IEEE/ASME Transactions on Mechatronics最新文献_第7页

High-Precision Hollow Triaxial Force Sensor for Cannulation in Minimally Invasive Surgery 用于微创手术插管的高精度空心三轴力传感器

IF 6.3 1区工程技术

IEEE/ASME Transactions on Mechatronics Pub Date : 2026-10-01 Epub Date: 2026-02-20 DOI: 10.1109/TMECH.2026.3659890

Weiquan Deng;Chongyang Wang;Dingjia Li;Yongming Yang;Wenpeng Gao;Yili Fu;Jie Li;Hao Liu

{"title":"High-Precision Hollow Triaxial Force Sensor for Cannulation in Minimally Invasive Surgery","authors":"Weiquan Deng;Chongyang Wang;Dingjia Li;Yongming Yang;Wenpeng Gao;Yili Fu;Jie Li;Hao Liu","doi":"10.1109/TMECH.2026.3659890","DOIUrl":"10.1109/TMECH.2026.3659890","url":null,"abstract":"Cannulation is a common procedure in minimally invasive surgery. Force sensing during this procedure is essential for its safety and effectiveness. Achieving high-precision force sensing remains challenging due to the dimensional constraints of catheters and the need for hollow channels. This study presents a hollow triaxial force sensor based on fiber Bragg gratings, featuring a double-layer beam configuration that achieves both compact size and balanced stiffness. We develop an evolutionary design process of the sensor using the Freedom and Constraint Topology method. We also establish a mechanical model of the sensor, and optimize structural parameters through the condition number of the mapping matrix to suppress error amplification. In addition, we propose an improved tree Parzen estimator optimized random forest algorithm, integrated with temperature compensation, to enhance the precision of triaxial force sensing. The sensor achieves root mean square errors of 0.0214 and 0.0225 N for radial force components <inline-formula><tex-math>$F_{x}$</tex-math></inline-formula> and <inline-formula><tex-math>$F_{y}$</tex-math></inline-formula> with measurement ranges of <inline-formula><tex-math>$pm$</tex-math></inline-formula> 2N, and 0.0170N for axial force component <inline-formula><tex-math>$F_{z}$</tex-math></inline-formula> with measurement range of 0–2N. An ex vivo tissue experiment validates that the sensor effectively detects dynamic force variations and facilitates compliant operation with surgical instruments in a porcine duodenal papilla.","PeriodicalId":13372,"journal":{"name":"IEEE/ASME Transactions on Mechatronics","volume":"31 5","pages":"5424-5435"},"PeriodicalIF":6.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146230825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CIBVS: Continuous Image-Based Visual Servoing Against Visual Signal Loss CIBVS：针对视觉信号丢失的连续图像视觉伺服

IF 6.3 1区工程技术

IEEE/ASME Transactions on Mechatronics Pub Date : 2026-10-01 Epub Date: 2026-03-02 DOI: 10.1109/TMECH.2026.3657797

Rui He;Yuan Xuan;Hongkang Cui;Peng Li;Haoyao Chen

{"title":"CIBVS: Continuous Image-Based Visual Servoing Against Visual Signal Loss","authors":"Rui He;Yuan Xuan;Hongkang Cui;Peng Li;Haoyao Chen","doi":"10.1109/TMECH.2026.3657797","DOIUrl":"10.1109/TMECH.2026.3657797","url":null,"abstract":"Image-based visual servoing guides a robotic system to its desired place through ongoing feedback from visual signals. However, interference such as object occlusion and camera drift may cause visual signal loss, ultimately leading to servo failure. This article proposes a novel continuous image-based visual servoing (CIBVS) approach to address the potential visual signal loss. A geometric relationship is established between the positions of natural features and servo features. In each iteration, natural features are coarsely matched between frames, and mismatched pairs are eliminated by the proposed refining score based on the geometric relationship. When visual signal loss occurs, CIBVS leverages the natural features and the geometric relationship to estimate the lost servo features through optimization, ensuring continuous and stable visual feedback generation. In simulation, CIBVS was evaluated across three scenarios and 750 test cases, achieving an enhanced success rate and estimation accuracy. In the real world, CIBVS was integrated into various robotic systems, including manipulators, drones, and ground vehicles, to achieve multiple tasks. Experimental results demonstrated that, in scenarios with visual signal loss, CIBVS achieved significant improvements over extended-Kalman-filter-based IBVS and visual-odometry-based IBVS in servoing success rate, estimation accuracy, and convergence speed.","PeriodicalId":13372,"journal":{"name":"IEEE/ASME Transactions on Mechatronics","volume":"31 5","pages":"5674-5685"},"PeriodicalIF":6.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147351038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

BT-TL-DMPs: A Novel Robot TAMP Framework Combining Behavior Tree, Temporal Logic, and Dynamical Movement Primitives 结合行为树、时间逻辑和动态运动原语的新型机器人TAMP框架

IF 6.3 1区工程技术

IEEE/ASME Transactions on Mechatronics Pub Date : 2026-10-01 Epub Date: 2026-03-04 DOI: 10.1109/TMECH.2026.3665687

Zezhi Liu;Shizhen Wu;Hanqian Luo;Deyun Qin;Yongchun Fang

{"title":"BT-TL-DMPs: A Novel Robot TAMP Framework Combining Behavior Tree, Temporal Logic, and Dynamical Movement Primitives","authors":"Zezhi Liu;Shizhen Wu;Hanqian Luo;Deyun Qin;Yongchun Fang","doi":"10.1109/TMECH.2026.3665687","DOIUrl":"10.1109/TMECH.2026.3665687","url":null,"abstract":"In the field of learning from demonstration (LfD), enabling robots to generalize learned manipulation skills to novel scenarios for long-horizon tasks remains challenging. Specifically, it is still difficult for robots to adapt the learned skills to new environments with different task and motion requirements, especially in long-horizon, multistage scenarios with intricate constraints. This article proposes a novel hierarchical framework, called BT-TL-DMPs, that integrates behavior tree (BT), temporal logic (TL), and dynamical movement primitives (DMPs) to address this problem. Within this framework, signal temporal logic (STL) is employed to formally specify complex, long-horizon task requirements and constraints. These STL specifications are systematically transformed to generate reactive and modular BTs for high-level decision-making task structure. An STL-constrained DMP optimization method is proposed to optimize the DMP forcing term, allowing the learned motion primitives to adapt flexibly while satisfying intricate spatiotemporal requirements and, crucially, preserving the essential dynamics learned from demonstrations. The framework is validated through simulations demonstrating generalization capabilities under various STL constraints and real-world experiments on several long-horizon robotic manipulation tasks, where it significantly improves the success rate from 0.25 to 0.85, compared with the baseline. The results demonstrate that the proposed framework effectively bridges the symbolic-motion gap, enabling more reliable and generalizable autonomous manipulation for complex robotic tasks.","PeriodicalId":13372,"journal":{"name":"IEEE/ASME Transactions on Mechatronics","volume":"31 5","pages":"5722-5733"},"PeriodicalIF":6.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147361018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning Globally Stable Neural Imitation Policies via Reshaped Energy Functions 基于重构能量函数的全局稳定神经模仿策略学习

IF 6.3 1区工程技术

IEEE/ASME Transactions on Mechatronics Pub Date : 2026-10-01 Epub Date: 2026-03-04 DOI: 10.1109/TMECH.2026.3665234

Haohui Huang;Wenxu Zheng;Junda Duan;Kailun Huang;Jing Guo;Chenguang Yang

引用次数: 0

Adaptive Painting Strategy Generation for Embodied Robotic Painting via LLM-Based AI Agents 基于llm的人工智能代理的具身机器人自适应绘画策略生成

IF 6.3 1区工程技术

IEEE/ASME Transactions on Mechatronics Pub Date : 2026-10-01 Epub Date: 2026-09-16 DOI: 10.1109/TMECH.2026.3724257

Yong Dou;Chao Guo;Ziyan Tan;Wenda Xie;Yue Lu;Qinghua Ni;Yisheng Lv

{"title":"Adaptive Painting Strategy Generation for Embodied Robotic Painting via LLM-Based AI Agents","authors":"Yong Dou;Chao Guo;Ziyan Tan;Wenda Xie;Yue Lu;Qinghua Ni;Yisheng Lv","doi":"10.1109/TMECH.2026.3724257","DOIUrl":"10.1109/TMECH.2026.3724257","url":null,"abstract":"The rapid development of AI technology has greatly advanced the generation of creative content. Robotic painting aims to simulate and learn the human creative process by generating brushstroke sequences and the embodied robot’s motion trajectories, progressively completing the painting process and producing physical artworks. However, existing methods typically produce a fixed brushstroke strategy or use predefined stroke characteristics to generate painting trajectories in a coarse-to-fine hierarchical manner. These methods struggle to adaptively select painting techniques and brushstroke styles for different painting content and local regions, leading to a significant gap between the generated paintings and human artwork. To this end, we propose an adaptive embodied robotic painting strategy generation method using LLM-based AI agents. We construct AI agents using LLMs for task reasoning, which then call professional painting models and tools to adaptively select different painting strategies for various contents and regions. The agents autonomously complete demand analysis, multistage painting plan development, brushstroke sequence generation, and evaluate and modify the painting plan through computational experiments, ultimately prescribing the embodied robot to adopt differentiated techniques and brushstroke features to complete the entire painting process. Experimental results show that our method exhibits stronger strategy flexibility and higher quality in diverse painting scenarios, generating more natural and human-like artwork compared to existing methods with fixed strategies.","PeriodicalId":13372,"journal":{"name":"IEEE/ASME Transactions on Mechatronics","volume":"31 5","pages":"5030-5041"},"PeriodicalIF":6.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149009835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intelligent Impedance Control for Soft Robotic Arms With Environmental Force Interaction 环境力作用下柔性机械臂的智能阻抗控制

IF 6.4 1区工程技术

IEEE/ASME Transactions on Mechatronics Pub Date : 2026-10-01 DOI: 10.1109/tmech.2026.3731122

Saeedeh Shekari, S. Ali A. Moosavian

引用次数: 0

High-Precision Magnetic Tracking With Individual Magnet Identification for Medical Applications 高精度磁跟踪与单个磁体识别的医疗应用

IF 6.3 1区工程技术

IEEE/ASME Transactions on Mechatronics Pub Date : 2026-10-01 Epub Date: 2026-02-20 DOI: 10.1109/TMECH.2026.3660131

Zhuocong Cai;Mingyu Wang;Hongpeng Wang;Jianda Han;Yanding Qin

{"title":"High-Precision Magnetic Tracking With Individual Magnet Identification for Medical Applications","authors":"Zhuocong Cai;Mingyu Wang;Hongpeng Wang;Jianda Han;Yanding Qin","doi":"10.1109/TMECH.2026.3660131","DOIUrl":"10.1109/TMECH.2026.3660131","url":null,"abstract":"Permanent magnetic tracking can accurately track the surgical target within the human body via the embedded miniaturized magnet, such as in the tracking of implantable devices and minimally invasive surgical navigation. The measurement accuracy directly affects the safety and effectiveness in these surgical scenarios. Due to inevitable parameter perturbances of the miniaturized magnet, it is difficult to enhance the measurement accuracy using nominal parameters. In this article, an identified parameter-based magnetic tracking is proposed to enhance measurement accuracy, where the identified parameters are used in the tracking algorithm to attenuate the influence of parameter perturbations. Simulation results verify the ultrahigh fidelity of the established model of the magnet. Static and dynamic trajectory experiments further validate the effectiveness and applicability of this method at different positions and under various motion patterns. Compared with conventional methods, the proposed method enhances the position accuracy by 65.24% and the orientation accuracy by 41.35% on average. Finally, <italic>ex vivo</i> tissue experiments verify the feasibility of tracking the tip of a surgical tool in surgical scenarios. The results demonstrate that the proposed method effectively attenuates the influence of parameter perturbations on measurement accuracy and provides reliable technical support for clinical applications.","PeriodicalId":13372,"journal":{"name":"IEEE/ASME Transactions on Mechatronics","volume":"31 5","pages":"5458-5469"},"PeriodicalIF":6.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146230824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Synchronous Vibration Suppression for Active Magnetic Bearing Systems With Induced Current and Stiffness Variation 具有感应电流和刚度变化的主动磁轴承系统同步振动抑制

IF 6.3 1区工程技术

IEEE/ASME Transactions on Mechatronics Pub Date : 2026-10-01 Epub Date: 2026-02-20 DOI: 10.1109/TMECH.2026.3659881

Qi Liu;Zhenzhong Su;Shouding Xu;Hao Jiang;Zhi Li

{"title":"Synchronous Vibration Suppression for Active Magnetic Bearing Systems With Induced Current and Stiffness Variation","authors":"Qi Liu;Zhenzhong Su;Shouding Xu;Hao Jiang;Zhi Li","doi":"10.1109/TMECH.2026.3659881","DOIUrl":"10.1109/TMECH.2026.3659881","url":null,"abstract":"The synchronous vibration suppression controllers (SVSCs) based on active magnetic bearings (AMBs) can isolate the synchronous electromagnetic force to achieve synchronous vibration suppression. In this article, we address two key factors that have limited the conventional SVSCs: the induced current and the stiffness variation, which are addressed by induced current compensation and online stiffness measurement. First, the induced current under both open-loop and closed-loop conditions, as well as its effect on the AMB electromagnetic forces, is analyzed. Additionally, an online stiffness measurement method is introduced, which requires only adjusting the bias current without increasing the test weight or altering the speed, thereby ensuring practical applicability. Then, an optimized phase-shifted bandpass filter SVSC is implemented, whose parameters are dynamically tuned by the real-time values of the induced current and stiffness. Finally, experimental results at various speeds demonstrate the effectiveness of the proposed method, achieving vibration reduction of at least 3.5 dB and up to 18 dB compared to conventional SVSCs.","PeriodicalId":13372,"journal":{"name":"IEEE/ASME Transactions on Mechatronics","volume":"31 5","pages":"5447-5457"},"PeriodicalIF":6.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146230828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Gradient Direction Consistency-Based Redundancy Optimization for Smooth Joint Paths Generation of Industrial Robots 基于梯度方向一致性的工业机器人光滑关节路径冗余优化

IF 6.3 1区工程技术

IEEE/ASME Transactions on Mechatronics Pub Date : 2026-10-01 Epub Date: 2026-02-19 DOI: 10.1109/TMECH.2026.3659351

Mansen Chen;Yuwen Sun;Shanglei Jiang;Jinting Xu;Chengxiang Lu;Qiang Guo;Jun Liu

{"title":"Gradient Direction Consistency-Based Redundancy Optimization for Smooth Joint Paths Generation of Industrial Robots","authors":"Mansen Chen;Yuwen Sun;Shanglei Jiang;Jinting Xu;Chengxiang Lu;Qiang Guo;Jun Liu","doi":"10.1109/TMECH.2026.3659351","DOIUrl":"10.1109/TMECH.2026.3659351","url":null,"abstract":"The discontinuity of geometric paths is a primary obstacle to high performance robotic milling, because it can easily cause abrupt changes in velocity, acceleration, and cutting load, which is adverse to milling stability and accuracy. To address this challenge, this article provides a novel approach to generating smooth joint paths for industrial robots through redundancy optimization. Specifically, a new smoothness metric based on a gradient direction consistency principle is introduced at first. Subsequently, a simple yet effective redundancy optimization model is built by incorporating the joint space limitation, singularity avoidance and stiffness constraints. This transforms the complex smooth joint paths generation problem into a manageable binary classification task. In addition, by combining the Taylor series expansion, a generalized solution algorithm based on sequential quadratic programming is also proposed to solve the problem. Comparative experiments are conducted to validate the proposed method. The experimental results demonstrate that, in comparison to other representative approaches, this method achieves a significant improvement in the smoothness of joint paths, with an 88% reduction in the metric, but also enhances machining accuracy, as evidenced by a 23% contour error reduction.","PeriodicalId":13372,"journal":{"name":"IEEE/ASME Transactions on Mechatronics","volume":"31 5","pages":"5388-5399"},"PeriodicalIF":6.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146230846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Fingertip-Size Six-Axis Force Sensor via Origami Coil Arrays for Intrinsic Tactile Sensing 一种基于折纸线圈阵列的指尖大小的六轴力传感器

IF 6.3 1区工程技术

IEEE/ASME Transactions on Mechatronics Pub Date : 2026-10-01 Epub Date: 2026-02-18 DOI: 10.1109/TMECH.2026.3660186

Yingao Xu;Houping Wu;Yunfei Xie;Jiayuan Zhang;Hongbo Wang

{"title":"A Fingertip-Size Six-Axis Force Sensor via Origami Coil Arrays for Intrinsic Tactile Sensing","authors":"Yingao Xu;Houping Wu;Yunfei Xie;Jiayuan Zhang;Hongbo Wang","doi":"10.1109/TMECH.2026.3660186","DOIUrl":"10.1109/TMECH.2026.3660186","url":null,"abstract":"Force and tactile sensing play increasingly important roles in robotics hands to complete complex tasks safely and effectively, complementing the last piece of the puzzle of human-level dexterity. Despite the advances in flexible sensors and skins, tactile sensing at the fingertip of robotic hands remains an open question. Exploiting embedded six-axis force/torque (F/T) sensors for external stimuli estimation, namely, intrinsic tactile sensing, seems to be an effective solution. Here, we present OriCube, an origami-inspired, fingertip-size (14.5 × 14.5 × 12.5 mm<sup>3</sup>), lightweight (4 g), fully integrated, inductive six-axis F/T sensor. It utilizes an origami coil array to achieve self-decoupled six-axis F/T measurements by detecting the displacements and rotations of a metal shell via eddy–current coupling. A modular silicone spring-based elastomer design allows fine-tuning of the stiffness and performance of each axis independently. The calibrated OriCube exhibits a high resolution of 0.01% F.S. (23 N), low crosstalk (2%), high stability (<0.2% drift in 6 h), and insensitivity to strong magnetic field changes. It is capable of detecting light touch by a feather as well as high impact force when hammered. We demonstrate real-time tactile sensing (contact position and force vector) at the curved surface of a robotic fingertip via one embedded OriCube sensor.","PeriodicalId":13372,"journal":{"name":"IEEE/ASME Transactions on Mechatronics","volume":"31 5","pages":"5377-5387"},"PeriodicalIF":6.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146230851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0