检索结果-内蒙古大学图书馆

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Jincun Liu Zhenna Liu Zhengxing Wu Junzhi Yu State Key Laboratory for Turbulence and Complex Systems BIC-ESAT College of Engineering Peking University Beijing China Shandong Labor Vocational and Technical College Jinan China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728172934

ISBN: (纸本)9781728172941

In this paper, a novel improved deep reinforcement learning (DRL) strategy is utilized to solve the three-dimensional path-following control problem for an underactuated robotic dolphin in order to meet the complex and intractable hydrodynamic model. Firstly, a brief overview of the developed robotic dolphin consisting of two-degree-of-freedom paired pectoral fins and the slider-crank-based flapping two-joint tail is introduced. After that, path-following controller includes a novel lookahead-based guidance law, decoupling motion strategy, and a deep deterministic policy gradient algorithm based on the the prior knowledge is proposed. The novel lookahead based 3-D LOS guidance law is employed to transform the 3-D waypoints to the desired heading and pitch angles with its simplicity, intuitiveness, and small computational footprint. Finally, the effectiveness of the proposed controller is demonstrated after numerous simulations. It will offer a rich vein of insight for the real-time task execution in bioinspired underwater robots.

关键词： Robots Dolphins Sports Oscillators Biological system modeling Turning Aerospace electronics

来源：评论

学校读者我要写书评

暂无评论

Calibration of Agent-Based Model Using Reinforcement Learning

Calibration of Agent-Based Model Using Reinforcement Learnin...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Bing Song Gang Xiong Songmin Yu Peijun Ye Xisong Dong Yisheng Lv The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Chinese Academy of Sciences Beijing China Fraunhofer Institute for Systems and Innovation Research Breslauer Germany

In the research and application of Agent-Based Models (ABM), parameter calibration is an important content. Based on the existing state transfer equations that link the micro-parameters and macro-states of the multi-agent system, this paper further proposes to introduce Reinforcement Learning when calibrating the parameters. The state transfer of the agent after learning is used to calibrate the micro-parameters of ABM, and the interaction between each agent and multiple other agents is expressed as the parameters of the agent. The application case study of population migration demonstrates that our method can achieve high accuracy and low computational complexity.

关键词： Learning systems Microscopy Digital twin Sociology Reinforcement learning Mathematical models Calibration

来源：评论

学校读者我要写书评

暂无评论

Visual Pencil: Design of Portable Human-Computer Interaction Based on 2D Visual Tracking

Visual Pencil: Design of Portable Human-Computer Interaction...

引用

IEEE International Conference on Mechatronics and automation

作者： Ru Tong Tianzhu Wang Junzhi Yu State Key Lab Management and Control for Complex Systems Institute of Automation CAS Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China College of Engineering Peking University Beijing China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

Convenient and efficient human-computer interaction has always been the goal pursued by researchers. In this paper, we present a vision-based handwriting interaction device for non-touch screens called Visual Pencil. Unlike the conventional interactive method that captures the user's gestures using a motionless visual sensor, Visual Pencil directly mounts the visual sensor in the device. More specifically, the visual data are processed by the feature detection algorithm, and the movement of the pen tip in a 2D plane is calculated, so as to control the cursor and achieve the purpose of interaction. We further define performance indicators for evaluating the design and select more reasonable parameters through specific experiments to achieve the best interaction performance. The experiments verify that the proposed design is able to fulfill the desired operations. The significance of this design lies in that it integrates the functions of the mouse and smart pen, thus removing the requirement of more auxiliary equipment. This work sheds light on the interaction with non-touch screen computers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed Formation of Autonomous Underwater Vehicles with Unreliable Switching Topologies and Transmission Delays

Distributed Formation of Autonomous Underwater Vehicles with...

引用

第三十九届中国控制会议

作者： Chao Ma Wei Wu Yidao Ji Hang Fu School of Mechanical Engineering University of Science and Technology Beijing State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Automation and Electrical Engineering University of Science and Technology Beijing

This paper investigates the formation problem of autonomous underwater vehicles with unreliable switching communication topologies and time-varying transmission delays. More precisely, the switching topologies contains achievable and unachievable sub-topologies, which can better describe the practical underwater communication environment. By performing model transformation and constructing appropriate multiple Lyapunov-function method, sufficient conditions are established based on admissible edge-dependent average dwell time, such that the desired formation configuration can be achieved with transmission delays. Finally, an illustrative example is given at last to verify the effectiveness of the main results.

关键词： Distributed formation Autonomous underwater vehicles Switching topologies Admissible edge-dependent switching

来源：评论

学校读者我要写书评

暂无评论

Dynamic horizon value estimation for model-based reinforcement learning

arXiv

引用

arXiv 2020年

作者： Wang, Junjie Zhang, Qichao Zhao, Dongbin Zhao, Mengchen Hao, Jianye State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Huawei Noah’s Ark Lab Beijing China

Existing model-based value expansion methods typically leverage a world model for value estimation with a fixed rollout horizon to assist policy learning. However, the fixed rollout with an inaccurate model has a potential to harm the learning process. In this paper, we investigate the idea of using the model knowledge for value expansion adaptively. We propose a novel method called Dynamic-horizon Model-based Value Expansion (DMVE) to adjust the world model usage with different rollout horizons. Inspired by reconstruction-based techniques that can be applied for visual data novelty detection, we utilize a world model with a reconstruction module for image feature extraction, in order to acquire more precise value estimation. The raw and the reconstructed images are both used to determine the appropriate horizon for adaptive value expansion. On several benchmark visual control tasks, experimental results show that DMVE outperforms all baselines in sample efficiency and final performance, indicating that DMVE can achieve more effective and accurate value estimation than state-of-the-art model-based methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Parallel Medical Imaging: An ACP-Based Approach for Intelligent Medical Image Recognition with Small Samples

Parallel Medical Imaging: An ACP-Based Approach for Intellig...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Tianyu Shen Chao Gou Jiangong Wang Jun Huang Yonglan He Huadan Xue Zhengyu Jin Fei-Yue Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Shenzhen Campus of Sun Yat-sen University Sun Yat-sen University Guangzhou China Peking Union Medical College Hospital Chinese Academy of Medical Sciences Peking Union Medical College Beijing China

The deep learning methods trained with large-scale manually annotated datasets have led to significant breakthroughs in medical image community. However, obtaining such datasets remains a challenging work in medical domain. In this paper, we propose an ACP-based approach named parallel medical imaging (PMI) for analyzing and addressing the small sample problem of medical image recognition. Firstly, we present the basic framework and key techniques of PMI, in which the Artificial imaging systems are constructed to effectively augment the “medical small sample”, the Computational experiments are carried out for designing and evaluating the visual models trained with small samples, and the Parallel execution is conducted to achieve closed-loop interaction and optimization in the domain-knowledge guidance. Furthermore, we illustrate a preliminary implementation and application of PMI approach through the case study of mammogram analysis.

关键词： Deep learning Visualization Image recognition Annotations Digital twin Conferences Computational modeling

来源：评论

学校读者我要写书评

暂无评论

A Learner Model Integrating Cognitive and Metacognitive And Its Application on Scratch Programming Projects

引用

IFAC-PapersOnLine 2020年第5期53卷 644-649页

作者： Sifeng Jing Ying Tang Xiwei Liu Xiaoyan Gong The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Institute of Smart Education Systems Qingdao Academy of Intelligent Industries Qingdao 266044 China Department of Electrical and Computer Engineering Rowan University Glassboro NJ 08028 USA

learner’s cognitive and metacognitive are key personal profile for individualized teaching. To evaluate learner’s comprehensive characteristics, existing learner model were reviewed. Two challenges of constructing an accurate and comprehensive learner model integrating cognitive and metacognitive were summarized. A plan of constructing a comprehensive learner model was made based on analysis of existing massive online learning environment, sensor information technology and educational data-mining. As a case study, a method of how to map learning data onto learners’ cognitive and metacognitive was proposed based on an analysis of a number of pupils’ Scratch projects. Three mapping table were established. Pupil’s cognitive skill could be evaluated from technology shown from Scratch project, namely, data structure, algorithm, computational practices and overall evaluation. Content shown from Scratch project were used to infer pupil’s cognitive style. Meta-cognitive ability can be measured from computational practices and behavior in programming process.

关键词： learner model cognitive state metacognitive ability individualized teaching

来源：评论

学校读者我要写书评

暂无评论

An Interpretable Neural Network Model Through Piecewise Linear Approximation

arXiv

引用

arXiv 2020年

作者： Guo, Mengzhuo Zhang, Qingpeng Liao, Xiuwu Zeng, Daniel Dajun School of Management Xi’an Jiaotong University School of Data Science City University of Hong Kong State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Department of Management Information Systems Eller College of Management University of Arizona

Most existing interpretable methods explain a black-box model in a post-hoc manner, which uses simpler models or data analysis techniques to interpret the predictions after the model is learned. However, they (a) may derive contradictory explanations on the same predictions given different methods and data samples, and (b) focus on using simpler models to provide higher descriptive accuracy at the sacrifice of prediction accuracy. To address these issues, we propose a hybrid interpretable model that combines a piecewise linear component and a nonlinear component. The first component describes the explicit feature contributions by piecewise linear approximation to increase the expressiveness of the model. The other component uses a multi-layer perceptron to capture feature interactions and implicit nonlinearity, and increase the prediction performance. Different from the post-hoc approaches, the interpretability is obtained once the model is learned in the form of feature shapes. We also provide a variant to explore higher-order interactions among features to demonstrate that the proposed model is flexible for adaptation. Experiments demonstrate that the proposed model can achieve good interpretability by describing feature shapes while maintaining state-of-the-art accuracy. Copyright © 2020, The Authors. All rights reserved.

关键词： Piecewise linear techniques

来源：评论

学校读者我要写书评

暂无评论

Effect of Compliant Passive Joint on Swimming Performance for a Multi-Joint Robotic Fish

Effect of Compliant Passive Joint on Swimming Performance fo...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Di Chen Zhengxing Wu Junzhi Yu State Key Lab Management and Control for Complex Systems Institute of Automation CAS Beijing China

In this paper, a novel compliant passive joint with two torsion springs is designed for a multi-joint robotic fish to improve propulsive performance. The motion of the multi-joint robotic fish is governed by the central pattern generator (CPG) control method. Using this multi-joint robotic fish as a testbed, the effect of compliant passive joint on swimming speed with changes in spring constant and CPG parameters such as oscillation frequency and phase difference is explored. As for the multi-joint robotic fish with a compliant passive joint, the swimming speed increases directly with the increase of oscillation frequency and the swimming speed achieved at maximum oscillation frequency increases with the decrease of phase difference. In addition, the comparison of swimming performance between robotic fish with a compliant passive joint and a fixed passive joint is made. Remarkably, the maximum swimming speed after improvement increases approximately 9.43 cm/s, corresponding to 0.17 BL/s. Experimental results reveal that adding an extra compliant passive joint can not always bring an improvement in swimming performance. Appropriate stiffness of passive joint and control parameters are needed to achieve better swimming performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development and Evaluation of a 7-DOF Haptic Interface

引用

IEEE/CAA Journal of Automatica Sinica 2018年第1期5卷 261-269页

作者： Jian-Long Hao Xiao-Liang Xie Gui-Bin Bian Zeng-Guang Hou Xiao-Hu Zhou Key Laboratory of Management and Control for Complex Systems Institute of Automation University of Chinese Academy of Sciences Beijing 100190 China IEEE

With the development of human robot interaction technologies, haptic interfaces are widely used for 3 D applications to provide the sense of touch. These interfaces have been utilized in medical simulation, virtual assembly and remote manipulation tasks. However, haptic interface design and control are still critical problems to reproduce the highly sensitive touch sense of humans. This paper presents the development and evaluation of a7-DOF(degree of freedom) haptic interface based on the modified delta mechanism. Firstly, both kinematics and dynamics of the modified mechanism are analyzed and presented. A novel gravity compensation algorithm based on the physical model is proposed and validated in simulation. A haptic controller is proposed based on the forward kinematics and the gravity compensation algorithm. To evaluate the control performance of the haptic interface, a prototype has been implemented. Three kinds of experiments: gravity compensation, static response and force tracking are performed respectively. The experimental results show that the mean error of the gravity compensation is less than 0.7 N and the maximum continuous force along the axis can be up to 6 N. This demonstrates the good performance of the proposed haptic interface.

关键词： Dynamic modeling evaluation haptic interface impedance control

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：