Surface defect segmentation is the basis of industrial production, where pixel-level defect prediction plays a vital role in many applications. As a new trend, few-shot defect detection aims to recognize defects by combining information from a few defect samples. However, many traditional few-shot methods do not consider patch-level correlations between input images and memory banks. This work introduces a novel representation framework consisting hierarchical normal and defect memory banks for few-shot surface defect detection. We propose an adaptive feature bank updating scheme that dynamically integrates frequent features while discarding rare ones. We design a fine-grain feature replacement module rooted in a matching attention mechanism to highlight ambiguous regions for input images, and use fused features to identify overall defects. On benchmark data sets, our strategy can obtain in-depth insights from multiple scales, which showcase superiority in generalization for unidentified anomalies better than others in experiments. The experimental results for the 10-shot scenarios demonstrate that the proposed method achieves an average pixel AUC of 88.6%, 93.7%, and 98.7% on three benchmark data sets, respectively, and with more genuine and pseudo anomalous samples, the proposed approach can achieve 98.5% and 95.5% in image AUC and pixel F1 score respectively, outperforming the state-of-the-art with 1.2% and 24% in each metric.

Vision-based tactile sensor (VBTS) has gained great traction within embodied tactile community in recent years. However, to reproduce a high-performance one, the contact elastomer is the key and its processing method largely depends on equipment and sophisticated operating skills, which sets obstacles for labs lacking hardware expertise and financial support. In this work, we present a low-cost and easy-to-fabricate processing scheme for the contact elastomer. Our scheme adopts a novel structure of reflective membrane by chemically bonding two different reflective layers, and utilizes laser stencils and bearing balls to make marker layers with high dimension consistency. The whole manufacturing process is completed manually and costs only 4.34 USD per elastomer. Several experiments are conduct to evaluate the performance of the elastomer. Results show that the finished elastomer possesses microlevel tactile mapping resolution and reliable force perception, as well as favorable durability. Additionally, the versatility of the method is shown by successfully designing and making other two different VBTSs. Compared to other advanced manufacturing methods, our proposed method not only enables the finished elastomer with comparable tactile performance, but also achieves a trade-off between simplicity and high sensitivity, making high-performance VBTSs more accessible to robotic community.

This article reports the in-depth analysis, software simulation, and experimental validation of the negative effects of roller compaction on the electrodes of double-layer capacitors, including particle detachment and current collector elongation. The main component of the coatings of double-layer capacitors is porous-particle-type activated carbon containing agglomerates. This study analyzed the interactions between activated carbon particles and agglomerates and constructed electrode models comprising particles of various shapes based on the results of the aforementioned analyses. A bonded particle model implemented in the discrete element method simulation software was employed to simulate and analyze the vertical pressing and bidirectional movements of the particles. Additionally, the simulation results were validated through roller compaction experiments on the electrodes of double-layer capacitors. The results of the simulations and experiments indicated that the roller compaction of double-layer-capacitor electrodes improved their performance and lifespan but lead to various issues such as particle detachment, current collector elongation, and electrode-thickness rebound. Roller compaction degree, compaction speed, and particle shape were found to be the major factors affecting the outcome of calendering. A greater degree of compaction resulted in greater particle detachment, and increased irregularity of particle shapes had a considerable negative impact on electrodes, which can be alleviated by appropriately increasing the compaction speed.

In this article, a low-cost but high-fidelity rolling tactile system is proposed for distinguishing patterns on curved surface, including an improved vision-based tactile sensor (VBTS) and a novel lightweight processing framework. The proposed VBTS contains a modular ring-shaped illumination configuration and an improved sensing elastomer, which is easy to fabricate without complex processing and costs only 16.95 USD in total. To achieve real-time data processing of rolling tactile images, inspired by event-based cameras, an efficient processing framework is introduced based on computer graphics, which can integrate sparse rolling tactile images into complete high-fidelity images for the final classification. To evaluate the effectiveness of the proposed system, a classification model is trained using dataset generated by 13 cylinders with similar textures, where the identification accuracy of validation is up to 98.3%. Then, we test each cylinder sample for 3 rolling tactile perceptions and achieve 100% identification accuracy within 1.2 s on average, indicating a promising prospect of the proposed perception system for real-time application