检索结果-内蒙古大学图书馆

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Qi, Xiangyuan He, Zhen Wang, Qiang Department of Control Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (纸本)9781665464543

Human action generation has shown critical value in both industry application and academic research, especially fine-grained skeleton-based action generation. At present, there are several main ways to achieve fine-grained skeleton-based action generation. In this work, we utilize a generative adversarial network with in-betweening, in order to generate natural and continuous skeleton sequences and better capture complex motion details. In-betweening can be viewed as a prediction task based on the past and future context. Besides, it is convenient to control the result in a personalized way and combine the framework with other network structures to further improve the performance. In particular, two simple discriminators are applied on different timescales and LSTM serves as the foundation of the action generator because of its capability of effectively capturing long-term dependencies and processing sequence data of different lengths. The target noise added to the input of the generator can contribute to the robustness of the system and further improve the performance. Moreover, a novel Tai Chi dataset composed of fine-grained skeleton-based action data is created using high quality motion capture technology. The model is evaluated on two fine-grained skeleton-based datasets, LaFAN1 and Tai Chi, which contain common daily actions and professional sports actions respectively, and it achieves superior performance both qualitatively and quantitatively. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning-based dynamics control of biped reconfigurable robots for standing balancing tasks

Reinforcement learning-based dynamics control of biped recon...

引用

2024 China Automation Congress, CAC 2024

作者： Pan, Qiang Yao, Yuan Li, Yuanchun An, Tianjiao Dong, Bo Ma, Bing Department of Control Science and Engineering Changchun University of Technology Changchun China

ISBN: (纸本)9798350368604

This paper presents a standing balance control scheme for biped reconfigurable robots (BRRs) via neuro-dynamic programming (NDP) method. First, a global dynamic model of BRRs is established, in which the torso model is approximated by utilizing the virtual model control (VMC). Then, the cost function is developed including the system state, control law, and the coupling torque between the torso and legs, to construct the optimal standing balance control framework. On the basis of NDP algorithm, the near-optimal standing balance control strategy is developed by designing the critic-only neural network to solve the Hamilton-Jacobi-Bellman equation. Then, the tracking error of closed-loop BRRs is proved to be uniformly ultimately bounded. Finally, a series of experimental studies are carried out on the self-designed hyper-redundant BRRs experimental platform to show the effectiveness of the proposed control method. © 2024 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Adaptive Dynamic Programming-based Approximate Optimal control for Collaborative Robot via Quintic Polynomial Planning 7

Adaptive Dynamic Programming-based Approximate Optimal Contr...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Dong, Bo Pan, Jinlong An, Tianjiao Wang, Chong Ma, Bing Changchun University of Technology Department of Control Science and Engineering Changchun China

ISBN: (纸本)9798350363173

In this paper, we investigate adaptive dynamic programming-based quintic polynomial trajectory planning and optimal tracking control for collaborative robotic systems. According to polynomial interpolation, a quintuple polynomial trajectory planning method is proposed, which solves the problems of non-smooth angular velocity changes and jumps in acceleration with cubic polynomial interpolation. In addition, the optimal control strategy is solved by adaptive dynamic programming. Lyapunov functions are introduced to prove the stability of the control system. At last, the simulation results verify the truth of the above theory. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第12期10卷 2233-2247页

作者： Hongyu Ding Yuanze Tang Qing Wu Bo Wang Chunlin Chen Zhi Wang the Department of Control Science and Intelligence Engineering School of Management and EngineeringNanjing UniversityNanjing 210093China the Department of Power Engineering and Process Machinery School of Mechanical and Power EngineeringEast China University of Science and TechnologyShanghai 200237China IEEE

Goal-conditioned reinforcement learning(RL)is an interesting extension of the traditional RL framework,where the dynamic environment and reward sparsity can cause conventional learning algorithms to *** shaping is a practical approach to improving sample efficiency by embedding human domain knowledge into the learning *** reward shaping methods for goal-conditioned RL are typically built on distance metrics with a linear and isotropic distribution,which may fail to provide sufficient information about the ever-changing environment with high *** paper proposes a novel magnetic field-based reward shaping(MFRS)method for goal-conditioned RL tasks with dynamic target and *** by the physical properties of magnets,we consider the target and obstacles as permanent magnets and establish the reward function according to the intensity values of the magnetic field generated by these *** nonlinear and anisotropic distribution of the magnetic field intensity can provide more accessible and conducive information about the optimization landscape,thus introducing a more sophisticated magnetic reward compared to the distance-based ***,we transform our magnetic reward to the form of potential-based reward shaping by learning a secondary potential function concurrently to ensure the optimal policy invariance of our *** results in both simulated and real-world robotic manipulation tasks demonstrate that MFRS outperforms relevant existing methods and effectively improves the sample efficiency of RL algorithms in goal-conditioned tasks with various dynamics of the target and obstacles.

关键词： Dynamic environments goal-conditioned reinforcement learning magnetic field reward shaping

来源：评论

学校读者我要写书评

暂无评论

Enhancement of ionic conductivity and fracture toughness by infiltrating porous Li_(0.33)La_(0.56)TiO_(3) pellets

引用

Journal of Rare Earths 2024年第2期42卷 392-398,I0006页

作者： Xiaojuan Lu Mingyang Duan Jingyu Xiang Yuning Liang Songtao Liu Hebei Key Lab of Power Plant Flue Gas Multi-Pollutants Control Department of Environmental Science and EngineeringNorth China Electric Power UniversityBaoding071003China

Although solid-state lithium electrolytes have the potential to reduce the safety issues associated with organic liquid electrolytes,disadvantages such as low total conductivity,large interface impedance,and delamination of the interface due to cyclic stress still need to be *** solid-state lithium-ion conductor Li_(0.33)La_(0.56)TiO_(3)(LLTO) was prepared via a hydrothermal route by using CTAB as templates in this *** LLTO with micro-porous channels was obtained and the total conductivity is comparable to the non-porous *** LLTO pellets are infiltrated with the non-porous LLTO precursor solution,and the total conductivities of the infiltrated porous LLTO are all higher than those without *** infiltration,the porous LLTO calcined at 600℃ achieves the highest total conductivity,7.88×10^(-5) S/*** fracture toughness of the infiltrated LLTO is higher than that of the non-porous *** results demonstrate a new way to prepare solid-state lithium-ion conductors with high ionic conductivity and great tolerance to cyclic stress.

关键词： Perovskite Porous material Infiltration Ionic conductors Fracture toughness Rare earths

来源：评论

学校读者我要写书评

暂无评论

Radar style transfer for metric robot localisation on lidar maps

引用

CAAI Transactions on Intelligence Technology 2023年第1期8卷 139-148页

作者： Huan Yin Yue Wang Jun Wu Rong Xiong College of Control Science and Engineering Zhejiang UniversityHangzhouChina Department of Electronic and Computer Engineering Hong Kong University of Science and TechnologyKowloonHong KongChina

Lidar and visual data are affected heavily in adverse weather conditions due to sensing mechanisms,which bring potential safety hazards for vehicle *** sensing is desirable to build a more robust navigation *** this paper,a cross-modality radar localisation on prior lidar maps is ***,the proposed workflow consists of two parts:first,bird's-eye-view radar images are transferred to fake lidar images by training a generative adversarial network *** with online radar scans,a Monte Carlo localisation framework is built to track the robot pose on lidar *** whole online localisation system only needs a rotating radar sensor and a pre-built global lidar *** the experimental section,the authors conduct an ablation study on image settings and test the proposed system on Oxford Radar Robot Car *** promising results show that the proposed localisation system could track the robot pose successfully,thus demonstrating the feasibility of radar style transfer for metric robot localisation on lidar maps.

关键词： lidar local maps

来源：评论

学校读者我要写书评

暂无评论

EASI: Evolutionary Adversarial Simulator Identification for Sim-to-Real Transfer 38

EASI: Evolutionary Adversarial Simulator Identification for ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Dong, Haoyu Fu, Huiqiao Xu, Wentao Zhou, Zhehao Chen, Chunlin Department of Control Science and Intelligent Engineering School of Management and Engineering Nanjing University China

Reinforcement Learning (RL) controllers have demonstrated remarkable performance in complex robot control tasks. However, the presence of reality gap often leads to poor performance when deploying policies trained in simulation directly onto real robots. Previous sim-to-real algorithms like Domain Randomization (DR) requires domain-specific expertise and suffers from issues such as reduced control performance and high training costs. In this work, we introduce Evolutionary Adversarial Simulator Identification (EASI), a novel approach that combines Generative Adversarial Network (GAN) and Evolutionary Strategy (ES) to address sim-to-real challenges. Specifically, we consider the problem of sim-to-real as a search problem, where ES acts as a generator in adversarial competition with a neural network discriminator, aiming to find physical parameter distributions that make the state transitions between simulation and reality as similar as possible. The discriminator serves as the fitness function, guiding the evolution of the physical parameter distributions. EASI features simplicity, low cost, and high fidelity, enabling the construction of a more realistic simulator with minimal requirements for real-world data, thus aiding in transferring simulated-trained policies to the real world. We demonstrate the performance of EASI in both sim-to-sim and sim-to-real tasks, showing superior performance compared to existing sim-to-real algorithms. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time-Varying Formation Tracking control of Heterogeneous Multi-Agent Systems With Intermittent Communications and Directed Switching Networks

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 294-296页

作者： Yuhan Wang Zhuping Wang Hao Zhang Huaicheng Yan the Shanghai Research Institute for Intelligent Autonomous Systems Tongji University the National Key Laboratory of Autonomous Intelligent Unmanned Systems the Frontiers Science Center for Intelligent Autonomous System of Ministry of Education the College of Electronic and Information Engineering the Department of Control Science and Engineering Tongji University the Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education the School of Information Science and Engineering East China University of Science and Technology

Dear Editor,This letter is concerned with the problem of time-varying formation tracking for heterogeneous multi-agent systems(MASs) under directed switching networks. For this purpose, our first step is to present so... 详细信息

关键词： Switches Topology Observers Formation control Event detection Switched systems Multi-agent systems control theory Autonomous systems Stability

来源：评论

学校读者我要写书评

暂无评论

WAVELET BASED INDEPENDENT COMPONENT FEATURES FOR CLASSIFICATION OF LOWER-LIMB MOVEMENTS FROM SURFACE EMG SIGNALS

Biomedical Sciences Instrumentation

引用

Biomedical sciences Instrumentation 2024年第1期60卷 109-115页

作者： Madan, S. Arunganesh, K. Sivakumaran, N. Karthick, P.A. Department of Instrumentation and Control Engineering National Institute of Technology Tiruchirappalli Tamilnadu India Periyar Maniammai Institute of Science and Technology Thanjavur India

Surface electromyography is a non-invasive technique of measuring the electrical activities of contracting skeletal muscles. Recently, there are several attempts have been made to actively decode these signals for the applications such as myoelectric control, rehabilitation and sports mechanics. However, the decoding of the surface EMG signals remains a challenging task for the researchers because of its randomness associated with the signal generation mechanism. Further, the stochastic nature of these signals contributes to the non-stationary and multicomponent variations in the signals and this makes the analysis highly complex. In this work an attempt has been made to develop a non-stationary signal processing framework using wavelet transform (WT) and independent component analysis (ICA) for the recognizing standing and sitting tasks from surface EMG. For this purpose, the surface EMG signals of vastus medialis recorded from fourteen untrained subjects are considered for the analysis the signals are preprocessed and subjected to wavelet transform and ICA. In addition to this, the time and frequency domain measures namely, mean average value (MAV), root-mean-square (RMS), zerocrossing (ZC), mean frequency (MNF) and median frequency (MDF) also are used to develop the classification models based on support vector machine (SVM). The models are validated using five-fold cross validation. The results show that the time, frequency and time-frequency features show considerable variations in both the tasks. All extracted features exhibits significant difference in sitting and standing tasks. The proposed SVM based WT-ICA technique is found to achieve a classification accuracy of 92.31%. The performances of time and frequency domain metrics are found to lower than timefrequency approaches. It appears that the proposed technique is capable of handling the complex non-stationary EMG effectively. It could be used for controlling external devices such as prosthetic legs. © 20

关键词： Myoelectrically controlled prosthetics

来源：评论

学校读者我要写书评

暂无评论

Event-based sliding mode control under denial-of-service attacks

引用

science China(Information sciences) 2022年第6期65卷 125-141页

作者： Yingxin TIAN Xiang LI Bo DONG Yabin GAO Ligang WU Department of Control Science and Engineering Harbin Institute of Technology School of Software Harbin Institute of Technology

This paper deals with the problem of estimator-based sliding mode control against denial-of-service(DoS) attacks and discrete events via a time-delay approach. A networked system is considered an uncertain dynamical system with matched and mismatched perturbations and exogenous disturbance in the network environment. A network-resource-aware event-triggering mechanism is designed with aperiodically releasing system measurements. Furthermore, to describe the DoS attack duration and inter-event time, a time-delay modeling approach considers the DOS attack duration and inter-event time as a “time delay” of the measurements between the sensor and controller over the network is proposed. Consequently, an intervaltime-delay system with uncertainties is formulated. A state-observer-based sliding mode controller, by which the ideal sliding mode can be achieved, is proposed against the DoS attacks. The resulting sliding motion is proved to be robust and stable with an Lgain performance. Finally, the effectiveness and applicability of the present sliding mode control are validated in a simulated pendulum system.

关键词： sliding mode control time delay uncertain system state observer event trigger

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：