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

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.

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.

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.

Inspired by organisms that utilize multimodal locomotion strategies to adapt to diverse environments, the development of analogous capabilities in soft robots has garnered growing attention. This review comprehensively surveys recent advances in multimodal locomotion within soft robotics. Typical locomotion modes are summarized and categorized. Furthermore, the underlying mechanisms enabling multimodal locomotion, encompassing both the integration of distinct locomotion modes and transitions between them, are discussed in detail and classified into three primary categories: active control-based, reconfiguration-based, and environment-responsive strategies. Leveraging these mechanisms, soft robots demonstrate enhanced adaptability for applications such as cross-domain transition, surface adaptation, and obstacle negotiation. Finally, key challenges in advancing the capabilities of multimodal locomotion to address real-world applications are discussed.

Non-small cell lung cancer (NSCLC) comprises the largest subtype of lung cancer with the most cases. Lung adenocarcinoma and lung squamous cell carcinoma are two NSCLC subtypes that pose challenges for accurate diagnosis using conventional methods, including histological examination and imaging, which can be slow and inconclusive. To address these concerns, RPSLearner is proposed, which combines random projection (RP) for dimensionality reduction and stacking ensemble learning to accurately predict lung cancer subtypes. Specifically, multiple independent RP matrices are first generated to project the high-dimensional RNA-seq data into a lower-dimensional space, whose features are subsequently concatenated. After that, the concatenated RP features are fed into a stack of diverse base classifiers, and integrated the predictions from base models via a deep linear layer network. Benchmarking tests on 1 333 NSCLC patients demonstrated that RPSLearner outperformed state-of-the-art approaches for lung cancer subtype classification. Specifically, RPSLearner efficiently preserved sample-to-sample distances even after significant dimension reduction, and the meta-model in RPSLearner yielded consistently higher scores than individual base models. In addition, the feature fusion method outperformed conventional score ensemble methods. We believe RPSLearner is a promising model for downstream lung cancer clinical diagnosis, and it holds the potential to be extended to subtyping of other types of cancer.

Bats species navigating dense vegetation based on biosonar must obtain sensory information about their environments from “clutter echoes”, i.e., echoes that are superpositions from many unresolved reflecting facets (e.g., leaves) with unpredictable individual waveforms. Prior results suggested that pinna deformations can aid performance in sensing tasks based on deterministic echo patterns, raising the question of whether varying pinna shapes can also have functional significance for biosonar tasks performed on clutter echoes. To test this hypothesis, this work investigates whether different pinna shapes have a consistent effect on clutter echoes despite the random nature of these signals. This is accomplished using a dedicated laboratory setup that produces large amounts of uncorrelated clutter echo data by agitating artificial foliage with fans between echo recordings. Deep learning then identifies the pinna shape that receives a given clutter echo using a data-driven classification approach that learns features directly from echoes without explicit physical modeling. A ResNet-50 achieves 97.8% overall classification accuracy for the pinna shape conformations (true-positive identifications 91.67–100%), whereas a two-dimensional convolutional neural network operating on echo spectrograms still achieves 90% accuracy. These findings demonstrate that even small pinna deformations can impart consistent effects on the clutter echoes.

Perching robots offer an effective solution to the energy limitations of small robots during long-duration missions. However, without integrated sensing capabilities, they are prone to failure in complex environments. This study presents a remora-inspired sensing suction cup to enhance adhesion reliability for robots in complex aerial–aquatic conditions. Mimicking remora fish, the design incorporates liquid metal microchannel sensors arranged at 90° intervals to monitor lip deformation, enabling real-time assessment of adhesion state and force distribution. The optimized suction cup morphology improves deformation sensitivity, while the integrated sensor system operates effectively in both aquatic and aerial environments. Performance tests demonstrate that the sensors exhibit nonlinear but repeatable responses, with 2° bending resolution and stable operation over 1,000 cycles despite minor hysteresis. Experimental results confirm that the four-directional sensor array can reflect adhesion status and horizontal force detection, validating the design's feasibility. When deployed on an aerial–aquatic robot, the system successfully enables real-time leakage detection, lateral disturbance detection, and environmental tactile sensing. This bioinspired approach enhances the environmental adaptability and operational reliability of robots, offering a robust solution for maintaining attachment in complex conditions and significantly enhances the applicability of such systems in robotic applications.

Skeletal muscles are the primary power source for voluntary limb joint motions, thus muscle deformation (MD) is vital to reflect human motions. However, most sensors can capture only 1D MD features, and are suitable only for on-land scenarios, leading to the under evaluation and under exploitation of MD sensing. This article develops a 4 × 4 soft magnetic sensor array (SMSA) to capture 3D MD distribution. Compared to solid structures, the used porous elastomer mitigates hydraulic pressure disturbances by half within 0–100-m water depth, while sensitivity increases by 10 times. The SMSA has consistent amphibious measurements and about 200 ms faster response than inertial measurement units (IMUs). Mapping between 3D magnetic flux densities and deformations of elastomers is justified by calibration errors within 1% of full ranges. Experiments justify the proposed method in multiple environments, muscles, motions, and subjects. Average gait classification accuracy is 98.73%, and phase estimation error is 2.85% when using only one SMSA, which is better than existing commercial sensors (with 82.40% and 10.39% for one IMU, and 89.06% and 6.33% for one flexible resistive sensor array). The proposed method can contribute to muscle state monitoring for human–machine interaction, rehabilitation engineering, and sports science.

Understanding rare-earth element (REE) mineralization mechanisms is essential for developing efficient separation strategies. Although the geochemical pathways that generate REE deposits are qualitatively known, quantitative links between specific conditions and mineralization outcomes remain limited. Herein, the repurpose laboratory REE hydrothermal synthesis data—originally collected for functional-materials fabrication—as a surrogate for studying mineralization with data-driven methods. The compiled 1,200+ hydrothermal reaction records and trained three machine-learning models—K-nearest neighbors (KNN), random forest (RF), and extreme gradient boosting (XGB)—to predict product elements and phases from precursors, additives, reaction conditions, and engineered features. Validation shows XGB achieves the highest accuracy. Feature importance indicates thermodynamic properties of cations and anions dominate model decisions. Correlations reveal positive relationships among precursor concentration, reaction time, pH, and temperature, consistent with classical crystallization behavior. XGB-based regressors are built to predict crystallization temperature and pH from precursor/product attributes. Performance is strongest when similar training examples exist, while accuracy declines for underrepresented reactions, notably REE carbonates and heavy-REE systems. Overall, the study shows that functional-materials datasets can illuminate REE mineralization and provide priors for exploration and processing. Expanding datasets with less-studied chemistries and conditions will improve generality and support deposit discovery and more efficient REE recovery.