首页 > 最新文献

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

英文 中文
Data-Driven Modeling and High-Precision Tracking Control of a Soft Continuum Manipulator: Enabling Robotic Sorting of Multiwire Cables 软连续机械手的数据驱动建模和高精度跟踪控制:实现多线电缆的机器人分类
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-09-09 DOI: 10.1002/aisy.202300827
Yuan Gao, Zhi Chen, Fangxun Zhong, Xiang Li, Yun-Hui Liu

As a new class of robots, soft continuum manipulators have attracted attention due to their flexibility and compliance. However, these characteristics create challenges for precise modeling and control. This study proposes a hybrid offline and online data-driven scheme to achieve high-precision tracking control of a soft continuum manipulator. First, a novel multiscale deep neural network learns the manipulator model offline. Specifically, the feature fusion module extracts highly discriminative features and captures long-term dependencies from the temporal trajectory data. The self-attention module strengthens the ability to represent fusion features and enhances the model prediction accuracy. Then, the learnt model is updated using multisensor data online, and the proposed controller further compensates for the updated model and enhances the tracking accuracy in the movement stage. Finally, the experimental results demonstrate a significant improvement in motion accuracy under different trajectory-tracking scenarios (i.e., deviations of <1 mm in position and <0.8° in orientation). The example of the multiwire cable sorting proves the feasibility of the proposed scheme in high-precision industrial applications.

作为一类新型机器人,软连续机械手因其灵活性和顺应性而备受关注。然而,这些特性给精确建模和控制带来了挑战。本研究提出了一种离线和在线数据驱动的混合方案,以实现对软连续机械手的高精度跟踪控制。首先,新型多尺度深度神经网络离线学习机械手模型。具体来说,特征融合模块从时序轨迹数据中提取高区分度特征并捕捉长期依赖关系。自我关注模块加强了表示融合特征的能力,提高了模型预测的准确性。然后,利用多传感器数据对学习到的模型进行在线更新,提议的控制器进一步对更新后的模型进行补偿,并提高运动阶段的跟踪精度。最后,实验结果表明,在不同的轨迹跟踪情况下(即位置偏差为 1 毫米,方向偏差为 0.8°),运动精度都有显著提高。多线电缆分拣的实例证明了所提方案在高精度工业应用中的可行性。
{"title":"Data-Driven Modeling and High-Precision Tracking Control of a Soft Continuum Manipulator: Enabling Robotic Sorting of Multiwire Cables","authors":"Yuan Gao,&nbsp;Zhi Chen,&nbsp;Fangxun Zhong,&nbsp;Xiang Li,&nbsp;Yun-Hui Liu","doi":"10.1002/aisy.202300827","DOIUrl":"https://doi.org/10.1002/aisy.202300827","url":null,"abstract":"<p>As a new class of robots, soft continuum manipulators have attracted attention due to their flexibility and compliance. However, these characteristics create challenges for precise modeling and control. This study proposes a hybrid offline and online data-driven scheme to achieve high-precision tracking control of a soft continuum manipulator. First, a novel multiscale deep neural network learns the manipulator model offline. Specifically, the feature fusion module extracts highly discriminative features and captures long-term dependencies from the temporal trajectory data. The self-attention module strengthens the ability to represent fusion features and enhances the model prediction accuracy. Then, the learnt model is updated using multisensor data online, and the proposed controller further compensates for the updated model and enhances the tracking accuracy in the movement stage. Finally, the experimental results demonstrate a significant improvement in motion accuracy under different trajectory-tracking scenarios (i.e., deviations of &lt;1 mm in position and &lt;0.8° in orientation). The example of the multiwire cable sorting proves the feasibility of the proposed scheme in high-precision industrial applications.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"6 10","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202300827","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443496","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}
引用次数: 0
Multihead Attention U-Net for Magnetic Particle Imaging–Computed Tomography Image Segmentation 用于磁粉成像-计算机断层扫描图像分割的多头注意力 U-Net
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-09-09 DOI: 10.1002/aisy.202400007
Aniwat Juhong, Bo Li, Yifan Liu, Chia-Wei Yang, Cheng-You Yao, Dalen W. Agnew, Yu Leo Lei, Gary D. Luker, Harvey Bumpers, Xuefei Huang, Wibool Piyawattanametha, Zhen Qiu

Magnetic particle imaging (MPI) is an emerging noninvasive molecular imaging modality with high sensitivity and specificity, exceptional linear quantitative ability, and potential for successful applications in clinical settings. Computed tomography (CT) is typically combined with the MPI image to obtain more anatomical information. Herein, a deep learning-based approach for MPI-CT image segmentation is presented. The dataset utilized in training the proposed deep learning model is obtained from a transgenic mouse model of breast cancer following administration of indocyanine green (ICG)-conjugated superparamagnetic iron oxide nanoworms (NWs-ICG) as the tracer. The NWs-ICG particles progressively accumulate in tumors due to the enhanced permeability and retention (EPR) effect. The proposed deep learning model exploits the advantages of the multihead attention mechanism and the U-Net model to perform segmentation on the MPI-CT images, showing superb results. In addition, the model is characterized with a different number of attention heads to explore the optimal number for our custom MPI-CT dataset.

磁粉成像(MPI)是一种新兴的无创分子成像方式,具有高灵敏度和高特异性、卓越的线性定量能力以及成功应用于临床的潜力。计算机断层扫描(CT)通常与 MPI 图像相结合,以获得更多的解剖信息。本文介绍了一种基于深度学习的 MPI-CT 图像分割方法。训练所提出的深度学习模型所使用的数据集来自乳腺癌转基因小鼠模型,该模型在施用吲哚菁绿(ICG)共轭超顺磁性氧化铁纳米虫(NWs-ICG)作为示踪剂后获得。由于增强的渗透性和滞留(EPR)效应,NWs-ICG 颗粒会在肿瘤中逐渐累积。所提出的深度学习模型利用了多头注意机制和 U-Net 模型的优势,对 MPI-CT 图像进行分割,取得了极佳的效果。此外,该模型还采用了不同数量的注意力头,以探索我们定制的 MPI-CT 数据集的最佳数量。
{"title":"Multihead Attention U-Net for Magnetic Particle Imaging–Computed Tomography Image Segmentation","authors":"Aniwat Juhong,&nbsp;Bo Li,&nbsp;Yifan Liu,&nbsp;Chia-Wei Yang,&nbsp;Cheng-You Yao,&nbsp;Dalen W. Agnew,&nbsp;Yu Leo Lei,&nbsp;Gary D. Luker,&nbsp;Harvey Bumpers,&nbsp;Xuefei Huang,&nbsp;Wibool Piyawattanametha,&nbsp;Zhen Qiu","doi":"10.1002/aisy.202400007","DOIUrl":"https://doi.org/10.1002/aisy.202400007","url":null,"abstract":"<p>Magnetic particle imaging (MPI) is an emerging noninvasive molecular imaging modality with high sensitivity and specificity, exceptional linear quantitative ability, and potential for successful applications in clinical settings. Computed tomography (CT) is typically combined with the MPI image to obtain more anatomical information. Herein, a deep learning-based approach for MPI-CT image segmentation is presented. The dataset utilized in training the proposed deep learning model is obtained from a transgenic mouse model of breast cancer following administration of indocyanine green (ICG)-conjugated superparamagnetic iron oxide nanoworms (NWs-ICG) as the tracer. The NWs-ICG particles progressively accumulate in tumors due to the enhanced permeability and retention (EPR) effect. The proposed deep learning model exploits the advantages of the multihead attention mechanism and the U-Net model to perform segmentation on the MPI-CT images, showing superb results. In addition, the model is characterized with a different number of attention heads to explore the optimal number for our custom MPI-CT dataset.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"6 10","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400007","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443498","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}
引用次数: 0
Game Theoretic Non-cooperative Dynamic Target Tracking for Directional Sensing-Enabled Unmanned Aerial Vehicles 支持定向传感的无人飞行器的博弈论非合作动态目标跟踪
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-09-04 DOI: 10.1002/aisy.202300725
Peng Yi, Ge Jin, Wenyuan Wang

In this article, a game theoretic non-cooperative dynamic target tracking algorithm that empowers defensive unmanned aerial vehicles (UAVs), with directional sensing capabilities to track and collect information on intrusive UAVs, is proposed. Specifically, defenders aim to maximize the collection of identity information from intruders possessing anti-tracking and evading capabilities, while simultaneously preventing their entry into protected areas. Game theory is employed to determine the optimal confrontation paths for defenders against the intruders. The probability perception model is utilized for evaluating the dynamic target tracking capability and designing a tracking merit function to assess tracking performance, taking into account both the target's position and the perception relative angle. Furthermore, considering the dynamic interactive behaviors between intruders and defenders, the iterative linear quadratic game (ILQG) algorithm is employed to solve the Nash equilibrium of the non-cooperative target tracking game. Through simulation experiments, the effectiveness of the proposed algorithm in accomplishing multi-agent dynamic target tracking tasks is demonstrated and the performance of the algorithm under varying parameters in the intruder's cost function is evaluated, which represent different intrusion intentions.

本文提出了一种博弈论非合作动态目标跟踪算法,该算法使具有定向感应能力的防御型无人飞行器(UAV)能够跟踪和收集入侵型无人飞行器的信息。具体来说,防御者的目标是最大限度地收集具有反跟踪和规避能力的入侵者的身份信息,同时阻止其进入保护区。博弈论被用来确定防御者与入侵者的最佳对抗路径。利用概率感知模型来评估动态目标跟踪能力,并设计跟踪优点函数来评估跟踪性能,同时考虑目标的位置和感知相对角度。此外,考虑到入侵者和防御者之间的动态交互行为,采用迭代线性二次博弈(ILQG)算法求解非合作目标跟踪博弈的纳什均衡。通过仿真实验,证明了所提算法在完成多代理动态目标跟踪任务中的有效性,并评估了算法在入侵者成本函数参数变化(代表不同入侵意图)下的性能。
{"title":"Game Theoretic Non-cooperative Dynamic Target Tracking for Directional Sensing-Enabled Unmanned Aerial Vehicles","authors":"Peng Yi,&nbsp;Ge Jin,&nbsp;Wenyuan Wang","doi":"10.1002/aisy.202300725","DOIUrl":"https://doi.org/10.1002/aisy.202300725","url":null,"abstract":"<p>In this article, a game theoretic non-cooperative dynamic target tracking algorithm that empowers defensive unmanned aerial vehicles (UAVs), with directional sensing capabilities to track and collect information on intrusive UAVs, is proposed. Specifically, defenders aim to maximize the collection of identity information from intruders possessing anti-tracking and evading capabilities, while simultaneously preventing their entry into protected areas. Game theory is employed to determine the optimal confrontation paths for defenders against the intruders. The probability perception model is utilized for evaluating the dynamic target tracking capability and designing a tracking merit function to assess tracking performance, taking into account both the target's position and the perception relative angle. Furthermore, considering the dynamic interactive behaviors between intruders and defenders, the iterative linear quadratic game (ILQG) algorithm is employed to solve the Nash equilibrium of the non-cooperative target tracking game. Through simulation experiments, the effectiveness of the proposed algorithm in accomplishing multi-agent dynamic target tracking tasks is demonstrated and the performance of the algorithm under varying parameters in the intruder's cost function is evaluated, which represent different intrusion intentions.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"6 10","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202300725","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443573","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}
引用次数: 0
A Shared Control Method for Teleoperated Robot Using Artificial Potential Field 利用人工势场的遥控机器人共享控制方法
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-09-04 DOI: 10.1002/aisy.202300814
Wenlei Qin, He Zhang, Zhibin Fan, Yanhe Zhu, Jie Zhao

Retinal surgery requires enclosed spatial constraints to improve the safety and success of the surgery. Herein, a shared control method is proposed for master–slave robot systems, utilizing tubular guidance constraints based on a novel potential field function to optimize the commands of the surgeon. Within the tube, attractive constraints intensify with increasing task error and approach infinity at the boundary of the tube. This ensures that the surgery is confined within a closed tubular space. Haptic feedback provides force cues to inform the surgeon about the feasibility of the input commands. Theoretical derivations demonstrate that the entire closed-loop system is passive. Two simulation experiments are conducted on the ophthalmic surgery robot platform to evaluate the functionality of the proposed method. The experimental results indicate that translational errors are kept less than certain predefined values. Furthermore, the proposed method outperforms the comparison method in terms of task accuracy and efficiency.

视网膜手术需要封闭的空间约束,以提高手术的安全性和成功率。本文为主从机器人系统提出了一种共享控制方法,利用基于新型势场函数的管状引导约束来优化外科医生的指令。在管内,吸引力约束会随着任务误差的增加而增强,并在管的边界接近无穷大。这确保了手术被限制在一个封闭的管状空间内。触觉反馈提供力的提示,让外科医生了解输入指令的可行性。理论推导证明,整个闭环系统是被动的。在眼科手术机器人平台上进行了两次模拟实验,以评估所提出方法的功能。实验结果表明,平移误差保持在预定值以下。此外,就任务准确性和效率而言,所提出的方法优于对比方法。
{"title":"A Shared Control Method for Teleoperated Robot Using Artificial Potential Field","authors":"Wenlei Qin,&nbsp;He Zhang,&nbsp;Zhibin Fan,&nbsp;Yanhe Zhu,&nbsp;Jie Zhao","doi":"10.1002/aisy.202300814","DOIUrl":"https://doi.org/10.1002/aisy.202300814","url":null,"abstract":"<p>Retinal surgery requires enclosed spatial constraints to improve the safety and success of the surgery. Herein, a shared control method is proposed for master–slave robot systems, utilizing tubular guidance constraints based on a novel potential field function to optimize the commands of the surgeon. Within the tube, attractive constraints intensify with increasing task error and approach infinity at the boundary of the tube. This ensures that the surgery is confined within a closed tubular space. Haptic feedback provides force cues to inform the surgeon about the feasibility of the input commands. Theoretical derivations demonstrate that the entire closed-loop system is passive. Two simulation experiments are conducted on the ophthalmic surgery robot platform to evaluate the functionality of the proposed method. The experimental results indicate that translational errors are kept less than certain predefined values. Furthermore, the proposed method outperforms the comparison method in terms of task accuracy and efficiency.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"6 10","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202300814","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443571","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}
引用次数: 0
Nonlinear Variation Decomposition of Neural Networks for Holistic Semiconductor Process Monitoring 用于整体半导体过程监控的神经网络非线性变化分解
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-09-04 DOI: 10.1002/aisy.202300920
Hyeok Yun, Hyundong Jang, Seunghwan Lee, Junjong Lee, Kyeongrae Cho, Seungjoon Eom, Soomin Kim, Choong-Ki Kim, Hong-Chul Byun, Seongjoo Han, Min-Soo Yoo, Rock-Hyun Baek

Artificial intelligence (AI) is increasingly used to solve multi-objective problems and reduce the turnaround times of semiconductor processes. However, only brief AI explanations are available for process/device/circuit engineers to provide holistic feedback on the manufactured results. Herein, linear/nonlinear variation decomposition (LVD/NLVD) of neural networks is demonstrated to quantitatively evaluate the influence of unit processes on the figure of merit (FoM) and co-analyze the unit process influences with device characteristic behaviors. The NLVD can evaluate the output variation from each input of neural networks in an individual sample, although neural networks are not available in an analytic form. The NLVD is successfully verified by confirming that a) the output and summation of all decomposed output variations perfectly coincide and b) the process influences on the FoM are decomposed to 6.01–54.86% more accurately compared with those of LVD in 1Y nm node dynamic random-access memory test vehicles with a baseline and split tests introducing high-k metal gates with a minimum gate length of 1 A nm node for further node scaling. The approaches identify defective processes and defect mechanisms in each sample and wafer, which enhance causal analyses for individual cases in diverse fields based on regression artificial neural networks.

人工智能(AI)越来越多地被用于解决多目标问题和缩短半导体工艺的周转时间。然而,工艺/器件/电路工程师只能获得简短的人工智能解释,以便对制造结果提供整体反馈。在此,我们展示了神经网络的线性/非线性变化分解(LVD/NLVD),以定量评估单元制程对功绩值(FoM)的影响,并共同分析单元制程影响与器件特征行为。尽管神经网络没有分析形式,但 NLVD 可以评估单个样本中神经网络每个输入的输出变化。NLVD 成功地验证了:a) 所有分解输出变化的输出和总和完全重合;b) 在 1Y nm 节点动态随机存取存储器测试车辆中,与 LVD 相比,工艺对 FoM 的影响分解精确度提高了 6.01-54.86%。这些方法可识别每个样品和晶圆中的缺陷过程和缺陷机制,从而加强基于回归人工神经网络的不同领域个案的因果分析。
{"title":"Nonlinear Variation Decomposition of Neural Networks for Holistic Semiconductor Process Monitoring","authors":"Hyeok Yun,&nbsp;Hyundong Jang,&nbsp;Seunghwan Lee,&nbsp;Junjong Lee,&nbsp;Kyeongrae Cho,&nbsp;Seungjoon Eom,&nbsp;Soomin Kim,&nbsp;Choong-Ki Kim,&nbsp;Hong-Chul Byun,&nbsp;Seongjoo Han,&nbsp;Min-Soo Yoo,&nbsp;Rock-Hyun Baek","doi":"10.1002/aisy.202300920","DOIUrl":"https://doi.org/10.1002/aisy.202300920","url":null,"abstract":"<p>Artificial intelligence (AI) is increasingly used to solve multi-objective problems and reduce the turnaround times of semiconductor processes. However, only brief AI explanations are available for process/device/circuit engineers to provide holistic feedback on the manufactured results. Herein, linear/nonlinear variation decomposition (LVD/NLVD) of neural networks is demonstrated to quantitatively evaluate the influence of unit processes on the figure of merit (FoM) and co-analyze the unit process influences with device characteristic behaviors. The NLVD can evaluate the output variation from each input of neural networks in an individual sample, although neural networks are not available in an analytic form. The NLVD is successfully verified by confirming that a) the output and summation of all decomposed output variations perfectly coincide and b) the process influences on the FoM are decomposed to 6.01–54.86% more accurately compared with those of LVD in 1Y nm node dynamic random-access memory test vehicles with a baseline and split tests introducing high-k metal gates with a minimum gate length of 1 A nm node for further node scaling. The approaches identify defective processes and defect mechanisms in each sample and wafer, which enhance causal analyses for individual cases in diverse fields based on regression artificial neural networks.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"6 10","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202300920","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443572","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}
引用次数: 0
A Cable-Actuated Soft Manipulator for Dexterous Grasping Based on Deep Reinforcement Learning 基于深度强化学习的用于灵巧抓取的线控软机械手
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-08-29 DOI: 10.1002/aisy.202400112
Kunyu Zhou, Baijin Mao, Yuzhu Zhang, Yaozhen Chen, Yuyaocen Xiang, Zhenping Yu, Hongwei Hao, Wei Tang, Yanwen Li, Houde Liu, Xueqian Wang, Xiaohao Wang, Juntian Qu

The growing interest in the flexibility and operational capabilities of soft manipulators in confined spaces emphasizes the need for precise modeling and accurate motion control. Conventional control methods encounter difficulties in modeling and involve intricate computations. This work introduces a novel deep reinforcement learning (DRL) control algorithm based on neural network modeling. Using the Whale Optimization Algorithm, an approximate dynamic model for the soft manipulator is established. The twin delayed deterministic policy gradient is employed for DRL control. Domain randomization is applied during pretraining in a simulated environment. The algorithm addresses issues related to dependency on measurement data quality and redundant mappings, outperforming other methods by 8–15 mm in control accuracy. The trained DRL controller achieves precise trajectory tracking within the soft manipulator's task space, enabling successful grasping tasks in various complex environments, including pipelines and other narrow spaces. Experimental results confirm the autonomy of our controller in performing these tasks without human intervention.

人们对软体机械手在狭小空间内的灵活性和操作能力越来越感兴趣,这就强调了精确建模和精确运动控制的必要性。传统的控制方法在建模方面存在困难,并且涉及复杂的计算。这项工作介绍了一种基于神经网络建模的新型深度强化学习(DRL)控制算法。利用鲸鱼优化算法,建立了软机械手的近似动态模型。双延迟确定性策略梯度被用于 DRL 控制。在模拟环境中进行预训练时,采用域随机化。该算法解决了与测量数据质量和冗余映射相关的问题,控制精度比其他方法高出 8-15 毫米。训练有素的 DRL 控制器可在软机械手的任务空间内实现精确的轨迹跟踪,从而在各种复杂环境(包括管道和其他狭窄空间)中成功完成抓取任务。实验结果证实,我们的控制器能够在没有人工干预的情况下自主执行这些任务。
{"title":"A Cable-Actuated Soft Manipulator for Dexterous Grasping Based on Deep Reinforcement Learning","authors":"Kunyu Zhou,&nbsp;Baijin Mao,&nbsp;Yuzhu Zhang,&nbsp;Yaozhen Chen,&nbsp;Yuyaocen Xiang,&nbsp;Zhenping Yu,&nbsp;Hongwei Hao,&nbsp;Wei Tang,&nbsp;Yanwen Li,&nbsp;Houde Liu,&nbsp;Xueqian Wang,&nbsp;Xiaohao Wang,&nbsp;Juntian Qu","doi":"10.1002/aisy.202400112","DOIUrl":"https://doi.org/10.1002/aisy.202400112","url":null,"abstract":"<p>The growing interest in the flexibility and operational capabilities of soft manipulators in confined spaces emphasizes the need for precise modeling and accurate motion control. Conventional control methods encounter difficulties in modeling and involve intricate computations. This work introduces a novel deep reinforcement learning (DRL) control algorithm based on neural network modeling. Using the Whale Optimization Algorithm, an approximate dynamic model for the soft manipulator is established. The twin delayed deterministic policy gradient is employed for DRL control. Domain randomization is applied during pretraining in a simulated environment. The algorithm addresses issues related to dependency on measurement data quality and redundant mappings, outperforming other methods by 8–15 mm in control accuracy. The trained DRL controller achieves precise trajectory tracking within the soft manipulator's task space, enabling successful grasping tasks in various complex environments, including pipelines and other narrow spaces. Experimental results confirm the autonomy of our controller in performing these tasks without human intervention.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"6 10","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400112","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443490","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}
引用次数: 0
Deformable Capsules for Object Detection 用于物体探测的可变形胶囊
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-08-22 DOI: 10.1002/aisy.202400044
Rodney LaLonde, Naji Khosravan, Ulas Bagci

Capsule networks promise significant benefits over convolutional neural networks (CNN) by storing stronger internal representations and routing information based on the agreement between intermediate representations’ projections. Despite this, their success has been limited to small-scale classification datasets due to their computationally expensive nature. Though memory-efficient, convolutional capsules impose geometric constraints that fundamentally limit the ability of capsules to model the pose/deformation of objects. Further, they do not address the bigger memory concern of class capsules scaling up to bigger tasks such as detection or large-scale classification. Herein, a new family of capsule networks, deformable capsules (DeformCaps), is introduced to address object detection problem in computer vision. Two new algorithms associated with our DeformCaps, a novel capsule structure (SplitCaps), and a novel dynamic routing algorithm (SE-Routing), which balance computational efficiency with the need for modeling a large number of objects and classes, are proposed. This has never been achieved with capsule networks before. The proposed methods efficiently scale up to create the first-ever capsule network for object detection in the literature. The proposed architecture is a one-stage detection framework and it obtains results on microsoft common objects in context which are on par with state-of-the-art one-stage CNN-based methods, while producing fewer false-positive detection, generalizing to unusual poses/viewpoints of objects.

与卷积神经网络(CNN)相比,胶囊网络能存储更强的内部表征,并根据中间表征投影之间的一致性来路由信息,因而具有显著的优势。尽管如此,由于其计算昂贵的特性,它们的成功仅限于小规模分类数据集。虽然卷积胶囊具有内存效率高的特点,但其几何限制从根本上限制了胶囊对物体的姿势/变形进行建模的能力。此外,它们没有解决类胶囊在扩展到更大任务(如检测或大规模分类)时更大的内存问题。在此,我们引入了一个新的胶囊网络系列--可变形胶囊(DeformCaps),以解决计算机视觉中的物体检测问题。我们还提出了两种与 DeformCaps 相关的新算法,一种是新颖的胶囊结构(SplitCaps),另一种是新颖的动态路由算法(SE-Routing),这两种算法在计算效率与大量对象和类别建模需求之间取得了平衡。这在以前的胶囊网络中从未实现过。所提出的方法可以有效地扩展,在文献中首次创建了用于物体检测的胶囊网络。所提出的架构是一个单级检测框架,它在微型软件常见物体的上下文中获得的结果与基于单级 CNN 的先进方法相当,同时产生的假阳性检测结果较少,并可泛化到物体的异常姿势/视角。
{"title":"Deformable Capsules for Object Detection","authors":"Rodney LaLonde,&nbsp;Naji Khosravan,&nbsp;Ulas Bagci","doi":"10.1002/aisy.202400044","DOIUrl":"https://doi.org/10.1002/aisy.202400044","url":null,"abstract":"<p>Capsule networks promise significant benefits over convolutional neural networks (CNN) by storing stronger internal representations and routing information based on the agreement between intermediate representations’ projections. Despite this, their success has been limited to small-scale classification datasets due to their computationally expensive nature. Though memory-efficient, convolutional capsules impose geometric constraints that fundamentally limit the ability of capsules to model the pose/deformation of objects. Further, they do not address the bigger memory concern of class capsules scaling up to bigger tasks such as detection or large-scale classification. Herein, a new family of capsule networks, deformable capsules (<i>DeformCaps</i>), is introduced to address object detection problem in computer vision. Two new algorithms associated with our <i>DeformCaps</i>, a novel capsule structure (<i>SplitCaps</i>), and a novel dynamic routing algorithm (<i>SE-Routing</i>), which balance computational efficiency with the need for modeling a large number of objects and classes, are proposed. This has never been achieved with capsule networks before. The proposed methods efficiently scale up to create the first-ever capsule network for object detection in the literature. The proposed architecture is a one-stage detection framework and it obtains results on microsoft common objects in context which are on par with state-of-the-art one-stage CNN-based methods, while producing fewer false-positive detection, generalizing to unusual poses/viewpoints of objects.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"6 9","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400044","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142316857","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}
引用次数: 0
Design and Optimization of a Magnetic Field Generator for Magnetic Particle Imaging with Soft Magnetic Materials 设计和优化用于软磁材料磁粉成像的磁场发生器
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-08-22 DOI: 10.1002/aisy.202400017
Fynn Foerger, Marija Boberg, Jonas Faltinath, Tobias Knopp, Martin Möddel

Magnetic field generators are a key component of Magnetic Particle Imaging (MPI) systems, and their power consumption is a major obstacle on the path to human-sized scanners. Despite their importance, a focused discussion of these generators is rare, and a comprehensive description of the design process is currently lacking. This work presents a methodology for the design and optimization of selection field generators operating with soft magnetic materials outside the linear regime in the context of MPI. Key elements are a mathematical model of magnetic field generators, a formalism for defining field sequences, and a relationship between power consumption and field sequence. These are used to define the design space of a field generator given its system requirements and constraints. The design process is then formulated as an optimization problem. Subsequently, this methodology is then utilized to design a new magnetic field generator specifically for cerebral imaging studies. The optimization result outperforms our existing MPI field generator in terms of power consumption and field of view size, providing a proof-of-concept for the entire methodology. As the approach is very general, it can be extended beyond the MPI context to other areas such as magnetic manipulation of medical devices and micro-robotics.

磁场发生器是磁粉成像(MPI)系统的关键部件,其功耗是实现人体尺寸扫描仪的主要障碍。尽管磁场发生器非常重要,但对它们的集中讨论却很少见,目前也缺乏对设计过程的全面描述。这项研究提出了一种方法,用于设计和优化在 MPI 背景下使用线性机制之外的软磁材料运行的选择场发生器。其关键要素包括磁场发生器的数学模型、定义磁场序列的形式主义以及功耗与磁场序列之间的关系。根据系统要求和限制条件,这些内容可用于定义磁场发生器的设计空间。然后将设计过程表述为一个优化问题。随后,利用这种方法设计出一种专门用于脑成像研究的新型磁场发生器。优化结果在功耗和视场大小方面优于我们现有的 MPI 磁场发生器,为整个方法提供了概念验证。由于该方法具有很强的通用性,因此可将其从 MPI 范畴扩展到其他领域,如医疗设备的磁操控和微型机器人。
{"title":"Design and Optimization of a Magnetic Field Generator for Magnetic Particle Imaging with Soft Magnetic Materials","authors":"Fynn Foerger,&nbsp;Marija Boberg,&nbsp;Jonas Faltinath,&nbsp;Tobias Knopp,&nbsp;Martin Möddel","doi":"10.1002/aisy.202400017","DOIUrl":"https://doi.org/10.1002/aisy.202400017","url":null,"abstract":"<p>\u0000Magnetic field generators are a key component of Magnetic Particle Imaging (MPI) systems, and their power consumption is a major obstacle on the path to human-sized scanners. Despite their importance, a focused discussion of these generators is rare, and a comprehensive description of the design process is currently lacking. This work presents a methodology for the design and optimization of selection field generators operating with soft magnetic materials outside the linear regime in the context of MPI. Key elements are a mathematical model of magnetic field generators, a formalism for defining field sequences, and a relationship between power consumption and field sequence. These are used to define the design space of a field generator given its system requirements and constraints. The design process is then formulated as an optimization problem. Subsequently, this methodology is then utilized to design a new magnetic field generator specifically for cerebral imaging studies. The optimization result outperforms our existing MPI field generator in terms of power consumption and field of view size, providing a proof-of-concept for the entire methodology. As the approach is very general, it can be extended beyond the MPI context to other areas such as magnetic manipulation of medical devices and micro-robotics.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"6 11","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400017","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142664999","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}
引用次数: 0
A Bioinspired Robotic Finger for Multimodal Tactile Sensing Powered by Fiber Optic Sensors 由光纤传感器驱动的多模态触觉传感生物启发机器人手指
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-08-18 DOI: 10.1002/aisy.202470034
Baijin Mao, Kunyu Zhou, Yuyaocen Xiang, Yuzhu Zhang, Qiangjing Yuan, Hongwei Hao, Yaozhen Chen, Houde Liu, Xueqian Wang, Xiaohao Wang, Juntian Qu

Bioinspired Robotic Fingers

In article number 2400175, Juntian Qu and co-workers report a bio-inspired robotic finger for multi-modal tactile sensing. Inspired by the tactile perception mechanisms of various organisms, this work integrates distributed fiber optic sensing technology to propose a multimodal tactile sensing soft robotic finger with bio-inspired whisker and hair-like structures. It can perceive various parameters such as touch state, contact force, surface roughness, object hardness, and contact position. Additionally, it is capable of dexterously and non-destructively grasping fragile objects and underwater transparent objects.

生物启发机器人手指 在编号为 2400175 的文章中,曲俊田及其合作者报告了一种用于多模态触觉传感的生物启发机器人手指。受各种生物体触觉感知机制的启发,这项工作集成了分布式光纤传感技术,提出了一种具有生物启发胡须和毛发状结构的多模态触觉感知软机器人手指。它能感知触摸状态、接触力、表面粗糙度、物体硬度和接触位置等各种参数。此外,它还能灵巧、无损地抓取易碎物体和水下透明物体。
{"title":"A Bioinspired Robotic Finger for Multimodal Tactile Sensing Powered by Fiber Optic Sensors","authors":"Baijin Mao,&nbsp;Kunyu Zhou,&nbsp;Yuyaocen Xiang,&nbsp;Yuzhu Zhang,&nbsp;Qiangjing Yuan,&nbsp;Hongwei Hao,&nbsp;Yaozhen Chen,&nbsp;Houde Liu,&nbsp;Xueqian Wang,&nbsp;Xiaohao Wang,&nbsp;Juntian Qu","doi":"10.1002/aisy.202470034","DOIUrl":"https://doi.org/10.1002/aisy.202470034","url":null,"abstract":"<p><b>Bioinspired Robotic Fingers</b>\u0000 </p><p>In article number 2400175, Juntian Qu and co-workers report a bio-inspired robotic finger for multi-modal tactile sensing. Inspired by the tactile perception mechanisms of various organisms, this work integrates distributed fiber optic sensing technology to propose a multimodal tactile sensing soft robotic finger with bio-inspired whisker and hair-like structures. It can perceive various parameters such as touch state, contact force, surface roughness, object hardness, and contact position. Additionally, it is capable of dexterously and non-destructively grasping fragile objects and underwater transparent objects.\u0000\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":"6 8","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202470034","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142002528","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}
引用次数: 0
Fluid-Driven Director-Field Design Enables Versatile Deployment of Multistable Structures 流体驱动导向场设计实现了多稳态结构的多功能部署
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-08-18 DOI: 10.1002/aisy.202470039
Yaron Veksler, Ezra Ben-Abu, Amir D. Gat

Fluid-Driven Director-Field Design

In article number 2400179, Yaron Veksler and co-workers present a modular platform of interconnected multi-stable tubes that can transform into a wide range of desired shapes on demand. Using detachable links designed based on director-field theory and viscous fluid actuation, they easily control the shape morphing process. This enables dramatic changes in the final shape while unlocking numerous intermediate configurations. Their method opens new possibilities for deployable structures in applications ranging from soft robotics to medical devices and space exploration.

流体驱动的导演场设计 在编号为 2400179 的文章中,Yaron Veksler 及其合作者展示了一个由相互连接的多稳态管组成的模块化平台,该平台可以根据需要变换成各种所需的形状。他们利用基于导演场理论和粘性流体驱动设计的可拆卸链接,轻松控制了形状变形过程。这样,最终形状就能发生巨大变化,同时还能解锁多种中间配置。他们的方法为软机器人、医疗设备和太空探索等应用领域的可部署结构开辟了新的可能性。
{"title":"Fluid-Driven Director-Field Design Enables Versatile Deployment of Multistable Structures","authors":"Yaron Veksler,&nbsp;Ezra Ben-Abu,&nbsp;Amir D. Gat","doi":"10.1002/aisy.202470039","DOIUrl":"https://doi.org/10.1002/aisy.202470039","url":null,"abstract":"<p><b>Fluid-Driven Director-Field Design</b>\u0000 </p><p>In article number 2400179, Yaron Veksler and co-workers present a modular platform of interconnected multi-stable tubes that can transform into a wide range of desired shapes on demand. Using detachable links designed based on director-field theory and viscous fluid actuation, they easily control the shape morphing process. This enables dramatic changes in the final shape while unlocking numerous intermediate configurations. Their method opens new possibilities for deployable structures in applications ranging from soft robotics to medical devices and space exploration.\u0000\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":"6 8","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202470039","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142002531","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}
引用次数: 0
期刊
Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1