检索结果-内蒙古大学图书馆

A policy gradient algorithm integrating long and short-term rewards for soft continuum arm control

Science China(Technological Sciences) 2022年第10期65卷 2409-2419页

作者： DONG Xiang ZHANG Jing CHENG Long XU WenJun SU Hang MEI Tao School of Electrical Engineering and Automation Anhui UniversityHefei 230601China State Key Laboratory for Control and Management of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Robotics Research Center Peng Cheng LaboratoryShenzhen 518055China

The soft continuum arm has extensive application in industrial production and human life due to its superior safety and flexibility. Reinforcement learning is a powerful technique for solving soft arm continuous control problems, which can learn an effective control policy with an unknown system model. However, it is often affected by the high sample complexity and requires huge amounts of data to train, which limits its effectiveness in soft arm control. An improved policy gradient method, policy gradient integrating long and short-term rewards denoted as PGLS, is proposed in this paper to overcome this issue. The shortterm rewards provide more dynamic-aware exploration directions for policy learning and improve the exploration efficiency of the algorithm. PGLS can be integrated into current policy gradient algorithms, such as deep deterministic policy gradient(DDPG). The overall control framework is realized and demonstrated in a dynamics simulation environment. Simulation results show that this approach can effectively control the soft arm to reach and track the targets. Compared with DDPG and other model-free reinforcement learning algorithms, the proposed PGLS algorithm has a great improvement in convergence speed and performance. In addition, a fluid-driven soft manipulator is designed and fabricated in this paper, which can verify the proposed PGLS algorithm in real experiments in the future.

关键词： soft arm control Cosserat rod deep reinforcement learning policy gradient algorithm high sample complexity

来源：评论

学校读者我要写书评

暂无评论

Few-shot object detection via class encoding and multi-target decoding

引用

IET Cyber-systems and robotics 2023年第2期5卷 1-14页

作者： Xueqiang Guo Hanqing Yang Mohan Wei Xiaotong Ye Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhouChina Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province HangzhouChina

The task of few‐shot object detection is to classify and locate objects through a few annotated *** many studies have tried to solve this problem,the results are still not *** studies have found that the class margin significantly impacts the classification and representation of the targets to be *** methods use the loss function to balance the class margin,but the results show that the loss‐based methods only have a tiny improvement on the few‐shot object detection *** this study,the authors propose a class encoding method based on the transformer to balance the class margin,which can make the model pay more attention to the essential information of the features,thus increasing the recognition ability of the ***,the authors propose a multi‐target decoding method to aggregate RoI vectors generated from multi‐target images with multiple support vectors,which can significantly improve the detection ability of the detector for multi‐target *** on Pascal visual object classes(VOC)and Microsoft Common Objects in Context datasets show that our proposed Few‐Shot Object Detection via Class Encoding and Multi‐Target Decoding significantly improves upon baseline detectors(average accuracy improvement is up to 10.8%on VOC and 2.1%on COCO),achieving competitive *** general,we propose a new way to regulate the class margin between support set vectors and a way of feature aggregation for images containing multiple objects and achieve remarkable *** method is implemented on mmfewshot,and the code will be available later.

关键词： Class Margin Few-Shot Object Detection Multi-Target Transformer

来源：评论

学校读者我要写书评

暂无评论

Few-shot working condition recognition of a sucker-rod pumping system based on a 4-dimensional time-frequency signature and meta-learning convolutional shrinkage neural network

引用

Petroleum Science 2023年第2期20卷 1142-1154页

作者： Yun-Peng He Chuan-Zhi Zang Peng Zeng Ming-Xin Wang Qing-Wei Dong Guang-Xi Wan Xiao-Ting Dong State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyangLiaoning 110016China Key Laboratory of Networked Control Systems Chinese Academy of SciencesShenyangLiaoning 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyangLiaoning 110169China University of Chinese Academy of Sciences Beijing100049China Shenyang University of Technology ShenyangLiaoning 110870China School of Automation and Electrical Engineering Shenyang Ligong UniversityShenyangLiaoning 110159China

The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep learning working condition recognition model for pumping wells by obtaining enough new working condition samples is expensive. For the few-shot problem and large calculation issues of new working conditions of oil wells, a working condition recognition method for pumping unit wells based on a 4-dimensional time-frequency signature (4D-TFS) and meta-learning convolutional shrinkage neural network (ML-CSNN) is proposed. First, the measured pumping unit well workup data are converted into 4D-TFS data, and the initial feature extraction task is performed while compressing the data. Subsequently, a convolutional shrinkage neural network (CSNN) with a specific structure that can ablate low-frequency features is designed to extract working conditions features. Finally, a meta-learning fine-tuning framework for learning the network parameters that are susceptible to task changes is merged into the CSNN to solve the few-shot issue. The results of the experiments demonstrate that the trained ML-CSNN has good recognition accuracy and generalization ability for few-shot working condition recognition. More specifically, in the case of lower computational complexity, only few-shot samples are needed to fine-tune the network parameters, and the model can be quickly adapted to new classes of well conditions.

关键词： Few-shot learning Indicator diagram Meta-learning Soft thresholding Sucker-rod pumping system Time–frequency signature Working condition recognition

来源：评论

学校读者我要写书评

暂无评论

A New Recursive Composite Adaptive controller for Robot Manipulators

引用

Space(Science & Technology) 2021年第1期2021卷 77-83页

作者： Jianfei Li Yaobing Wang Zhiyong Liu Xin Jing Chengwei Hu The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Beijing Key Laboratory of Intelligent Space Robotic System Technology and Applications Beijing Institute of Spacecraft System EngineeringBeijing 100094China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

In this paper,a new recursive implementation of composite adaptive control for robot manipulators is *** investigate the recursive composite adaptive algorithm and prove the stability directly based on the Newton-Euler equations in matrix form,which,to our knowledge,is the first result on this point in the *** proposed algorithm has an amount of computation O(n),which is less than any existing similar algorithms and can satisfy the computation need of the complicated multidegree *** manipulator of the Chinese Space Station is employed as a simulation example,and the results verify the effectiveness of this proposed recursive algorithm.

关键词： Robot manipulators robot

来源：评论

学校读者我要写书评

暂无评论

Decoding split-frequency representation for cross-scale tracking

引用

Neural Networks 2025年 189卷

作者： Yuanming Zhang Hao Sun State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin 150001 China Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin 150001 China Bio-Computing Research Center Harbin Institute of Technology Shenzhen Shenzhen 518055 China

Learning tailored target representations for tracking is a promising direction in visual object tracking. Most state-of-the-art methods utilize autoencoders to generate representations by reconstructing the target’s appearance. However, these reconstructions are often augmented to mimic scale jitter and alteration, neglecting physical scale observations such as those in aerial videos. This article addresses the challenge of representation learning for cross-scale tracking in generalized scenarios. Specifically, we incorporate target scale directly into the positional encoding, indicating scale through relative pixel density rather than the conventional metric of image resolution. This scale-aware encoding is then integrated into the proposed asymptotic hierarchy of decoders, designed to reconstruct representations by emphasizing the restoration of high- and low-frequency features at large and tiny scales. The reconstruction process is guided by supervised learning using split losses, enabling the generation of robust cross-scale representations for generic objects. Extensive experiments on six benchmarks — GOT-10k, LaSOT, TrackingNet, DTB70, UAV123, and TNL2K — validate the superior performance of our method. Additionally, our tracker achieves a remarkable speed of 123 frames per second on a Graphics Processing Unit, surpassing the previous best autoencoder-based tracker. The code and raw results will be made publicly available at: https://***/pellab/DSC .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parallel Driving in CPSS:A Unified Approach for Transport Automation and Vehicle Intelligence

引用

IEEE/CAA Journal of Automatica Sinica 2017年第4期4卷 577-587页

作者： Fei-Yue Wang Nan-Ning Zheng Dongpu Cao Clara Marina Martinez Li Li Teng Liu IEEE State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Advanced Vehicle Engineering Center Cranfield University Department of Automation Tsinghua University State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Qingdao Huituo Intelligent Machine Company

The emerging development of connected and automated vehicles imposes a significant challenge on current vehicle control and transportation systems. This paper proposes a novel unified approach, Parallel Driving, a cloud-based cyberphysical-social systems(CPSS) framework aiming at synergizing connected automated driving. This study first introduces the CPSS and ACP-based intelligent machine systems. Then the parallel driving is proposed in the cyber-physical-social space,considering interactions among vehicles, human drivers, and information. Within the framework, parallel testing, parallel learning and parallel reinforcement learning are developed and concisely reviewed. Development on intelligent horizon(iHorizon)and its applications are also presented towards parallel *** proposed parallel driving offers an ample solution for achieving a smooth, safe and efficient cooperation among connected automated vehicles with different levels of automation in future road transportation systems.

关键词： ACP theory connected automated driving cyber-physical-social systems(CPSS) iHorizon parallel driving parallel horizon parallel learning parallel reinforcement learning parallel testing

来源：评论

学校读者我要写书评

暂无评论

Anti-windup-based Dynamic controller Synthesis for Lipschitz systems under Actuator Saturation

引用

IEEE/CAA Journal of Automatica Sinica 2015年第4期2卷 358-365页

作者： Naizhou Wang Hailong Pei Yong Tang Key Laboratory of Autonomous Systems and Networked Control Ministry of EducationSouth China University of Technology Key Laboratory of Surface Functional Structure Manufacturing of Guangdong Higher Education Institutes School of Mechanical and Automotive EngineeringSouth China University of Technology

This paper presents a new method for simultaneous synthesis of dynamic controller and static anti-windup compensator for saturated Lipschitz systems. Thanks to the reformulated Lipschitz property, the Lipschitz systems can be transformed into LPV (linear parameter-varying) systems whose system matrices are affine in a parameter matrix. Based on the modified sector condition dealing with saturation nonlinearity, the design of a nonlinear anti-windup-based controller leads to the solvability of a set of bilinear matrix inequalities (BMI) on the vertices of a bounded convex set which can be solved by the so-called iterative linear matrix inequality (ILMI) algorithm. A numerical example is presented to illustrate the effectiveness of the proposed method. © 2014 Chinese Association of Automation.

关键词： controllers Iterative methods Linear algebra Matrix algebra Numerical methods Set theory Synthesis (chemical)

来源：评论

学校读者我要写书评

暂无评论

Event-triggered state estimation for T-S fuzzy affine systems based on piecewise Lyapunov-Krasovskii functionals

引用

control Theory and Technology 2019年第1期17卷 99-111页

作者： Meng WANG Jianbin QIU Gang FENG Department of Biomedical Engineering City University of Hong Kong Kowloon Hong Kong China State Key Laboratory of Robotics and Systems & Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin Heilongjiang 150080 China

This paper investigates the problem of event-triggered H∞state estimation for Takagi-Sugeno (T-S) fuzzy affine systems. The objective is to design an event-triggered scheme and an observer such that the resulting estimation error system is asymptotically stable with a prescribed H∞performance and at the same time unnecessary output measurement transmission can be reduced. First, an event-triggered scheme is proposed to determine whether the sampled measurements should be transmitted or not. The output measurements, which trigger the condition, are supposed to suffer a network-induced time-varying and bounded delay before arriving at the observer. Then, by adopting the input delay method, the estimation error system can be reformulated as a piecewise delay system. Based on the piecewise Lyapunov-Krasovskii functional and the Finsler's lemma, the event-triggered H∞observer design method is developed. Moreover, an algorithm is proposed to co-design the observer gains and the event-triggering parameters to guarantee that the estimation error system is asymptotically stable with a given disturbance attenuation level and the signal transmission rate is reduced as much as possible. Simulation studies are given to show the effectiveness of the proposed method.

关键词： Takagi-Sugeno (T-S) fuzzy affine systems event-triggered scheme, piecewise Lyapunov-Krasovskii functional, state estimation

来源：评论

学校读者我要写书评

暂无评论

Failure mechanism and tunable mechanical responses of structured fabrics

引用

Composites Communications 2025年 57卷

作者： Zhantu Gan Weining Mao Qianpeng He Hao Tang Yifan Wang Nan Hu State Key Laboratory of Subtropical Building and Urban Science Guangzhou 510641 China School of Civil Engineering and Transportation South China University of Technology Guangzhou 510000 China School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore 639798 Singapore Key Laboratory of Autonomous Systems and Networked Control Ministry of Education South China University of Technology Guangzhou 510640 China

Structured fabrics have great potential in designing intelligent devices with their reconfigurable features and tunable mechanical responses, but existing studies have primarily explored stiffness and deformations without focusing on their load-bearing capacities. Here, we investigate the failure mechanism and mechanical responses of a structured fabric formed under various combinations of geometric features. Guided by experimental tests, we confirm the influence of geometric features that lead to rod fracture or membrane tearing due to different interaction mechanisms. Our findings indicate that the specific ultimate bearing capacity can be tuned within an order of magnitude with different parameter combinations. This study offers valuable insights into the governing factors in controlling the load-bearing capabilities of structured fabrics and lays the foundation for developing on-demand impact-protecting composites across fields.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and simulation of a cable-pulley-based transmission for artificial ankle joints

引用

Frontiers of Mechanical Engineering 2016年第2期11卷 170-183页

作者： Huaxin LIU Marco CECCARELLI Qiang HUANG Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing 100081 China Key Laboratory of Biomimetic Robots and Systems (Beijing Institute of Technology) Ministry of Education Beijing 100081 China Laboratory of Robotics and Mechatronics (LARM) DICeM University of Cassino and South Latium Cassino 03043 Italy Beijing Innovation Center for Intelligent Robots and Systems Beijing 100081 China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing 100081 China

In this paper, a mechanical transmission based on cable pulley is proposed for human-like actuation in the artificial ankle joints of human-scale. The anatomy articular characteristics of the human ankle is discussed for proper biomimetic inspiration in designing an accurate, efficient, and robust motion control of artificial ankle joint devices. The design procedure is presented through the inclusion of conceptual considerations and design details for an interactive solution of the transmission system. A mechanical design is elaborated for the ankle joint angular with pitch motion. A multi-body dynamic simulation model is elaborated accordingly and evaluated numerically in the ADAMS environment. Results of the numerical simulations are discussed to evaluate the dynamic performance of the proposed design solution and to investigate the feasibility of the proposed design in future applications for humanoid robots.

关键词： biomimetic designs ankle joints cable-pulleytransmissions multi-body dynamic simulation numericalcharacterization

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

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

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：