Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)最新文献

Nanomaterial properties and functionalities are influenced by their shape, size, and chemical composition. The importance of these parameters highlights the need for a statistically robust analysis of a large particle population, necessitating automation. This study introduces a neural network-empowered smart scan technique that achieves a relative increase in speed compared to traditional energy-dispersive X-ray spectroscopy (EDX) mapping. The main advantage is that it reduces the required dose, decreasing potential damage to the sample by avoiding unnecessary exposure. It holds potential use in other multimodal scanning transmission electron microscopy or scanning-based imaging approaches. In the first example, identifying particles in a matrix with a trained neural network reduces the acquisition time by two orders of magnitude. This acceleration enables a statistical compositional analysis of thousands of particles in less than 1 h. Similar improvements are observed for atomic resolution. The discrete positions of atoms identified by the trained network allow for selective EDX sampling at these centers, thereby identifying the atomic species of the column with much-reduced sampling. Consequently, a lower sampling dose is required, enabling mapping of more delicate materials with high lateral resolution and at a high statistical confidence interval. Even though manual training is still required, this approach greatly benefits repetitive quality control tasks.

Contrastive learning of sentence representations has achieved great improvements in several natural language processing tasks. However, the supervised contrastive learning model trained on the natural language inference (NLI) dataset is insufficient to elucidate the semantics of sentences since it is prone to make a prediction based on heuristics. Herein, by using the ParsEVAL and the word overlap metric, it is shown that sentence pairs in the NLI dataset have strong syntactic similarity and propose a framework to compensate for this problem in two aspects. 1) Apply simple syntactic transformations to the hypothesis and 2) expand the objective to SupCon Loss to leverage variants of sentences. The method is evaluated on semantic textual similarity (STS) tasks and transfer tasks. The proposed methods improve the performance of the BERT-based baseline in STS Benchmark and SICK Relatedness by 1.48% and 2.2%. Furthermore, the model achieves 82.65% on the HANS benchmark dataset, to the best of our knowledge, which is a state-of-the-art performance demonstrating that our approach is effective in grasping semantics without heuristics in the NLI dataset at supervised contrastive learning. The code is available at https://github.com/whnhch/Break-the-Similarity.

Soft robots exhibit significant flexibility but normally lack stability owing to their inherent low stiffness. Current solutions for achieving variable stiffness or implementing lock mechanisms tend to involve complex structures. Additionally, passive solutions like bistable and multistate mechanisms lack spatial stable characteristics. This study presents a novel shape memory alloy (SMA) modular robot with spatially stable structure, by utilizing gooseneck as the backbone. This is the first time that a concept of spatially stable structure is proposed. When the power is off, the robot can still maintain its current posture in three-dimensional space and resist external disturbance. The SMA spring and gooseneck are characterized, elucidating the mechanism behind achieving spatial stability. Then, a controller based on the inverse kinematics is designed, and validated by experiments. The results demonstrate the structural stability of the robot. Specifically, it can withstand a maximum external force of 2.5 N (0.0875 Nm) when bent at an angle of 20° without consuming energy. Moreover, with the assistance of the SMA spring, this resistance capacity surpasses 5 N (0.175 Nm).

Automated drug delivery systems (ADDS) improve chronic disease management by enhancing adherence and reducing patient burden, particularly in conditions like type 1 diabetes, through intraperitoneal insulin delivery. However, periodic invasive refilling of the reservoir is needed in such a class of implantable devices. In previous work, an implantable ADDS with a capsule docking system is introduced for non-invasive reservoir refilling. Yet, it encounters reliability issues in manufacturing, sealing, and docking design and lacks evidence on intestinal tissue compression effects and chronic in vivo data. This work proposes an optimization of the different components featuring this ADDS. The ingestible capsule is designed, developed, and tested following ISO 13485, exhibiting high insulin stability and optimal sealing for six days in harsh gastrointestinal-like conditions. A magnetic docking system is optimized, ensuring reliable and stable capsule docking at a clinically relevant distance of 5.92 mm. Histological tests on human intestinal tissues confirm safe capsule compression during docking. Bench tests demonstrate that the integrated mechatronic system effectively docks capsules at various peristalsis-mimicking velocities. A six-week in vivo test on porcine models demonstrates chronic safety and provides hints on fibrotic reactions. These results pave the way for the further evolution of implantable ADDS.

As robotics and intelligence increasingly integrate into surgery, the pivotal role of human–robot interaction (HRI) in surgical procedures and outcomes becomes evident. However, debate rages over whether increasing robot autonomy will result in less human involvement. Some scholars assert that autonomy will reduce human participation, whereas others contend it will result in more complex interactions. To reveal the role of HRI in the evolution of autonomous surgery, this review systematically explores the HRI of robotic surgery with various levels of autonomy. The HRI is examined from both robotic science and clinical practice perspectives, incorporating relevant case studies. Two key components, intention detection and situation awareness, are especially concerned with a brief description of the interfaces and control strategies they rely on. Additional insights are drawn from analogous technologies in aviation, industrial robotics, and autonomous vehicles. The analysis suggests that HRI complexity tends to increase as the robot transitions from no autonomy to conditional autonomy and is predicted to subsequently decrease with a substantial shift in the interaction form when moving toward full autonomy. It is concluded by highlighting challenges from technical and clinical perspectives and delineating research trends in this rapidly evolving field.

In nature, gliding birds frequently execute intricate flight maneuvers such as aerial somersaults, perched landings, and swift descents, enabling them to navigate obstacles or hunt prey. It is evident that birds rely on different wing–tail configurations to accomplish a wide range of aerial maneuvers. For traditional fixed-wing unmanned aerial vehicles (UAVs), pitch control primarily comes from the tail's elevators, while adjusting flight lift and drag involves deploying wing flaps. Although these designs ensure reliable flight, they compromise the drones’ maneuverability to maintain longitudinal stability. Therefore, the study introduces a biomimetic morphing wing UAV, and presents a pitch control strategy that simultaneously engages morphing wings, ailerons, and tail elevators. The pull-up maneuver tests indicate that the proposed control method results in a pitch rate that is approximately 2.5 times greater than when using only the elevator control. A closed-loop control system for the drone is also established. The closed-loop flight experiment, which tracks a 45° pitch angle, demonstrates the effectiveness of the proposed coupled control method in adjusting the flight attitude. In addition, during cruising, the UAV employs three configurations, straight wing, forward-swept wing, and back-swept wing, to cater to different mission objectives and augment its flight capabilities.

To advance the design space of electrically-driven soft actuators, a flexible, architected soft robotic actuator is presented for motor-driven extensional motion. The actuator comprises a 3D printed, cylindrical handed shearing auxetic (HSA) structure and a deformable, internal rubber bellows shaft. The actuator linearly extends upon applying torque from a servo motor; the rubber bellows shaft is stretchable but resistant to torsional deflection, allowing it to transmit torque from the servo motor to the other end of the HSA. The high flexibility of the HSA and rubber bellows shaft enable the actuator to adaptively extend even when bent. The actuator's two components and its performance are mechanically characterized. Actuation strains of 45% elongation and a maximum blocked pushing force of about 8 N are demonstrated. The actuator's capabilities are showcased in two separate demonstrations: a crawling robot and a sensorized artificial muscle that integrates a microfluidic, liquid metal strain sensor. The architected material design approach for a robust, motor-driven soft actuator provides several unique features—including a compact form factor and ease of use—over other motorized soft robotic actuators based on HSA assemblies or cable tendon mechanisms.

Sperm morphology analysis is crucial in infertility diagnosis and treatment. However, current clinical analytical methods use either chemical stains that render cells unusable for treatment or rely on subjective manual inspection. Here, an ensemble deep-learning model is presented for classification of live, unstained human sperm using whole-cell morphology. This model achieves an accuracy and precision of 94% benchmarked against the consensus of three andrology scientists who classified the images independently. The model loses less than a 12% prediction performance even when image resolution is reduced by over sixfold. This ensures compatibility across varied clinical imaging setups. This model also provides a high certainty and robust classification of challenging images, which divided the experts. By providing a consistent, automated approach for classifying live, unstained cells using quantitative data, this model offers promising future opportunities for enhancing clinical sperm selection practices and reducing day-to-day variability in clinics.

Histopathology plays a pivotal role in medical diagnostics. In contrast to preparing permanent sections for histopathology, a time-consuming process, preparing frozen sections is significantly faster and can be performed during surgery, where the sample scanning time should be optimized. Super-resolution techniques allow imaging of histopathalogical samples in lower magnification, thus sparing scanning time. Herein, a new approach is presented to super-resolution of histopathological frozen sections, with focus on achieving better distortion measures, rather than pursuing photorealistic images that may compromise critical diagnostic information. Our deep-learning architecture focuses on learning the error between interpolated images and real images; thereby generating high-resolution images while preserving critical image details, which reduces the risk of diagnostic misinterpretation. This is done by leveraging the loss functions in the frequency domain and assigning higher weights to the reconstruction of complex, high-frequency components. In comparison with existing methods, significant improvements are obtained in terms of distortion metrics, improving the pathologist's clinical decisions. This approach has a great potential to provide faster frozen-section imaging, with less scanning, speeding up intraoperative decisions, while preserving the high-resolution details in the imaged sample.