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

Deterministic pseudorandom number generators used in generative artificial intelligence (GAI) models produce predictable patterns vulnerable to exploitation by attackers. Conventional defenses against the vulnerabilities often come with significant energy and latency overhead. Herein, hardware-generated true random bits from spin-transfer torque magnetic tunnel junctions (STT-MTJs) are embedded to address the challenges. A highly parallel, field-programmable gate array-assisted prototype computing system delivers megabit-per-second true random numbers, passing NIST randomness tests after in situ operations with minimal overhead. Integrating the hardware random bits into a generative adversarial network trained on CIFAR-10 reduces insecure outputs by up to 18.6 times compared to the low-quality random number generators (RNG) baseline. With nanosecond switching speed, high energy efficiency, and established scalability, the STT-MTJ-based system holds the potential to scale beyond 10⁶ parallel cells, achieving gigabit-per-second throughput suitable for large language model sampling. This advancement highlights spintronic RNGs as practical security components for next-generation GAI systems.

Interventionalist catheterization actions are essential for assessing tool navigation quality and procedural competence during interventions. Traditional assessment methods are subjective, lack immediate feedback, and limit timely performance improvement. To address these limitations, this study introduces a deep-learning framework designed to systematically analyze catheterization action data, address inherent class imbalances, and enable real-time action recognition. First, the proposed framework leverages advanced generative models to augment minority action classes, thus enhancing data representation and ensuring accurate recognition of catheterization actions. The six generative models utilized in this study undergo rigorous evaluation, achieving high fidelity with average precision and F1-scores exceeding 94% across all models except CTGAN. Second, a convolutional neural network (IAR-Net) tailored to recognize seven distinct catheterization actions is developed. Evaluated using the augmented dataset, IAR-Net achieves an accuracy of 98.9%, surpassing current benchmarks. Comparative analysis with state-of-the-art machine learning and transformer-based models designed for tabular data confirms IAR-Net's performance and robustness in recognizing catheterization actions. Lastly, interpretability methods are incorporated to elucidate the model's decision-making process, improving understanding and increasing the trustworthiness of predictions. These outcomes offer a promising avenue for enhancing trainee assessment and training protocols, thereby accelerating the acceptance and integration of robot-assisted endovascular systems into clinical practice.

This study presents a new method for measuring the effective stiffness of curved actuators. Actuators are loaded into tension, and analytical mechanical equilibrium formulations are used to determine the stress along the actuator. A new mechanical metric, Shape Actuation Modulus (SAM), defines the effective stiffness of the actuator during loading as the ratio of stress change to radius of curvature change. Conductive polylactic-acid shape-memory actuators are produced to benchmark this novel methodology. These actuators display a linear behavior between 25 and 50 mm radius of curvature with SAM of 3.8±0.9 MPa at 50 mm. The interval on which the radius of curvature to stress relationship is linear can be controlled by choosing the radius of curvature of the hinge. For instance, SAM calculation with R² > 0.97 was achieved in ranges of [22.7;79.6] mm and [16.4;51.5]mm for starting radius of curvature of 23.5±0.7 mm and 17.2±0.6 mm, respectively. Hence, the new technique proposed provides guidelines to design actuators. Finally, a comparison of bio-composite actuators made of the same material was conducted. The hygromnemic actuators tested displayed a stiffness more than one order of magnitude larger than the hygromorphic ones for the range of radius of curvature [20;100]mm.

This study investigates the application of Riemannian geometry-based methods for brain decoding using invasive electrophysiological recordings. While Riemannian geometry has been successfully applied in noninvasive settings, its utility for invasive datasets, which are typically smaller and scarcer, remains less explored. Herein, a minimum distance to mean (MDM) classifier is proposed using a Riemannian geometry approach based on covariance matrices extracted from intracortical local field potential (LFP) recordings across various regions during different brain state dynamics. For benchmarking, the performance of the approach is evaluated against convolutional neural networks (CNNs) and Euclidean MDM classifiers. The results indicate that the Riemannian geometry-based classification not only achieves a superior mean F1 macro-averaged score across different channel configurations but also requires up to two orders of magnitude less computational training time. Additionally, the geometric framework reveals distinct spatial contributions of brain regions across varying brain states, suggesting a state-dependent organization that traditional time series-based methods often fail to capture. The findings align with previous studies supporting the efficacy of geometry-based methods and extend their application to invasive brain recordings, highlighting their potential for broader clinical use, such as brain-computer interface applications.

Kirigami, or “jianzhi” in Chinese, is an art in paper-cutting. Using simple tools like scissors, artisans transform paper into intricate designs featuring flowers, animals, or characters (e.g., “囍”). Nowadays, kirigami has emerged as a particularly promising design strategy in engineering. This method involves creating systematic cut patterns on thin, planar sheets, which enables complex mechanical responses by changing dimensions, thereby offering innovative solutions for the development of metamaterials, soft actuators, and robotic systems. The concept of the integration of ancient art and modern science and technology has injected vitality into the development of many disciplines and become the forefront of interdisciplinary research. This review provides a systematic review of recent progress on the design of kirigami and applications in diverse robotic prototypes. The kirigami begins by classifying into two categories from a compliant mechanism perspective, and then it examines the distinctive mechanical properties that altered by cut patterns, followed by reviewing the design of the two types of kirigami. Next, the kirigami-inspired kinematic metamaterials is examined. Finally, applications in soft actuators and robotic systems is demonstrated. The integration of design methods, fabrication techniques, materials research, mechanics modeling, and control systems will further advance this emerging field.

Neuromorphic devices, inspired by the human brain's efficiency and adaptability, hold great potential for artificial intelligence (AI) hardware to overcome the limitations of traditional von Neumann architecture. As a subclass, multimodal and multifunctional neuromorphic devices have recently gained a lot of attention due to their advantages in in-sensor computing and sophisticated behaviors. In this review, recent advances in materials, device structures, and applications in this field are systematically presented. It includes optical, electrical, mechanical, and chemical sensing in multimodal neuromorphic device, which enable in-sensor computing to minimize energy consumption and enhance real-time decision-making. The materials applied in this field such as phase-change, 2D materials, and ferroelectrics are summarized for their roles in achieving synaptic plasticity, nonvolatile memory for multifunctional neuromorphic devices. Structural innovations, including reconfigurable, multi-terminal, and 3D-integrated designs, further optimize parallel processing and multifunctional integration. Besides, application scenarios of multimodal and multifunctional neuromorphic devices and their advantages for improving the efficiency of AI are reviewed. Finally, challenges in material stability and commercialization are discussed, it emphasizes the need for interdisciplinary efforts to bridge the gap. This review provides critical insights and future directions for developing brain-inspired, energy-efficient AI hardware.

Sensory feedback systems allow soft robots to interact and respond to their environment through embedded or external sensors. These sensors often rely on electronic components for signal interpretation and processing, which increases system complexity, reduces robustness under hazardous conditions, and limits the adaptability of the robots. Reducing complexity and improving adaptability in soft robots requires the development of electronics-free control systems. A 3D-printed, electronics-free sensory system is integrated into a six-legged soft robot, increasing its adaptability by enabling obstacle detection and directional change of locomotion using pneumatic logic gates. Pneumatic systems enable smooth, nature-like movements and can operate safely in environments where electronics might fail. The results show rapid sensor response times (1.41–1.52 s), low required input forces (1.07–4.62 N) of the sensor, and walking speeds up to 0.17 body lengths per second. Operating at 225 kPa with 13.64 l_n min⁻¹ of compressed air in tethered mode, the robot also functions autonomously with a CO₂ cartridge. Integrated pneumatic grippers enhance their utility for object retrieval. The design achieves a new level of autonomy and versatility, advancing electronics-free control systems, while maintaining cost efficiency. These findings lay the foundation for future innovations in increasingly autonomous electronic-free soft robots.

Bacterial cellulose (BC) is an emerging smart material, synthesized through microbial fermentation of environmentally friendly substrates, including organic waste. When functionalized with ionic liquids (ILs) and coated with conductive polymers, BC forms soft, sustainable, and electroactive composites, making it suitable for sensors in soft robotics, wearable, biomedical, and environmental monitoring applications. However, modeling frameworks for BC–IL sensors are still lacking, hindering their integration into real-world applications. To bridge this gap and support smart material design, we propose a novel first-principle white-box modeling framework is proposed that couples a 2D finite element method (FEM) for mechanical deformation with 1D FEM sub-models for ion transport and voltage generation. Specifically, this work introduces the first dual-carrier multiphysics model for mechanoelectric transduction in BC–IL sensors. The model, experimentally calibrated and validated, resolves the spatio-temporal dynamics of mechanical deformation and dual-ion transport, including diffusion, electromigration, and advection. By explicitly incorporating the transport and interaction of both cations and anions, previously neglected in smart-sensors modeling, the proposed strategy provides a foundational simulation framework for the scalable, rapid, and intelligent design of next-generation biodegradable and multifunctional smart sensors, advancing the integration of green materials into intelligent systems.

Active composite (AC) plates, composed of active and passive materials, can undergo complex shape transformations when stimulated. Leveraging 4D printing—which combines additive manufacturing with stimuli-responsive materials—digitally encoded design patterns offer flexibility in shape morphing. However, performing inverse design, i.e., determining the pattern to achieve a desired shape, remains challenging due to the vast design space. Recently, machine learning (ML) has been applied to inverse design tasks with promising results. Nevertheless, these approaches require large datasets, and even then, inverse design remains difficult, often demanding multiple strategies and trials to obtain optimal results. To address these challenges, this work introduces an iterative data curation strategy combined with transfer learning. This method ensures that newly curated data is nonredundant and distinct from existing datasets, reducing the required training data by a factor of eight while maintaining performance. Additionally, ML models are integrated with a genetic algorithm (ML-GA) to further fine-tune the generated design patterns. The results show that ML-GA enhances accuracy in achieving the desired shape while reducing computational effort. This framework offers an efficient and scalable approach for inverse design, reducing data needs and improving performance, making it a valuable tool for AC plate design and 4D printing.

This article introduces a novel approach for learning robotic skills from human demonstrations, Elastic Fast Marching Learning (EFML). This method seamlessly integrates concepts from Elastic Maps, a Learning from Demonstration (LfD) method based on a mesh of springs, and Fast Marching Learning (FML), an LfD method relying on light-based velocity fields. The combination of these methods allows a robot to generate reproductions with multiple properties, such as the ability to be trained with single or multiple demonstrations, adapt to any number of initial, final, or via-point constraints, and generate smooth reproductions. This algorithm not only improves the efficiency of the two previous methods but also enhances capabilities beyond prior works, as the new method operates in both orientation space and task space, which neither of the original methods were able to previously. EFML exhibits advantages in terms of precision, smoothness, and speed. This approach has been validated with various comparisons in simulated environments, evaluating its performance against Elastic Maps, FML, and other contemporary LfD methods using benchmarks such as the LASA and RAIL datasets. In addition, real-world experiments involving tasks like pouring, where both position and orientation are crucial, have been conducted to validate the approach.