检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Biomimetics

作者： Qing Bi Yixiang Liu Xizhe Zang Rui Song Haibin Wang Weimin Li Shandong Institute of Advanced Technology Chinese Academy of Sciences Jinan China School of Control Science and Engineering Shandong University Jinan China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

Achieving versatile and efficient walking on biped robots is an important research objective. The impact between the foot and the ground has significant effects on the walking stability of biped robots. Research on human walking indicates that the joints in human lower limbs show different stiffness values in different phases of walking. Inspired by humans, this paper presents the realization of biped robot walking with variable stiffness at the ankle joint. A walking control scheme which combines PD control and variable impedance control is designed for the biped robot. Results of dynamic walking simulation verified that variable stiffness at the ankle joint could contribute to the improvement of walking stability and energy efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Path planning of mobile robot based on improved DDQN

引用

Journal of Physics: Conference Series 2021年第1期2024卷

作者： Yang yunxiao Wangjun Zhang Hualiang Dai shilong School of Computer Science Shenyang University of Chemical Technology Shenyang 110142 China. Industrial Control Network and System Laboratory Shenyang Institute of Automation Chinese Academy of Sciences Shenyang 110016 China. Institudes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang 110169 China.

Aiming at the problem of overestimation and sparse rewards of deep Q network algorithm in mobile robot path planning in reinforcement learning, an improved algorithm HERDDQN is proposed. Through the deep convolutional neural network model, the original RGB image is used as input, and it is trained through an end-to-end method. The improved deep reinforcement learning algorithm and the deep Q network algorithm are simulated in the same two-dimensional environment. The experimental results show that the HERDDQN algorithm solves the problem of overestimation and sparse reward better than the DQN algorithm in terms of success rate and reward convergence speed, Which shows that the improved algorithm finds a better strategy than the DQN algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Electricity Loss and Electricity Consumption Law in low-Voltage Areas: A Case Study

引用

Journal of Physics: Conference Series 2021年第1期2022卷

作者： Xi Chen Chunhe Song Tianran Wang Key Laboratory of Network Control System Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang 110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang 110016 China University of Chinese Academy of Sciences Beijing 100049 China

Electric power is an important resource in energy. With the development of society, the consumption of electric power is more and more. Research on electricity consumption and power loss has become a hot *** this paper, we conduct statistical analysis on the power supply, power consumption and line loss rate of 395 power supply *** loss rate is an indicator to describe electricity *** found that the line loss rate decreased over the course of a *** overall distribution of line loss rate is approximately lognormal distribution. Total daily electricity supply and electricity consumption in the power supply area approximately obey exponential *** terms of electricity consumption, a statistical analysis was made on the daily electricity consumption of 100, 000 users in three years, and it was found that the electricity distribution of users was in line with the power law distribution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved Scan Matching Method Based on Laser Reflection Intensity

An Improved Scan Matching Method Based on Laser Reflection I...

引用

International Conference on Intelligent control and Information Processing (ICICIP)

作者： Guojing Wu Jingchuan Wang Hesheng Wang Le Xie Peng Li Key Laboratory of System Control and Information Processing Ministry of Education of China Institute of Medical Robotics SEIEE School Shanghai Jiao Tong University Shanghai China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China School of Mechanical Engineering and Automation Harbin Institute of Technology (Shenzhen) Shenzhen China

ISBN: (数字)9781728100159

ISBN: (纸本)9781728100166

High-precision localization performance of mobile robots in featureless environments plays an important role in the field of navigation. This paper describes an effective localization solution using a landmark whose surface is covered with two different materials resulting in different laser reflection intensities. Based on the landmark, a feature extraction algorithm is proposed and an improved scan matching method for mobile robot localization in featureless environments is described. Unlike traditional scan matching methods which only use geometric features, the proposed method mixes geometric information extracted from environment and laser reflection intensity extracted from the landmark to achieve accurate pose estimation. Experiments show that our method has higher precision than previous methods.

关键词： Reflection Sensors Feature extraction Data mining Iterative closest point algorithm Surface emitting lasers

来源：评论

学校读者我要写书评

暂无评论

Encoding Space to Count Multi-Targets with Multiplexed Binary Infrared Sensors

Encoding Space to Count Multi-Targets with Multiplexed Binar...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Longxiang Luo Yang Xiao Wei Liang Key Laboratory of Networked Control System Shenyang Institute of Automation Chinese Academy of Sciences Shenyang State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China Department of Computer Science The University of Alabama Tuscaloosa AL USA

ISBN: (数字)9781728152127

ISBN: (纸本)9781728152134

Recently, many researchers multiplex binary infrared sensors in object tracking, habitat monitoring, and atypical behavior detection. Due to the binary digit output of binary sensors, multiplex binary sensors may lead to count the wrong number of targets when three or more targets present in the field of interest (FOI). We call this as the invisible targets' problem. To enhance the sensing results of sensors, a reference structure tomography technique is used to segment and code the FOI by modulating the sensing view of sensors. In this paper, we propose a subregion coding method to count targets moving in the FOI. Hexagon modulators are designed to make their projections segment the FOI into hexagon cells. We also propose a signature construct scheme to code cells and a encoder to count the number of targets in the FOI. Experiment results show that the accuracy to correctly count targets of our method is around 90% which is much better than 45% of a conventional method.

关键词： Modulation Monitoring Shape Sensor systems Encoding Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Retrieval-based localization based on domain-invariant feature learning under changing environments

arXiv

引用

arXiv 2019年

作者： Hu, Hanjiang Wang, Hesheng Liu, Zhe Yang, Chenguang Chen, Weidong Xie, Le Autonomous Robot Lab Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University Shanghai200240 China T Stone Robotics Institute Chinese University of Hong Kong Hong Kong Bristol Robotics Laboratory University of the West of England BristolBS16 1QY United Kingdom School of Material Science and Engineering Shanghai Jiao Tong University Shanghai200240 China

Visual localization is a crucial problem in mobile robotics and autonomous driving. One solution is to retrieve images with known pose from a database for the localization of query images. However, in environments with drastically varying conditions (e.g. illumination changes, seasons, occlusion, dynamic objects), retrieval-based localization is severely hampered and becomes a challenging problem. In this paper, a novel domain-invariant feature learning method (DIFL) is proposed based on ComboGAN, a multi-domain image translation network architecture. By introducing a feature consistency loss (FCL) between the encoded features of the original image and translated image in another domain, we are able to train the encoders to generate domain-invariant features in a self-supervised manner. To retrieve a target image from the database, the query image is first encoded using the encoder belonging to the query domain to obtain a domain-invariant feature vector. We then preform retrieval by selecting the database image with the most similar domain-invariant feature vector. We validate the proposed approach on the CMU-Seasons dataset, where we outperform state-of-the-art learning-based descriptors in retrieval-based localization for high and medium precision scenarios. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Automatic Cell Assembly by Two-fingered Microhand

Automatic Cell Assembly by Two-fingered Microhand

引用

2019 IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Junnan Chen Xiaoming Liu Shengnan Dong Pengyun Li Xiaoqing Tang Dan Liu Masaru Kojima Qiang Huang Tatsuo Arai Intelligent Robotics Institute School of Mechatronical Engineering Key Laboratory of Biomimetic Robots and Systems Ministry of Education Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing CHINA Department of Systems Innovation Graduate school of Engineering Science Osaka University Toyonaka Osaka Japan Global Alliance Lab The University of Electro-Communications Tokyo Japan

We have successfully achieved manipulation and assembly of microbeads having the size of 100μm diameter by hemispherical end-effectors with high stability and accuracy. The motivation of achieving assembly of actual cells lies in the great significance of it in tissue regeneration and cell analysis. Firstly, the most difficult problem we need to solve is the releasing problem caused by adhesion force. The viscosity on cell surface is much larger than the microbeads which makes cell releasing challenging. Secondly, the cell can generate its deformation, then contact area with end-effector will change during grasping process. This may influence the adhesion force and also bring problem to releasing. Thirdly, cell is much smaller, around 15μm in diameter, so we need to fabricate smaller end-effector to achieve successful manipulation and ensure the stability in the meantime. In this paper, we realize the manipulation by decreasing the adhesion forces and apply vibration to release a cell stably. We found the appropriate scale size for the end-effector is around 10μm diameter. It can not only grasp a 15μm cell but also bring little interference to the environment. As a demonstration of the proposed manipulation method, the repeated experiments were conducted to explore the dependence of adhesion force on the grasping distance, which can be helpful in the improvement of successful rate. Finally, we achieved automatic cell assembly using Hela cells.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable control Design Based on Complete Parametric Approach for Spacecraft Rendezvous 36

Reconfigurable Control Design Based on Complete Parametric A...

引用

第36届中国控制会议

作者： Guangren Duan Qin Zhao State Key Laboratory of Robotics and System(HIT) Center for Control Theory and Guidance Technology Harbin Institute of Technology

ISBN: (纸本)9781538629185

This paper studies the problem of reconflgurable fault tolerant controller design for linear time-invariant systems with measurement unavailability based on a complete parametric *** attention is focused on completely recovering eigenvalues of the pre-fault system by resynthesizing an output feedback controller while the restrictions on assignable eigenvalues of existing results are ***,the complete parametric method is introduced to give the parametric expressions for all output feedback matrices with the advantage of guaranteeing the stability of the reconfigured ***'s more,reconflgurable controllers for the spacecraft rendezvous system are studied as the example in cases of different measurement failure ***,numerical calculations are given and results show the effectiveness of the proposed method.

关键词： Reconfigurable control Spacecraft Rendezvous Measurement Unavailability Complete Parametric Approach Output Feedback

来源：评论

学校读者我要写书评

暂无评论

Integrated guidance and control with input saturation 36

Integrated guidance and control with input saturation

引用

第36届中国控制会议

作者： Wangkui Liu Yiyin Wei Guangren Duan State Key Laboratory of Robotics and System Harbin Institute of Technology Center for Control Theory and Guidance Technology Harbin Institute of Technology

ISBN: (纸本)9781538629185

Based on backstepping control technique,a novel adaptive integrated guidance and control(IGC) law is presented for missile intercepting maneuvering target with input *** deal with the uncertainties in the IGC system,adaptive control technique is utilized to estimate the upper bounds of the ***,an auxiliary system is designed to cope with the input *** state of the auxiliary system is used in the IGC law design and stability *** detailed stability analysis of the closed-loop IGC system is carried out based on the Lyapunov ***,the effectiveness of the proposed adaptive IGC law is verified by the nonlinear numerical simulation results.

关键词： Backstepping control Adaptive Integrated guidance and control(IGC) Input saturation

来源：评论

学校读者我要写书评

暂无评论

Sparse Kernel Regression with Coefficient-based `q−regularization

引用

Journal of Machine Learning Research 2019年 20卷

作者： Shi, Lei Huang, Xiaolin Feng, Yunlong Suykens, Johan A.K. Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai China Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing Shanghai China Department of Mathematics and Statistics State University of New York at Albany New York United States Department of Electrical Engineering ESAT-STADIUS KU Leuven Kasteelpark Arenberg 10 LeuvenB-3001 Belgium

In this paper, we consider the `q−regularized kernel regression with 0 q−penalty term over a linear span of features generated by a kernel function. We study the asymptotic behavior of the algorithm under the framework of learning theory. The contribution of this paper is two-fold. First, we derive a tight bound on the `2−empirical covering numbers of the related function space involved in the error analysis. Based on this result, we obtain the convergence rates for the `1−regularized kernel regression which is the best so far. Second, for the case 0 ©c 2019 Lei Shi, Xiaolin Huang, Yunlong Feng, and Johan A.K. Suykens.

关键词： Regression analysis

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：