior of the spiral drum is hollow, providing buoyancy, allowing the robot to travel both on marshy, tidal flats and on the water surface, in conjunction with underwater thrusters. Additionally, a mechanical-arm shovel is designed, which achieves two-degrees-of-freedom movement through a spiral spline guide and servo, facilitating garbage collection. Our experimental results demonstrated that the robot exhibits excellent maneuverability in marine environments and on beach, marsh, and tidal flat areas, and that it collects garbage effectively.

In the realm of industrial quality inspection, defect detection stands as a critical component, particularly in high-precision, safety-critical sectors such as automotive components aerospace, and medical devices. Traditional methods, reliant on manual inspection or early image processing algorithms, suffer from inefficiencies, high costs, and limited robustness. This paper introduces a semi-supervised defect detection framework based on conditional diffusion (DSYM), leveraging a two-stage collaborative training mechanism and a staged joint optimization strategy. The framework utilizes labeled data for initial training and subsequently incorporates unlabeled data through the generation of pseudo-labels. A conditional diffusion model synthesizes multi-scale pseudo-defect samples, while a CLIP cross-modal feature-based noise filtering mechanism mitigates label contamination. Experimental results on the NEU-DET dataset demonstrate a 78.4% mAP@0.5 with the same amount of labeled data as traditional supervised methods, and 75.1% mAP@0.5 with only 40% of the labeled data required by the original supervised model, showcasing significant advantages in data efficiency. This research provides a high-precision, low-labeling-dependent solution for defect detection in industrial quality inspection scenarios. The work of this article has been open-sourced at https://github.com/cLin-c/Semisupervised-DSYM.