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

{"title":"Uncontrolled Learning: Codesign of Neuromorphic Hardware Topology for Neuromorphic Algorithms","authors":"Frank Barrows,&nbsp;Jonathan Lin,&nbsp;Francesco Caravelli,&nbsp;Dante R. Chialvo","doi":"10.1002/aisy.202400739","DOIUrl":"10.1002/aisy.202400739","url":null,"abstract":"<p>Neuromorphic computing has the potential to revolutionize future technologies and our understanding of intelligence, yet it remains challenging to realize in practice. The learning-from-mistakes algorithm, inspired by the brain's simple learning rules of inhibition and pruning, is one of the few brain-like training methods. This algorithm is implemented in neuromorphic memristive hardware through a codesign process that evaluates essential hardware trade-offs. While the algorithm effectively trains small networks as binary classifiers and perceptrons, performance declines significantly with increasing network size unless the hardware is tailored to the algorithm. This work investigates the trade-offs between depth, controllability, and capacity—the number of learnable patterns—in neuromorphic hardware. This highlights the importance of topology and governing equations, providing theoretical tools to evaluate a device's computational capacity based on its measurements and circuit structure. The findings show that breaking neural network symmetry enhances both controllability and capacity. Additionally, by pruning the circuit, neuromorphic algorithms in all-memristive circuits can utilize stochastic resources to create local contrasts in network weights. Through combined experimental and simulation efforts, the parameters are identified that enable networks to exhibit emergent intelligence from simple rules, advancing the potential of neuromorphic computing.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 7","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400739","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681003","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":"A Study on Optimal Data Bandwidth of Recurrent Neural Network–Based Dynamics Model for Robot Manipulators","authors":"Seungcheon Shin,&nbsp;Minseok Kang,&nbsp;Jaemin Baek","doi":"10.1002/aisy.202400879","DOIUrl":"10.1002/aisy.202400879","url":null,"abstract":"<p>In this article, a recurrent neural network (RNN)-based learning method is propdosed for achieving the overall dynamic model of robot manipulators. Several sections, e.g., data acquisition, learning model, hidden layers, nodes, activation function, and data bandwidth, are designed to make the RNN-based learning method establish the overall dynamic model of the robot manipulators. The proposed method has a key point that the optimal data bandwidth can be obtained by the loss function and its derivative in the robot manipulators. Since the data bandwidth is set to be effective in learning process, it helps to provide high learning hit rate while significantly reducing time-consuming tasks caused by trial and errors in any robot manipulators. From these benefits, the proposed method offers a compact form and simplicity so that it can produce the convenience of practicing engineers in industrial fields. The effectiveness of the proposed one is verified through experiments with three scenarios, which is compared with that of the original data bandwidth in a real robot manipulator.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 8","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://advanced.onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400879","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881188","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":"Real-Time Motion Generation for Robot Manipulators in Complex Dynamic Environments","authors":"Tianyu Zhang,&nbsp;Hongguang Wang,&nbsp;Peng Lv,&nbsp;Xin'an Pan,&nbsp;Daqian Wang,&nbsp;Bingbing Yuan,&nbsp;Huiyang Yu","doi":"10.1002/aisy.202400738","DOIUrl":"10.1002/aisy.202400738","url":null,"abstract":"<p>Motion generation in human–robot shared workspaces often faces challenges such as discontinuous movement and slow responses. To address these challenges, a real-time motion generation method for robot manipulators in complex dynamic environments is proposed. The method autonomously generates safe trajectories and significantly enhances path smoothness and reaction time. An online minimum distance calculation algorithm between human and robot manipulators is developed via an inertial measurement unit-based motion capture system. The algorithm employs a unified geometric representation of the “human–robot–environment” model using superquadric surfaces. It introduces a closed-form Minkowski sum-based minimum distance method for efficient calculations. Additionally, a collision-free motion generator is proposed that integrates global planning with local control, where the controller simultaneously considers all minimum distances, enhancing motion continuity and human–robot safety. Experiments on robot-manipulator-assisted aviation refueling are conducted. The results demonstrate that the method performs tasks safely and efficiently in complex dynamic environments, with notable improvements in path smoothness and reaction time.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 7","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400738","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144680993","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":"Design and Control of Dual-Body Negative Pressure Ground-Wall Transition Robot","authors":"Huan Shen,&nbsp;Kai Cao,&nbsp;Jiajun Xu,&nbsp;Wenjun Yan,&nbsp;Xuefei Liu,&nbsp;Huan Wang,&nbsp;Youfu Li,&nbsp;Linsen Xu,&nbsp;Aihong Ji","doi":"10.1002/aisy.202400467","DOIUrl":"10.1002/aisy.202400467","url":null,"abstract":"<p>This article presents a novel dual-body negative-pressure ground-wall transition robot (DNPTR) aimed at expanding the application scenarios of climbing robots to meet the functional requirements of obstacle traversal and wall transition in high-altitude operations. As a typical representative of highly nonlinear and multivariable strongly coupled systems, the wall transition actions of the DNPTR are analyzed and planned based on the mechanical structure characteristics. Subsequently, unified kinematic and dynamic models of the bipedal negative-pressure climbing robot are established. To improve the automation and ensure safe, efficient operation of climbing robots, effective trajectory tracking control for the DNPTR is crucial. Addressing challenges such as model parameter uncertainties and external disturbances, this study proposes an adaptive trajectory tracking control method based on a radial basis function neural network. The method integrates a boundary layer with an improved exponential reaching law, forming a non-singular terminal sliding mode control strategy. Using Lyapunov theory, the global asymptotic stability of the system is verified. Both simulation and experimental results demonstrate that this approach achieves faster convergence and effectively suppresses oscillations during trajectory tracking. This research is of practical importance, offering valuable guidance for the design of high-accuracy, robust trajectory-tracking controllers for dual-body climbing robots.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 4","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400467","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143809442","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":"An Optoelectronic Memristor Based on Proton-Involved Photoreduction for Bimodal Sensing, Memory, and Processing","authors":"Qiaoling Tian,&nbsp;Xinyu Sui,&nbsp;Xiaoning Zhao,&nbsp;Ya Lin,&nbsp;Zhongqiang Wang,&nbsp;Ye Tao,&nbsp;Haiyang Xu,&nbsp;Yichun Liu","doi":"10.1002/aisy.202400968","DOIUrl":"10.1002/aisy.202400968","url":null,"abstract":"<p>Advanced devices and systems with integrated sensing, memory, and processing functionalities similar to those of the human nervous system are highly desirable for efficient artificial intelligence applications. In this study, an optoelectronic memristor with integrated bimodal sensing, memory, and processing based on graphite oxide (GO)/titanium dioxide (TiO₂) nanocomposite is presented. The resistive switching behavior of the memristor is based on proton-involved photoreduction, and the memristor exhibits humidity-dependent optical resistive switching and synaptic behaviors similar to an artificial optoelectronic synapse. The plasticity of the artificial synapse can be further modulated by a heterosynapse with an external bias caused by electric field-driven oxygen migration. These features equip the artificial synapse with not only a combined light/humidity information sensing and memory but also contrast enhancement and attention-driven functionalities similar to those of the human visual memory system. Moreover, as a proof of concept, a sensory–motion system is constructed, which sends the synaptic feedback of the optoelectronic memristor to direct responses in a robotic arm. This work could provide a fundamental unit for the future development of perception systems in efficient humanoid robots.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 7","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400968","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681365","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":"A Robotic Prosthetic Hand for Computer Mouse Operations","authors":"Ziming Chen,&nbsp;Yiming He,&nbsp;Boao Li,&nbsp;Huasong Min,&nbsp;Fuchun Sun,&nbsp;Shuguang Li,&nbsp;Bin Fang","doi":"10.1002/aisy.202500126","DOIUrl":"10.1002/aisy.202500126","url":null,"abstract":"<p>Individuals with upper limb amputation face significant difficulty in operating standard computer peripherals with their prostheses, particularly the mouse, due to the constraints imposed by current prosthetic hand designs and the irregular shape of the computer mouse. This work introduces a soft myoelectric prosthesis system for operating different physical computer mouses. The proposed prosthesis has two tendon-driven soft fingers and three fin-ray fingers. It enables an enveloping grasp of the computer mouse and facilitates diverse finger-based clicking and scrolling operations. In addition, a mapping between the hand movements (myoelectric signals) and the computer mouse operations is created by combining a neural network classifier and a post-processing algorithm. Herein, the proposed system's performance is evaluated through a series of cursor control tasks involving both the able-bodied and amputee participants. In the experimental results, it is shown that the proposed soft prosthesis system effectively enables individuals with transradial amputation to operate a physical computer mouse using their residual limbs. Compared to a traditional cursor control method based on surface electromyography, the participants exhibit improved task performance (shorter completion time and higher throughput) and improved user experience (reduced muscle use and higher questionnaire scores).</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 5","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202500126","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144100508","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":"Spatial–Texture Hybrid MRI Model for Orbital Lymphoma Typing","authors":"Lunhao Li,&nbsp;Lai Wei,&nbsp;Jiahao Shi,&nbsp;Guangtao Zhai,&nbsp;Menghan Hu,&nbsp;Yixiong Zhou","doi":"10.1002/aisy.202400595","DOIUrl":"10.1002/aisy.202400595","url":null,"abstract":"<p>The ability to distinguish between mucosa-associated lymphoid tissue (MALT) and non-MALT orbital lymphomas aids ophthalmologists in opting for either conservative or aggressive treatment strategies. Radiographic assessment is a noninvasive approach to diagnose orbital lesions. This study aims to develop a hybrid model leveraging magnetic resonance imaging scans to discern between MALT and non-MALT orbital lymphomas. The occupation of the tumor alters the relative positions of structures in the orbit. Hence, for the first time, the relative spatial positional features are extracted between different orbital structures and the tumor, complemented by the texture characteristics of the tumor area, to perform hybrid modeling. To validate this idea, 114 orbital lymphoma patients were are included. Statistical analysis reveals significant differences between the two groups in terms of four spatial features (lymphoma lesion, eyeball, inferior rectus, and optic nerve) and two texture features (angular second moment and contrast). The accuracy of the classifier based on spatial, texture, and hybrid features is 84.7, 83.1, and 88.3%, respectively. The innovative hybrid model offers a supportive approach for the differentiation of MALT and non-MALT orbital lymphomas, enhancing the clinical decision-making process. To facilitate the use of this hybrid model, a web-based diagnostic tool has been launched at https://ads.testop.top.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 5","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400595","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144100509","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":"Versatile Rigid-Flexible Coupling Modules: Enhancing Soft Origami Structures with Cable-Driven Parallel Mechanisms","authors":"Ji Wang,&nbsp;Hao Yang,&nbsp;Jie Zhang,&nbsp;Houde Liu,&nbsp;Yanbin Zhong,&nbsp;Yunge Hu,&nbsp;Yanbo Liu,&nbsp;Chongkun Xia,&nbsp;Jianing Wu","doi":"10.1002/aisy.202401008","DOIUrl":"10.1002/aisy.202401008","url":null,"abstract":"<p>Soft robots have garnered significant attention due to their adeptness in addressing challenges that traditional rigid robots struggle to effectively manage, including adaptability to unstructured environments and safe human–robot interactions. However, these modular soft robots always show limitations in coping with application requirements due to the defects of their building blocks, including limited motion patterns, poor repetitive positioning accuracy, and weak load-bearing capacity. Herein, a rigid parallel structure on the exterior of a soft origami structure is introduced, developing a rigid-flexible coupling building block. In this combined theoretical and experimental study, the geometric parameters to realize the coupling synergy between the two structures in terms of kinematics are adapted. Then, diverse experiments are conducted to characterize the performance of this building block, indicating that this building block not only has all basic motion patterns (i.e., contraction Δ<i>H</i>_max = 30.78 mm, bending <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mi>θ</mi>\u0000 <mrow>\u0000 <mtext>max</mtext>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$left(thetaright)_{text{max}}$</annotation>\u0000 </semantics></math> = 59.96°, and twisting <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mi>φ</mi>\u0000 <mrow>\u0000 <mtext>max</mtext>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$left(varphiright)_{text{max}}$</annotation>\u0000 </semantics></math> = 33.67°) but also exhibits high repeatable positioning accuracy and strong load-bearing capacity. Based on this building block, a soft continuum robot that showcases its versatility, such as flexibly twisting light bulbs and using bending motion pattern to grasp items of varying weights is developed.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 8","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://advanced.onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202401008","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881076","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":"Inter-Day Grasping Model Generalization for Prosthetic Hand Using Soft Optical Sensing Sleeve","authors":"Linhang Ju,&nbsp;Hanze Jia,&nbsp;Yanggang Feng,&nbsp;Yan Huang,&nbsp;Yanjun Shi,&nbsp;Di Shi,&nbsp;Yixin Shao,&nbsp;Fuzhen Yuan,&nbsp;Yu Zhao,&nbsp;Xilun Ding,&nbsp;Wuxiang Zhang","doi":"10.1002/aisy.202400569","DOIUrl":"10.1002/aisy.202400569","url":null,"abstract":"<p>Inter-day motion intent recognition using wearable sensors, due to the change in position during multiple donning and doffing, i.e., surface electromyography, remains a challenge. Herein, an optimal optical sensing sleeve using a multilayer perceptron is introduced to achieve an accurate inter-day motion intent recognition. This sleeve, demonstrating a high correlation (<i>R</i>² = 0.93) with grasping force, incorporates six novel optical waveguides. Each waveguide is specifically designed to respond to pressing with high linearity, achieved by minimizing bending with a 3D-printed base and limiting elongation through carbon fiber reinforcement. This novel configuration enhances the generalization of the optical waveguides across multiple donning and doffing sessions. Furthermore, the multilayer perceptron model, which maps sensing signals to grasping forces, shows optimal performance compared to linear, quadratic, cubic, and quartic polynomial models. Remarkably, the correlation in mapping does not decrease in inter-day experiments; instead, it increases by 4.54%, indicating improved model generalization. Additionally, 12 commonly used items are grasped and held by a prosthetic hand, controlled by the optical sensing sleeve, which suggests the robustness in daily life, for an amputee. The optimal optical sensing sleeve holds promise for contributing to advancements in other wearable robots and achieving an inter-day model generalization.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 5","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400569","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144100507","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":"π-PhenoDrug: A Comprehensive Deep Learning-Based Pipeline for Phenotypic Drug Screening in High-Content Analysis","authors":"Xiao Li,&nbsp;Qinxue Ouyang,&nbsp;Mingfei Han,&nbsp;Xiaoqing Liu,&nbsp;Fuchu He,&nbsp;Yunping Zhu,&nbsp;Ling Leng,&nbsp;Jie Ma","doi":"10.1002/aisy.202400635","DOIUrl":"10.1002/aisy.202400635","url":null,"abstract":"<p>Image-based screening is an efficient drug discovery strategy. Combining high-content screening (HCS) with artificial intelligence efficiently detects drug-induced cellular phenotypes from a large pool of compounds. However, previous studies primarily focus on cell classification and cannot interpret models using morphological features. Additionally, the existing morphology-based studies use only few features, which cannot accurately characterize cell phenotypic perturbations. Herein, π-PhenoDrug, a deep learning-based pipeline, is developed for cell phenotype-driven drug screening. It integrates cell segmentation, morphological profile construction, and phenotype analysis modules of HCS processes. π-PhenoDrug is applied to evaluate drug response in various human melanoma cell lines. The results demonstrate that π-PhenoDrug can evaluate drug killing effects across different cell lines via both supervised and unsupervised modes. Furthermore, π-PhenoDrug identifies drugs with potential killing effects on melanoma cells from a library of diverse compounds. Compared with traditional single-readout assays, this method is more sensitive to compounds that induce weaker phenotypes, reducing the risk of overlooking effective drugs. These results confirm that π-PhenoDrug can achieve high-throughput and accuracy analysis of cell phenotypic data using an unbiased and automated workflow, improving drug discovery efficiency.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 6","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400635","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308834","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}