检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Li, Jinke Tian, Dingkui Li, Feng Sun, Jianquan Yin, Meng Wu, Xinyu University of Chinese Academy of Sciences Shenzhen College of Advanced Technology Shenzhen518055 China Siat Cuhk Joint Laboratory of Robotics and Intelligent Systems China Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9798350327182

Designed to provide rehabilitation or the assistance of walking for individuals who are with lower limb muscle injuries or spinal during their activities, self-balancing lower limb exoskeletons have been developed. This paper introduces an innovative controller for a fully actuated exoskeleton that ensures stable walking for wearers without the need for external devices. The exoskeleton robot is represented as a center of mass model, and based on this representation, the trajectory generation and controller are discussed, aiming to improve locomotion stability. To assess the stability and dynamic performance, a stable walking experiment with the exoskeleton was conducted, involving a male subject. © 2023 IEEE.

关键词： Exoskeleton (Robotics)

来源：评论

学校读者我要写书评

暂无评论

AMOR: a recipe for building adaptable modular knowledge agents through process feedback 24

AMOR: a recipe for building adaptable modular knowledge agen...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Jian Guan Wei Wu Zujie Wen Peng Xu Hongning Wang Minlie Huang The CoAI group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China and Ant Group Ant Group The CoAI group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9798331314385

The notable success of large language models (LLMs) has sparked an upsurge in building language agents to complete various complex tasks. We present AMOR, an agent framework based on open-source LLMs, which reasons with external knowledge bases and adapts to specific domains through human supervision to the reasoning process. AMOR builds reasoning logic over a finite state machine (FSM) that solves problems through autonomous executions and transitions over disentangled modules. This allows humans to provide direct feedback to the individual modules, and thus naturally forms process supervision. Based on this reasoning and feedback framework, we develop AMOR through two-stage fine-tuning: warm-up and adaptation. The former fine-tunes the LLM with examples automatically constructed from various public datasets, enabling AMoR to generalize across different knowledge environments, while the latter tailors AMOR to specific domains using process feedback. Extensive experiments across multiple domains demonstrate the advantage of AMoR to strong baselines, thanks to its FSM-based reasoning and process feedback mechanism. The code and data are publicly available at https://***/JianGuanTHU/AMOR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient learning of robust quadruped bounding usingpretrained neural networks

引用

IET Cyber-systems and Robotics 2022年第4期4卷 331-338页

作者： Zhicheng Wang Anqiao Li Yixiao Zheng Anhuan Xie Zhibin Li Jun Wu Qiuguo Zhu Institute of Cyber-Systems and Control Zhejiang UniversityZhejiangChina Intelligent Robot Research Center Zhejiang LabZhejiangChina Department of Computer Science University College LondonLondonUK State Key Laboratory of Industrial Control Technology Zhejiang UniversityZhejiangChina

Bounding is one of the important gaits in quadrupedal locomotion for negotiating *** authors proposed an effective approach that can learn robust bounding gaits more efficiently despite its large variation in dynamic body *** authors first pretrained the neural network(NN)based on data from a robot operated by conventional model-based controllers,and then further optimised the pretrained NN via deep reinforcement learning(DRL).In particular,the authors designed a reward function considering contact points and phases to enforce the gait symmetry and periodicity,which improved the bounding *** NN-based feedback controller was learned in the simulation and directly deployed on the real quadruped robot Jueying Mini successfully.A variety of environments are presented both indoors and outdoors with the authors’*** authors’approach shows efficient computing and good locomotion results by the Jueying Mini quadrupedal robot bounding over uneven *** cover image is based on the Research Article Efficient learning of robust quadruped bounding using pretrained neural networks by Zhicheng Wang et al.,https://***/10.1049/csy2.12062.

关键词： legged locomotion reinforcement learning robot learning

来源：评论

学校读者我要写书评

暂无评论

Design a Compliant Pivot with Nearly Zero Axial Drift and High Radial Stiffness 24th

Design a Compliant Pivot with Nearly Zero Axial Drift and Hi...

引用

24th IFToMM China International Conference on Mechanism and Machine Science and Engineering, IFToMM CCMMS 2024

作者： Bai, Ruiyu Ma, Fulei Li, Bo Chen, Guimin State Key Laboratory for Manufacturing Systems Engineering and Shaanxi Key Lab of Intelligent Robots Xi’an Jiaotong University Shaanxi Xi’an710049 China School of Electro-Mechanical Engineering Xidian University Shaanxi Xi’an710071 China

ISBN: (纸本)9789819614639

Compliant pivots are widely used in mechanical systems to provide accurate and repeatable rotations. However, the significant axial drift and low radial stiffness during the rotation of compliant pivots pose great challenges in the design and control of compliant pivot-based mechanisms. To mitigate these difficulties, this paper proposes a novel compliant pivot with nearly zero axial drift and high radial stiffness based on the rigid-body replacement method and symmetric arrangement. By designing a series of symmetric rigid linkages with one degree of freedom and substituting the rigid joints in them with compliant elements, several compliant building blocks are obtained. When arranging these building blocks in a circle, compliant pivots with zeros axial drift are obtained. By discussing the source of compliance in the radial direction, a pivot with high radial stiffness is obtained. The modeling of the pivot using a chained beam constraint model and a nonlinear finite element model demonstrates the kinetostatic properties of the pivot. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Fusing Data-and Model-driven Methods for RUL Prediction in Smart Manufacturing systems

Fusing Data-and Model-driven Methods for RUL Prediction in S...

引用

第43届中国控制会议

作者： Hongjie Cao Wei Xiao Jian Sun Ming-Gang Gan Gang Wang National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Remaining useful life(RUL) is of significance in prognostic and health management(PHM) of machinery equipment. The state-of-the-art RUL prediction methods, including data-driven, model-based, and hybrid approaches, suffer from constraints like incomplete/imprecise physical models, uncertainties in degradation processes, and measurement data noise. To address these constraints, a novel hybrid model-and data-driven RUL prediction approach is proposed in this paper, which leverage the strengths of data-based and model-driven approaches. The proposed method integrates an extended Kalman filter to estimate stochastic degradation model parameters and a multi-head attention transformer to extract information from sensor data. A regression token is introduced to seamlessly fuse the deep learning model and the stochastic filtering method. Numerical experiments conducted with real-world rolling bearing degradation datasets underscore the superiority of the proposed approach compared to competing methodologies.

关键词： Hybrid driven method Remaining useful life prediction Extended Kalman filter Multi-head attention mechanism

来源：评论

学校读者我要写书评

暂无评论

iNet:visual analysis of irregular transition in multivariate dynamic networks

引用

Frontiers of Computer Science 2022年第2期16卷 124-139页

作者： Dongming HAN Jiacheng PAN Rusheng PAN Dawei ZHOU Nan CAO Jingrui HE Mingliang XU Wei CHEN State Key Lab of CAD&CG Zhejiang UniversityHangzhou 310058China Department of Computer Science and Engineering Arizona State UniversityArizona 85287America Tong Ji Intelligent Big Data Visualisation Lab(iDVx Lab) TongJi UniversityShanghai 200082China Department of Computer Science and Technology Zhengzhou UniversityZhengzhou 450001China

Multivariate dynamic networks indicate networks whose topology structure and vertex attributes are evolving along *** are common in multimedia *** detection is one of the essential tasks in analyzing these networks though it is not well *** this paper,we combine a rare category detection method and visualization techniques to help users to identify and analyze anomalies in multivariate dynamic *** conclude features of rare categories and two types of anomalies of rare *** we present a novel rare category detection method,called DIRAD,to detect rare category candidates with *** develop a prototype system called iNet,which integrates two major visualization components,including a glyph-based rare category identifier,which helps users to identify rare categories among detected substructures,a major view,which assists users to analyze and interpret the anomalies of rare categories in network topology and vertex ***,including an algorithm performance evaluation,a case study,and a user study,are conducted to test the effectiveness of proposed methods.

关键词： multivariate dynamic networks rare categories anomaly detection visual analysis

来源：评论

学校读者我要写书评

暂无评论

Fabrication and characterization of high-sensitivity,wide-range,and flexible MEMS thermal flow velocity sensors

引用

Microsystems & Nanoengineering 2024年第4期10卷 139-151页

作者： Min Li Guangzhao Qin Chen Jia Danyu Zhang Zhikang Li Xiangguang Han Shusheng Xu Libo Zhao Guoxi Luo Cunlang Liu Ping Yang Qijing Lin State Key Laboratory for Manufacturing Systems Engineering International Joint Laboratory for Micro/Nano Manufacturing and Measurement TechnologiesXi’an Jiaotong University(Yantai)Research Institute for Intelligent Sensing Technology and SystemXi’an Jiaotong UniversityXi’an 710049China School of Instrument Science and Technology Xi’an Jiaotong UniversityXi’an 710049China Shandong Laboratory of Advanced Materials and Green Manufacturing at Yantai Yantai 264000China Brightstone Innovation(Yantai)Research Institute for Micronano Sensing Technology Yantai 264006China Xi’an Jingwei Sensing Technology Co. Ltd.Xi’an 712000China

With the rapid development of various fields,including aerospace,industrial measurement and control,and medical monitoring,the need to quantify flow velocity measurements is *** is difficult for traditional flow velocity sensors to fulfill accuracy requirements for velocity measurements due to their small ranges,susceptibility to environmental impacts,and ***,to optimize sensor performance,a flexible microelectromechanical system(MEMS)thermal flow sensor is proposed that combines the working principles of thermal loss and thermal temperature difference and utilizes a flexible cavity substrate made of a low-thermal-conductivity polyimide/SiO_(2)(PI/SiO_(2))composite porous film to broaden the measurement range and improve the *** measurement results show that the maximum measurable flow velocity can reach 30 m/s with a resolution of 5.4mm/*** average sensitivities of the sensor are 59.49 mV/(m s−1)in the medium-to-low wind velocity range of 0–2 m/s and 467.31 mV/(m s^(−1))in the wind velocity range of 2–30 m/*** sensor proposed in this work can enable new applications of flexible flow sensors and wearable devices.

关键词： flow thermal utilize

来源：评论

学校读者我要写书评

暂无评论

Design, Analysis, and Experiment of a Novel Ultrasonic Printing System

Design, Analysis, and Experiment of a Novel Ultrasonic Print...

引用

2022 IEEE International Conference on Manipulation, Manufacturing and Measurement on the Nanoscale, 3M-NANO 2022

作者： Pei, Zhichao Zhao, Haoxiang Li, Dongjie Wang, Lefeng Rong, Weibin Sun, Lining Harbin Institute of Technology State Key Laboratory of Robotics and Systems Harbin China Harbin University of Science and Technology Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration Harbin China

ISBN: (数字)9781665475433

ISBN: (纸本)9781665475433

Ultrasonic-driven printing technology is widely used in bioprinting because of its high precision, good biocompatibility, and low cost. However, the conventional ultrasonic printing technology still has problems such as cross-contamination of bio-ink during storage, transportation, and processing, and cumbersome ink replacement process. Therefore, a new ultrasonic printing device is developed in this paper, which uses PZT plates as the driving element. And a fluid sub-system has been fabricated based on the self-made glass micro-nozzle, which is connected to the drive element using ultrasonic couplant gel. The separation of the fluid system and the drive system has been realized through the modular design, thereby realizing the rapid replacement of different inks and this relatively independent fluid system is of great benefit to better sealing and aseptic operation. In addition, a digital model is built to analyze its working mechanism. And an experimental system is established to characterize the performance of the device. The results show that the system can generate droplets stably and accurately, and the droplet volume can be controlled by the excitation voltage amplitude and pulse width. © 2022 IEEE.

关键词： Biocompatibility

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning Method for Tractor-trailer System Based on Nonlinear Model Predictive Control

Trajectory Planning Method for Tractor-trailer System Based ...

引用

第43届中国控制会议

作者： Bobo Jia Liang Gao Daiwei Li Yi Yang Mengyin Fu Shanshan Xie National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology School of Automation Nanjing University of Science and Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The tractor-trailer system has the characteristics of high state dimension,complex constraints and poor internal stability in trajectory ***,this paper proposed a trajectory planning method for tractor-trailer system based on nonlinear model predictive control(NMPC) in static and dynamic ***,an NMPC optimization problem is formulated by constructing performance indicators and integrating the constraints of the ***,an approximate optimal path is found as a reference solution for the warm start of the optimization problem by RRT* sampling in high dimensional state ***,the NMPC problem is solved by Optimization Engine(OpEn) ***,simulation in different scenarios demonstrated the effectiveness and efficiency of the proposed method.

关键词： Tractor-trailer System Trajectory Planning Nonlinear Model Predictive Control

来源：评论

学校读者我要写书评

暂无评论

Generalized-Extended-state-Observer and Equivalent-Input-Disturbance Methods for Active Disturbance Rejection: Deep Observation and Comparison

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 957-968页

作者： Jinhua She Kou Miyamoto Qing-Long Han Min Wu Hiroshi Hashimoto Qing-Guo Wang School of Engineering Tokyo University of TechnologyHachiojiTokyo 192-0982Japan K.Miyamoto is with the Institute of Technology Shimizu CorporationKotoTokyo 135-0044Japan School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourneVIC 3122Australia School of Automation China University of GeosciencesWuhan 430074 Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of EducationWuhan 430074China School of Industrial Technology Advanced Institute of Industrial TechnologyTokyo 140-0011Japan Institute of Artificial Intelligence and Future Networks Beijing Normal UniversityZhuhai 519087 Guangdong Key Lab of AI and Multi-Modal Data Processing Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNUHKBU United International College Zhuhai 519087China

Active disturbance-rejection methods are effective in estimating and rejecting disturbances in both transient and steady-state *** paper presents a deep observation on and a comparison between two of those methods:the generalized extended-state observer(GESO)and the equivalent input disturbance(EID)from assumptions,system configurations,stability conditions,system design,disturbance-rejection performance,and extensibility.A time-domain index is introduced to assess the disturbance-rejection performance.A detailed observation of disturbance-suppression mechanisms reveals the superiority of the EID approach over the GESO method.A comparison between these two methods shows that assumptions on disturbances are more practical and the adjustment of disturbance-rejection performance is easier for the EID approach than for the GESO method.

关键词： Active disturbance-rejection control(ADRC) disturbance observer(DOB) equivalent input disturbance(EID) extendedstate observer(ESO) generalized extended-state observer(GESO)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：