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

{"title":"Design, Modeling, and Control of a Soft Robotic Diaphragm-Assist Device in a Respiratory Simulator","authors":"Diego Quevedo-Moreno,&nbsp;Sang-Yoep Lee,&nbsp;Jonathan Tagoe,&nbsp;Vishnu Emani,&nbsp;Jean Bonnemain,&nbsp;Ellen T. Roche","doi":"10.1002/aisy.70070","DOIUrl":"10.1002/aisy.70070","url":null,"abstract":"<p><b>Soft Robotic Diaphragm-Assist Device</b></p><p>In article number 2401087, Diego Quevedo-Moreno, Ellen T. Roche, and colleagues present a soft robotic diaphragm-assist device using fabric-based pneumatic actuators with a 2-step control system for optimized synchronization and support. The system detects breathing initiation to trigger assistance and regulates pressures for inhalation augmentation. Validation is conducted on a custom-built respiratory simulator. This research advances soft robotics in respiratory care, laying the groundwork for next-generation therapeutic devices for diaphragm dysfunction.\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure></p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 7","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.70070","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Soft Aerial Robots: The Development of Adaptive, Multi-Functional and Multi-Terrain Aerial Robots","authors":"P. H. Nguyen,&nbsp;S. Hamaza,&nbsp;P. Chirarattananon,&nbsp;Y. Chen,&nbsp;M. Kovac","doi":"10.1002/aisy.202500658","DOIUrl":"10.1002/aisy.202500658","url":null,"abstract":"&lt;p&gt;Classical aerial robots have demonstrated precise control and high speeds through the use of highly optimized rigid body structures. However, when compared to their biological flying counterparts, they still struggle to match performance parameters in energy efficiency, multi-functionality, multi-terrain accessibility, scalability (to micro-scale), agility, close contact interaction, robustness, and maneuverability in cluttered environments.&lt;/p&gt;&lt;p&gt;The recent emergence of soft aerial robotics has seen an increased interest in the utilization of smart and functional materials to develop aerial robots with innovative and morphologically adaptive structures. Through the interpretation and study of biological flyers, soft aerial robots leverage their morphological features, to exploit dynamic and biomechanical effects to achieve better aerodynamic performance, interact safely with unknown and cluttered environments, sensing itself and its surroundings better, and expand their range of capabilities. Taking another bold step towards autonomous operation in real-world environments.&lt;/p&gt;&lt;p&gt;We organized this special issue to highlight top-tier work of leading researchers in the field of bio-inspired, reconfigurable, adaptive, and soft aerial robotics, in order continue the ongoing conversation about the current state of the art, as well as technical and conceptual obstacles, and to examine the difficulties and prospects for the future of soft aerial robotics.&lt;/p&gt;&lt;p&gt;In this issue, we observe several research thrusts currently in focus. For example, &lt;b&gt;De Petris et al&lt;/b&gt;. demonstrate how &lt;b&gt;morphological compliance, embedded sensing, and collision resilience&lt;/b&gt; converge in Morphy. A quadcopter developed with sensorized elastic joints that withstand high-speed impacts, provide real-time angle deflection feedback, and compress to squeeze through narrow openings.&lt;sup&gt;[&lt;/sup&gt;&lt;span&gt;&lt;sup&gt;1&lt;/sup&gt;&lt;/span&gt;&lt;sup&gt;]&lt;/sup&gt; &lt;b&gt;Abazari et al.&lt;/b&gt; investigated optimal compliance in MAVs for collision resilience. Their tests showed that softer propeller guards led to more elastic collisions without improving energy dissipation, while softening the inner frame enhanced energy damping and extended collision time, reducing impact accelerations.&lt;sup&gt;[&lt;/sup&gt;&lt;span&gt;&lt;sup&gt;2&lt;/sup&gt;&lt;/span&gt;&lt;sup&gt;]&lt;/sup&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Kubota et al&lt;/b&gt;. explored a &lt;b&gt;learning-based wind classification method using multiple strain sensors&lt;/b&gt; that detect wing deformation in flexible wings on a hummingbird-mimetic mechanism. The setup highlighted high accuracies in distinguishing wind direction under varying flow conditions. This highlights the potential of wing strain sensing for enabling quick responses to flow disturbances in aerial robots.&lt;sup&gt;[&lt;/sup&gt;&lt;span&gt;&lt;sup&gt;3&lt;/sup&gt;&lt;/span&gt;&lt;sup&gt;]&lt;/sup&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Shape morphing to extend the flight envelope of aerial robots&lt;/b&gt; was another pivotal focus. &lt;b&gt;Tang et al&lt;/b&gt;. developed PairTilt, a quadcopter with a two pair of tiltable, coupled rotors that minimizes gyroscopic ","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 7","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202500658","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DuckyDog: An Erect Amphibious Robot with Variable-Stiffness Legs and Passive Fins","authors":"Yilin Wang,&nbsp;Felix Pancheri,&nbsp;Tim C. Lueth,&nbsp;Yilun Sun","doi":"10.1002/aisy.70068","DOIUrl":"10.1002/aisy.70068","url":null,"abstract":"<p><b>Amphibious Robots</b></p><p>Inspired by nature, bionic robots are brought to life through human creativity, returning to the wild as enchanting spirits. Meet DuckyDog, a vibrant fusion of technology and nature, a quadruped amphibious robot using erect posture, is proposed with dog-inspired tendon-driven compliant legs for walking and paddling, a duck-inspired body for buoyancy, and passive fins to increase propulsion. More details can be found in article number 2500267 by Yilun Sun and co-workers.\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure></p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 7","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.70068","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Linear and Tree-Based Intelligent Investigation of Cross-Domain Housing Features to Enhance Energy Efficiency","authors":"Hafiz Muhammad Shakeel,&nbsp;Shamaila Iram,&nbsp;Hafiz Muhammad Athar Farid,&nbsp;Richard Hill","doi":"10.1002/aisy.202400939","DOIUrl":"10.1002/aisy.202400939","url":null,"abstract":"<p>Energy efficiency is a critical concern in built environment. Identifying key features that drive energy consumption is essential for optimizing building performance. Traditionally, studies have focused on single-domain datasets. These approaches overlook the potential insights gained from integrating data across different domains. This research addresses this gap using a cross-domain dataset that includes building characteristics, energy usage, and environmental factors. Feature selection techniques, including filter methods (correlation, mutual information), wrapper methods (RFE), embedded methods (Lasso, Random Forest, and gradient boosting), and dimensionality reduction are used to identify the most significant features contributing to the energy efficiency of residential properties. These techniques identify the most significant features influencing energy consumption. The findings show that cross-domain features like energy consumption, CO₂ emissions, and heating cost play a key role in predicting energy performance. By integrating data from multiple domains, the feature selection process reveals areas for energy optimization that are previously overlooked in single-domain studies. The results provide valuable insights for energy consultants, building managers, and policymakers aiming to enhance energy efficiency in residential buildings. This research highlights the importance of cross-domain data integration and offers a robust framework for feature selection. Ultimately, it contributes to more effectiveenergy-saving strategies and sustainable building practices.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 8","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://advanced.onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400939","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MedVH: Toward Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context.","authors":"Zishan Gu, Jiayuan Chen, Fenglin Liu, Changchang Yin, Ping Zhang","doi":"10.1002/aisy.202500255","DOIUrl":"https://doi.org/10.1002/aisy.202500255","url":null,"abstract":"<p><p>Large vision language models (LVLMs) have achieved superior performance on natural image and text tasks, inspiring extensive fine-tuning research. However, their robustness against hallucination in clinical contexts remains understudied. We propose the Medical Visual Hallucination Test (MedVH), a novel evaluation framework assessing hallucination tendencies in both medical-specific and general-purpose LVLMs. MedVH encompasses six tasks targeting medical hallucinations, including two traditional tasks and four novel tasks formatted as multi-choice visual question answering and long response generation. Our extensive experiments with six evaluation metrics reveal that medical LVLMs, despite promising performance on standard medical tasks, are particularly susceptible to hallucinations-often more so than general models. This raises significant concerns about domain-specific model reliability. For real-world applications, medical LVLMs must accurately integrate medical knowledge while maintaining robust reasoning to prevent hallucination. We explore mitigation methods without model-specific fine-tuning, including prompt engineering and collaboration between general and domain-specific models. Our work provides a foundation for future evaluation studies. The dataset is available at PhysioNet: https://physionet.org/content/medvh.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12363988/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144982104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evolutionary Codesign and Fabrication of Tensegrity Joints with Integrated Pneumatic Artificial Muscles","authors":"Jan Petrš,&nbsp;Ryota Kobayashi,&nbsp;Fuda van Diggelen,&nbsp;Hiroyuki Nabae,&nbsp;Koichi Suzumori,&nbsp;Dario Floreano","doi":"10.1002/aisy.202500310","DOIUrl":"10.1002/aisy.202500310","url":null,"abstract":"<p>Tensegrity robotic joints, inspired by the musculoskeletal systems of vertebrate animals, have gained interest due to their unique interplay of tension and compression forces, offering a high strength-to-weight ratio and inherent adaptability. However, their use in legged and grasping applications remains challenging. A key challenge is striking the right balance between high compliance, which can undermine stability and control, and high stiffness, which can restrict essential movement and demand more powerful actuators. This study presents a tensegrity-inspired spine-like joint that integrates thin McKibben pneumatic artificial muscles and rubber cords directly into its tensile network. The artificial muscles enable active joint bending while also serving as tensile elements. The rubber cords counteract these forces, storing elastic energy to facilitate smooth recovery to the original position. The joint's topology design is primarily influenced by the artificial muscles’ limited 20% contraction. To optimize the balance between range of motion, payload capacity, and structural stability, the joint's geometry is refined through an evolutionary algorithmic form-finding process. Two generated joints are integrated into two functional robotic applications: a crawling robot and a gripper, showcasing their adaptability for diverse robotic applications.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 9","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://advanced.onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202500310","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145111224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Wearable Pneumatic Soft Physiotherapy Device for Shoulder and Neck Acupoint Massage","authors":"Zixin Huang,&nbsp;Chengsong Yu,&nbsp;Junjie Lu,&nbsp;Peng Huang,&nbsp;Liu Wang","doi":"10.1002/aisy.202500365","DOIUrl":"10.1002/aisy.202500365","url":null,"abstract":"<p>The high reliance on traditional Chinese medicine (TCM) knowledge and practical skills has led to prolonged training cycles for therapists and a significant talent shortage, posing a severe challenge to the standardization of TCM physiotherapy in rehabilitation. Meanwhile, most physiotherapy robots based on rigid robotics technology suffer from insufficient safety and adaptability, resulting in unsatisfactory treatment effects. This paper presents a novel wearable pneumatic soft physiotherapy device, designed to achieve high-safety and personalized physiotherapy for shoulder and neck acupoint massage. The device integrates four soft massage actuators, four embedded thin-film stress sensors, two miniature airflow sources, and a power supply system, enhancing its portability. Additionally, a hybrid control strategy combining feedforward inverse compensation and PID feedback is proposed to regulate and customize the therapy intensity on human acupoints. Experimental results demonstrate that the developed device can apply therapeutic intensities ranging from 0 to 3.45 N to human acupoints, effectively adapting to the human shoulder and neck region to achieve good wearing comfort, and performing safe acupoint massage with customized physiotherapy intensities. This study explores and realizes the integration of emerging soft robotics technology with TCM, providing a paradigm for the development of more soft physiotherapy devices.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 9","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://advanced.onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202500365","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145110833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Harnessing Discrete Differential Geometry: A Virtual Playground for the Bilayer Soft Robots","authors":"Jiahao Li,&nbsp;Dezhong Tong,&nbsp;Zhuonan Hao,&nbsp;Yinbo Zhu,&nbsp;Hengan Wu,&nbsp;Mingchao Liu,&nbsp;Weicheng Huang","doi":"10.1002/aisy.202500141","DOIUrl":"10.1002/aisy.202500141","url":null,"abstract":"<p>Soft robots have garnered significant attention due to their promising applications across various domains. A hallmark of these systems is their bilayer structure, where strain mismatch caused by differential expansion between layers induces complex deformations. Despite progress in theoretical modeling and numerical simulation, accurately capturing their dynamic behavior, especially during environmental interactions, remains challenging. This study presents a novel simulation environment based on the discrete elastic rod (DER) model to address the challenge. By leveraging discrete differential geometry, the DER approach offers superior convergence compared to conventional methods like finite element method, particularly in handling contact interactions—an essential aspect of soft robot dynamics in real-world scenarios. The simulation framework incorporates key features of bilayer structures, including stretching, bending, twisting, and interlayer coupling. This enables the exploration of a wide range of dynamic behaviors for bilayer soft robots, such as gripping, crawling, jumping, and swimming. The insights gained from this work provide a robust foundation for the design and control of advanced bilayer soft robotic systems.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 9","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://advanced.onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202500141","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145110754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DBF-Net: A Deep Bidirectional Fusion Network for 6D Object Pose Estimation with Sparse Linear Transformer","authors":"Xuan Fan,&nbsp;Tao An,&nbsp;Hongbo Gao,&nbsp;Tao Xie,&nbsp;Lijun Zhao,&nbsp;Ruifeng Li","doi":"10.1002/aisy.202401001","DOIUrl":"10.1002/aisy.202401001","url":null,"abstract":"<p>6D object pose estimation, a critical component in computer vision and robotics domains, involves determining the 3D location and orientation of an object relative to a canonical reference frame. Recently, the widespread proliferation of RGB-D sensors has precipitated a marked increase in interest towards 6D pose estimation leveraging RGB-D data. A deep bidirectional fusion network is developed, DBF-Net, achieving efficient yet accurate 6D object pose estimation. Specifically, a sparse linear Transformer (SLT) with linear computation complexity is introduced to effectively leverage cross-modal semantic resemblance during the feature extraction stage, such that it fully models semantic associations between various modalities and efficiently aggregates the globally enhanced features of each modality. Once acquiring two feature representations from two modalities, a feature balancer (FB) based on SLT is proposed to adaptively reconcile the importance of these feature representations. Leveraging the global receptive field of SLT, FB effectively eliminates the ambiguity induced by visual similarity in appearance representation or depth missing of reflective surfaces in geometry representations, thereby enhancing the generalization ability and robustness of the network. Experimental results demonstrate that DBF-Net surpasses current state-of-the-art works by nontrivial margins across multiple benchmarks. The code is available at https://github.com/Mrfanxuan/dbf_net.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 8","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://advanced.onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202401001","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Model-Free Deep Reinforcement Learning with Multiple Line-of-Sight Guidance Laws for Autonomous Underwater Vehicles Full-Attitude and Velocity Control","authors":"Chengren Yuan,&nbsp;Changgeng Shuai,&nbsp;Zhanshuo Zhang,&nbsp;Jianguo Ma,&nbsp;Yuan Fang,&nbsp;YuChen Sun","doi":"10.1002/aisy.202400991","DOIUrl":"10.1002/aisy.202400991","url":null,"abstract":"<p>Autonomous underwater vehicles (AUVs) are increasingly utilized, driving the need for enhanced autonomy. Conventional proportional–integral–derivative (PID) algorithms require frequent control parameter adjustments under varying voyage conditions, which increases operational and experimental costs. To address this issue, a multiple line-of-sight guidance law integrated with a deep reinforcement learning control framework is proposed. This framework enables seamless switching among guidance modes, such as waypoint following, path following, and trajectory tracking, to achieve optimal attitude control. For comprehensive control of roll, pitch, yaw, and longitudinal velocity, an augmented-twin delayed deep deterministic policy gradient (A-TD3) algorithm streamlines the training of the control agent. It enables adaptation to large-range attitude variations using small-scale training data, thereby reducing computational costs for diverse missions. Simulations demonstrate the efficacy of the proposed approach: A-TD3 improves training speed by 30.8% while mitigating issues such as excessive rudder motion, poor operability, and high energy consumption across different missions. The attitude control experiments on the X-AUV prototype validate that A-TD3's control performance with PID method.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 8","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://advanced.onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400991","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}