In recent years, functional fluidic and gas electrohydrodynamic (EHD) pumps have received considerable attention due to their remarkable features, such as simple structure, quiet operation, and energy-efficient utilization. EHD pumps can be applied in various industrial applications, including flow transfer, thermal management, and actuator drive. In this paper, the authors reviewed the literature surrounding functional fluidic and gas EHD pumps regarding the following aspects: the initial observation of the EHD effect, mathematical modeling, and the choice of pump structure, electrode configuration, and working medium. Based on the review, we present a summary of the development and latest research on EHD pumps. This paper provides a critical analysis of the current limitations of EHD pumps and identifies potential areas for future research. Additionally, the potential application of artificial intelligence in the field of EHD pumps is discussed in the context of its cross-disciplinary nature. Many reviews on EHD pumps focus on rigid pumps, and the contribution of this review is to summarize and analyze soft EHD pumps that have received less attention, thus reducing the knowledge gap.

Rolling motions have been observed in many animals and insects. In the previous fluidic rolling system, a deformed chamber and long cables were imperative to drive the soft rolling actuators, which required high pressure and a sophisticated controlling strategy. In this study, we propose a soft fluidic roller using a simple structure composed of a bendable and twistable electrohydrodynamic (EHD) pump and a layer of natural latex. To realize the rolling motion, we first optimized the electrode and channel height of the EHD pumps using different patterns and designs. We also examined the output power, efficiency, pressure loss, bending, and twisting performance. Subsequently, the optimized electrodes and channel height were selected to design the power source of the EHD roller. This roller was lightweight (0.7 g) with an amount of liquid (0.6 g). This EHD robot can roll as the EHD liquid oscillates under a duty-controlled voltage realized using a high-voltage circuit. Next,we investigated the influence of frictional forces on rolling performance. Finally, the rolling motion in the liquid was demonstrated. This study extends the EHD pumps to independent soft actuators integrated with a soft power source.

In recent years, deep learning techniques for processing 3D point cloud data have seen significant advancements, given their unique ability to extract relevant features and handle unstructured data. These techniques find wide-ranging applications in fields like robotics, autonomous vehicles, and various other computer-vision applications. This paper reviews the recent literature on key tasks, including 3D object classification, tracking, pose estimation, segmentation, and point cloud completion. The review discusses the historical development of these methods, explores different model architectures, learning algorithms, and training datasets, and provides a comprehensive summary of the state-of-the-art in this domain. The paper presents a critical evaluation of the current limitations and challenges in the field, and identifies potential areas for future research. Furthermore, the emergence of transformative methodologies like PoinTr and SnowflakeNet is examined, highlighting their contributions and potential impact on the field. The potential cross-disciplinary applications of these techniques are also discussed, underscoring the broad scope and impact of these developments. This review fills a knowledge gap by offering a focused and comprehensive synthesis of recent research on deep learning techniques for 3D point cloud data processing, thereby serving as a useful resource for both novice and experienced researchers in the field.