检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Real-Time Computing and robotics, RCAR 2022

作者： Chang, Yingao Wu, Yinan Fang, Yongchun Fan, Zhi Nankai University Inst. of Robotics and Automat. Info. System and the Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence Tianjin300350 China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

In this study, a novel method combining pulse coupled neural network (PCNN) and social network search (SNS) is proposed to achieve accurate image segmentation for an atomic force microscopy (AFM). The proposed method utilizes the biological visual characteristics of PCNN and the solution space search ability of SNS to determine the optimal key parameters, which can address the issue of incorrect image segmentation caused by different topographic heights of specimens in an AFM image. In the tests, the performance of the proposed method is compared with the traditional PCNN method and the Otsu method, which demonstrates that the proposed method can automatically segment the AFM image with higher accuracy and robustness. © 2022 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Celebrating Robustness in Efficient Off-Policy Meta-Reinforcement Learning

Celebrating Robustness in Efficient Off-Policy Meta-Reinforc...

引用

2022 IEEE International Conference on Real-Time Computing and robotics, RCAR 2022

作者： Liu, Ziyi Li, Zongyuan Cao, Qianqian Wan, Yuan Guo, Xian NanKai University Inst. of Robotics and Automat. Info. System and the Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence Tianjin300350 China Wuhan University of Technology Department of Mathematical WuHan430070 China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

Deep reinforcement learning algorithms can enable agents to learn policies for complex tasks without expert knowledge. However, the learned policies are typically specialized to one specific task and can not generalize to new tasks. While meta-reinforcement learning (meta-RL) algorithms can enable agents to solve new tasks based on prior experience, most of them build on on-policy reinforcement learning algorithms which require large amounts of samples during meta-Training and do not consider task-specific features across different tasks and thus make it very difficult to train an agent with high performance. To address these challenges, in this paper, we propose an off-policy meta-RL algorithm abbreviated as CRL (Celebrating Robustness Learning) that disentangles task-specific policy parameters by an adapter network to shared low-level parameters, learns a probabilistic latent space to extract universal information across different tasks and perform temporal-extended exploration. Our approach outperforms baseline methods both in sample efficiency and asymptotic performance on several meta-RL benchmarks. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Coupling Enhanced Emergency Braking Approach for Double Pendulum Cranes

A Coupling Enhanced Emergency Braking Approach for Double Pe...

引用

2022 IEEE International Conference on Real-Time Computing and robotics, RCAR 2022

作者： Chen, He Li, Mengyuan Wu, Yinan Hebei University of Technology School of Artificial Intelligence Tianjin300401 China Nankai University Inst. of Robotics and Automat. Info. System and the Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence Tianjin300350 China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

Crane systems are commonly used transportation tools in industry to transport heavy cargoes to corresponding target positions. If the cargo shape is large which could not be regarded as a mass point or the hook mass also needs to be taken into account, the cranes would perform as double pendulum systems, whose dynamics are more complex than those of single pendulum systems. Since the working environment for crane systems can be very complex in practice, unavoidable emergency situations may occur, which are very dangerous. To avoid possible accidents, effective emergency braking methods are urgently needed, especially for double pendulum cranes with large cargoes. Considering this fact, this paper presents a coupling enhanced braking strategy for double pendulum cranes, which stops the trolley fast and achieves double pendulum vibration elimination objectives simultaneously. Specifically, an elaborately designed variable consisting of the trolley movement, the hook's swing, and the payload's swing, is utilized as feedback, which enhances the system couplings and improves the vibration elimination ability. Some constraint items are also introduced to restrict the payload in a safety domain and further avoid possible collisions. The effectiveness is rigorously analyzed and proved by mathematical analysis. Some experiments are executed to show the performance of the designed strategy. © 2022 IEEE.

关键词： Cranes

来源：评论

学校读者我要写书评

暂无评论

A Standing Assist Trajectory Generation Method of Transfer Robot

A Standing Assist Trajectory Generation Method of Transfer R...

引用

2022 IEEE International Conference on Real-Time Computing and robotics, RCAR 2022

作者： Yang, Jing Song, Zhen Wu, Ruikai Wang, Jingchuan Dalian Polytechnic University China Min. of Educ. of China Shanghai Eng. Res. Ctr. of Intelligent Contr. and Mgmt. Inst. of Med. Robotics Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

The increase in the number of the elderly and the disabled in China has brought a huge pressure to daily nursing work. Standing assistance for the elderly and the disabled is an important part of daily nursing work. Robots are used to assist nursing staff in completing this work, which reduces the work pressure of nursing staff. This article focuses on the research of a transfer robot system used to assist the elderly and the disabled to stand and transfer. Since the predefined standing assist trajectory need to collect the user's standing motion, this paper proposes a standing assist trajectory generation method based on the direct collocation method, which can generate the standing assist trajectory according to the user's height, weight and body state. © 2022 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Design of Lifting Mechanism of Transfer Robot for the Elderly

Design of Lifting Mechanism of Transfer Robot for the Elderl...

引用

2022 IEEE International Conference on Real-Time Computing and robotics, RCAR 2022

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

With the intensification of the aging trend, the promotion of the design of aging facilities is conducive to improving the livelihood and welfare of the elderly and is of great significance to promoting the comprehensive, coordinated and sustainable development of the cause of aging. The transfer concept of the robot designed in this article is to enable the elderly and the disabled who are living at home to complete the actions of standing, transferring, and sitting like normal people. In view of the lack of analysis of the user's own body state in the current transfer assist equipment in the design process, the robot's lifting mechanism is optimized from the perspective of biomechanics, and finally the optimal size parameter combination of the robot's lifting mechanism is obtained. © 2022 IEEE.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Intercellular Movement Tracking for Damage Assessment during Cell Micromanipulation 11

Intercellular Movement Tracking for Damage Assessment during...

引用

11th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent systems, CYBER 2021

作者： Chen, Yizhe Du, Yue Liu, Yaowei Zhao, Qili Sun, Mingzhu Cui, Maosheng Zhao, Xin Inst. of Robotics and Automat. Info. System and the Tianjin Key Laboratory of Intelligent Robotic Nankai University Tianjin300350 China Institute of Animal Science and Veterinary of Tianjin Tianjin300381 China

ISBN: (纸本)9781665425278

Robotic cell micromanipulation that is designed for delicate operation has brought new prospects for enhancing cell developmental potential. However, mechanical damage of cells during robotic micromanipulation cannot be ignored such that it compromises the effort of the system in improving cell viability. Therefore, cell damage assessment is particularly important, but also a great challenge due to the complexity of the composition of a cell and its functions. In this paper, a novel cell damage assessment method was proposed, relying on the sensing of mitochondrial micron-scale displacement and intracellular strain. Mitochondria in living cells were stained and used as physical markers to avoid the shortcomings of introducing physical markers into cell body. We designed a quantitative marker to characterize cell mechanical damage during the penetration process. The experimental result shows that the high-strain damage is intensified as the penetration proceeds. The maximum displacement and mean displacement were respectively 3.87 pixels (2.42\mu m) and 0.78 pixels (0.49\mu m). The maximum strain and mean strain were respectively 0.107 and 0.0143 between two adjacent frames with the micropipette speed of 10\mu m/s. The maximum displacement measurement error was from 0.294 before optimization to 0.065 after optimization. The quantitative damage marker was sufficiently sensitive to sense the different levels of damage at different time sequences. At the penetration proceeds, the value of such marker at the high-strain region was several times higher than that of the low-strain region. The proposed method has implication for improving the biological efficacy of the robotic micromanipulation. © 2021 IEEE.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

Visual Detection of Cells in Brain Tissue Slice for Patch Clamp system 11

Visual Detection of Cells in Brain Tissue Slice for Patch Cl...

引用

11th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent systems, CYBER 2021

作者： Ma, Yuxin Cai, Yunyao Wang, Zeyu Sun, Mingzhu Zhao, Xin College of Artificial Intelligence Nankai University Tianjin300071 China Inst. of Robotics and Automat. Info. System and the Tianjin Key Laboratory of Intelligent Robotic Nankai University Tianjin300350 China

ISBN: (纸本)9781665425278

Whole-cell patch clamping is the gold-standard technology for electrical activities recordings of living single cells. Since it is difficult to train patch clamp operators, automatic patch clamp technologies have gained much attention. The key step in fully automated patch clamping is visual detection of cells in brain tissue slice under view of differential interference contrast (DIC) microscope. This paper proposes a cell detection method based on DIC images, which includes image classification based on image clarity and visual detection of cells in brain tissue slice based on machine learning. Firstly, combining the gray features and texture features of DIC images, we define a clarity evaluation function based on principal component analysis (PCA). Afterwards, by using K-Means Algorithm, DIC images can be divided into clear class and blurred class. The precision of this method is 99.1% in test set, which indicates that it can select the images with clear cell contour from a series of DIC images for subsequent processing. Secondly, we design a neuron detection process based on sliding window and pre-Trained classifier to take cell detection in the selected clear images. We finally choose GoogLeNet as classifier in the detection process after comparing the advantages and disadvantages of classification methods based on support vector machine (SVM) and deep learning. The results show that the detected cells are basically operable living cells. The proposed cell detection technology in this paper provides an effective visual tool for fully automated patch clamping. © 2021 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Single focused-beam acoustical tweezers: Trapping cells in 3‐D

引用

The Journal of the Acoustical Society of America 2023年第4_SUPPLEMENT期154卷 A263-A263页

作者： Zhixiong Gong Shiyu Li Zhichao Ma Key Lab. of Marine Intelligent Equipment and System State Key Lab. of Ocean Eng. School of Naval Architecture Ocean and Civil Eng. Shanghai Jiao Tong Univ. Dongchuan Rd. #800 Minhang District Shanghai 200240 China zhixiong.gong@*** Key Lab. of Marine Intelligent Equipment and System State Key Lab. of Ocean Eng. School of Naval Architecture Ocean and Civil Eng. Shanghai Jiao Tong Univ. Shanghai China Inst. of Medical Robotics School of Biomedical Eng. Shanghai Jiao Tong Univ. Shanghai China

Single focused beams have shown great potential in acoustofluidics and medical ultrasound because of their large pressure gradient and acoustic-thermal effect, such as acoustical tweezers and high-intensity focused ultrasound (HIFU) technique. However, the three-dimensional trapping of typical cells is still challenging since cells in water have a positive acoustic contrast factor and will be repulsive from the focus [Gong and Baudoin, Phys. Rev. Applied 18, 044033 (2022)]. In this work, to reverse this positive acoustic contrast factor into negative, we propose to use a cell-friendly medium (made of iodixanol with water) [Augustsson et al., Nat. Commun. 7, 11556 (2016)]. This enables a single focused beam to selectively trap and control cells in 3‐D, and more importantly, keeps the manipulated cells with good viability. This work will extend the applications of acoustical tweezers, which may be beneficial to single cell analysis, cellular phenotyping, precise assembly of different cells in tissue engineering, and controlled drug delivery.

关键词：

来源：评论

学校读者我要写书评

暂无评论

From single autonomous robots toward cooperative robotic interactions for future planetary exploration missions 69

From single autonomous robots toward cooperative robotic int...

引用

69th International Astronautical Congress: #InvolvingEveryone, IAC 2018

作者： Wedler, Armin Wilde, Martina Reill, Josef Schuster, Martin J. Vayugundla, Mallikarjuna Brunner, Sebastian G. Bussmann, Kristin DÃ¶mel, Andreas Drauschke, Martin Gmeiner, Heinrich Lehner, Hannah Lehner, Peter MÃ¼ller, Marcus G. StÃ¼rzl, Wolfgang Triebel, Rudolph Vodermayer, Bernhard BÃ¶rner, Anko Krenn, Rainer Dammann, Armin Fiebig, Uwe-Carsten Staudinger, Emanuel WenzhÃ¶fer, Frank FlÃ¶gel, Sascha Sommer, Stefan Asfour, Tamim Flad, Michael Hohmann, SÃ¶ren Brandauer, Martin Albu-SchÃ¤ffer, Alin Olimpiu Institute of Robotics and Mechatronics MÃ¼nchener Str. 20 WeÃŸling82234 Germany Institute of Optical Sensor Systems Rutherfordstr. 2 Berlin12489 Germany Institute of System Dynamics and Control MÃ¼nchener Str. 20 WeÃŸling82234 Germany Institute of Communications and Navigation MÃ¼nchener Str. 20 WeÃŸl82234 Germany Centre for Polar and Marine Research Am Handelshafen 12 Bremerhafen27570 Germany GEOMAR Helmholtz Centre for Ocean Research Wischhofstr. 1-3 Kiel24148 Germany Institute for Anthr. and Robotics Am Fasanengarten 5 Karlsruhe76131 Germany Institute for Control Systems Kaiserstr. 12 Karlsruhe76131 Germany Inst. of Techn. and Manag. in Construction Am Fasanengarten Karlsruhe76131 Germany

Mobile robotics will play a key role in future space, ocean and deep sea exploration activities. Besides the actual development of the robotic systems, the different ways of commanding those systems, using technologies varying from teleoperation with the human in the loop, through shared autonomy towards highly autonomous systems, will be the main challenges of these missions. This paper describes the robotic activities of the DLR institutions within the Helmholtz projects ROBEX and ARCHES, dealing with robots for autonomous space and ocean exploration applications. Furthermore, it describes the challenges, the overlap and the synergies of those domains, the different approaches of operating robots from far distances in extreme environments and gives an outlook on future mission possibilities. Copyright © 2018 by the International Astronautical Federation (IAF). All rights reserved.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

A Way of Nuclear Station Inspection Robot Location

A Way of Nuclear Station Inspection Robot Location

引用

IEEE International Conference on Information and Automation

作者： Jinke Li Ruiqing Fu Xinyu Wu Qingsong Liu Guohe Wang Shuo Hou Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Nucl. Power Technol. Res. Inst. (CNPRI)

ISBN: (纸本)9781467391054

Nuclear safety is an important strategic demand in China. Steam generator is one of the key equipment in nuclear station, therefore its daily detection is very important. Robot is the most effective mean of detecting steam generator, and the location in the steam generator will greatly improves the detection efficiency of the robot in the detection process. This paper establishes a coordinate system consists of steam generator and detection robot, clarifies the location problem we need to solve. Then we establish odometer location model and image location model with its sensors, then derive and analyze both of the two models. This paper fuses the above two models together through particle filter method, introduces the location method we use and the specific steps are given. In the end of this paper, we design experiments for the robot location, experiments show that the particle filter location for nuclear station steam generator climbing-robot is accuracy and effectively.

关键词： Nuclear station steam generator Climbing-robot Location Particle filter

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：