检索结果-内蒙古大学图书馆

22nd IEEE International Conference on E-Health Networking, Application and Services, HEALTHCOM 2020

作者： Liu, Xiang Wu, Hancheng Fang, Senlin Yi, Zhengkun Wu, Xinyu CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen Key Laboratory of Smart Sensing and Intelligent Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China

ISBN: (纸本)9781728162676

In this paper, we propose a novel method for multimodal material classification based on ensemble learning and optimized features. The proposed method consists of three key steps. Firstly, we extract a set of features for each modality. Compared to existing methods, the extracted features are relatively simple but more effective when they are incorporated into the classifiers. Then, the feature selection algorithms, including Multi-Cluster Feature Selection (MCFS) and Laplacian Score (LS) are employed to reduce the feature dimension due to the curse of dimensionality. Finally, an ensemble learning method is proposed to integrate the merits of different feature selection methods. The effectiveness of the proposed method is demonstrated on the LMT-108 surface material dataset which includes multiple modalities such as sound, acceleration, and image. The experimental results have shown that our approach performs better than the competing methods. © 2021 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Posture Estimation and Trajectory Tracking for SQuRo: a Small-sized Quadruped Robotic Rat

Posture Estimation and Trajectory Tracking for SQuRo: a Smal...

引用

IEEE International Conference on Cyborg and Bionic systems (CBS)

作者： Junhui Gao Rongjie Du Xiaolong Quan Guanglu Jia Qiang Huang Toshio Fukuda Qing Shi School of Mechatronical Engineering Intelligent Robotics InstituteBeijing Institute of Technology Beijing China Ministry of Education >Laboratory of Biomimetic Robots and Systems(Beijing Institute of Technology) Beijing China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing China Ministry of Education Laboratory of Biomimetic Robots and Systems (Beijing Institute of Technology) Beijing China

Large quadruped robots have shown high environmental adaptability and promising applications. However, due to the difficulty of integrating multiple sensors or highperformance CPU in such a limited dimension, which strongly hindered the perception and calculation ability, quadruped robots in small scale haven’t shown equally performance. To overcome this limitation, we integrated the inertial measurement unit (IMU) into the small-sized robotic rat SQuRo, and proposed simplified control strategies to enhance its robustness. The improvements includes three parts: 1) A posture control strategy is proposed and verified by posture adjustment in a slope test; 2) Straight line tracking was achieved by detecting and controlling the yaw angle of SQuRo; 3) The autonomous fall recovery was achieved by detecting the fall and executed a predefined fall recovery strategy.

关键词： Measurement units Trajectory tracking Kinematics Inertial navigation Rats Robot sensing systems Robustness

来源：评论

学校读者我要写书评

暂无评论

Simulator Design Using a General Purpose PC and Off-The-Shelf Interface Boards for GNSS/INS Integrated Navigation System

Simulator Design Using a General Purpose PC and Off-The-Shel...

引用

International Conference on Control, Automation and systems ( ICCAS)

作者： Jae Hoon Son Yeong Hye Lee Junwoo Jurug Yongtaek Hwang Jiwoo Hwang Minsu Kim Gyeongmin Park JunMin Park Hoyoung Yoo Chansik Park Sang Heon Oh Sang Jeong Lee Dong-Hwan Hwang Department of Electronics Engineering Chungnam National University Daejeon Korea Department of Intelligent Systems & Robotics Chungbuk National University Daejeon Korea Advanced Technology Laboratory Microinfinity Co. Ltd. Daejeon Korea

When a navigation systems are developed, lots of tests have to be performed. If a simulator is available which can generate signal and data of real environment, huge amount of time and cost can be reduced for development. In this paper, a simulator design method is proposed for GNSS/INS integrated navigation system using a general-purpose PC and OTS interface boards. In order to verify the proposed design method, a simulator of GPS L1 C/A and HG1700AG58 is implemented using a PC with intel i7-8700 CPU, USRP 2952-R, PCI-1780U-AE, FSCC/4-PCIe and LabVIEW2015. The implementation results show that GNSS signal and IMU data can be used for GNSS/INS integrated navigation system design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nowhere to Go: Benchmarking Multi-robot Collaboration in Target Trapping Environment

arXiv

引用

arXiv 2023年

作者： Zhang, Hao Chen, Jiaming Cheng, Jiyu Li, Yibin Yang, Simon X. Zhang, Wei The School of Control Science and Engineering Shandong University Jinan250061 China The Advanced Robotics and Intelligent Systems Laboratory School of Engineering University of Guelph GuelphONN1G2W1 Canada

Collaboration is one of the most important factors in multi-robot systems. Considering certain real-world applications and to further promote its development, we propose a new benchmark to evaluate multi-robot collaboration in Target Trapping Environment (T2E). In T2E, two kinds of robots (called captor robot and target robot) share the same space. The captors aim to catch the target collaboratively, while the target will try to escape from the trap. Both the trapping and escaping process can use the environment layout to help achieve the corresponding objective, which requires high collaboration between robots and the utilization of the environment. For the benchmark, we present and evaluate multiple learning-based baselines in T2E, and provide insights into regimes of multi-robot collaboration. We also make our benchmark publicly available and encourage researchers from related robotics disciplines to propose, evaluate, and compare their solutions in this benchmark. Our project is released at https://***/Dr-Xiaogaren/T2E. Copyright © 2023, The Authors. All rights reserved.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

A Novel Transfer Learning Method for Robot Bearing Fault Diagnosis Based on Deep Convolutional Residual Wasserstein Adversarial Network 16th

A Novel Transfer Learning Method for Robot Bearing Fault Dia...

引用

16th International Conference on intelligent robotics and Applications, ICIRA 2023

作者： Pan, Bing Xiong, Xin Hu, Hailiang He, Jun Yang, Shixi The State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou China The Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province School of Mechanical Engineering Zhejiang University Hangzhou China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai200444 China Hangzhou Steam Turbine Power Group Co. Ltd. Hangzhou China

ISBN: (纸本)9789819965007

In the process of robot bearing fault diagnosis based on data-driven, transfer learning is an effective method to solve the lack of labeled data, and data distribution difference between source domain data and target domain data will lead to domain drifts under variable working conditions. In this paper, a robot bearing fault diagnosis method based on deep convolutional residual Wasserstein adversarial network (DCRWAN) is proposed to reduce domain offsets and improve the robot bearing fault diagnosis accuracy. In the proposed method, a deep convolutional residual network is constructed to extract the transferable features of source domain and target domain. Then, a domain discrimination module is constructed and the domain adversarial training is carried out to minimize the distribution discrepancy of cross-domain by the Wasserstein loss function. At the same time, a domain distribution discrepancy metrics module is applied to estimate the difference of features distribution between two domains, and further fine-tuning the network parameters to obtain domain-invariant and class-separable features for the classification. The average accuracy of the two transfer tasks using this method is 95.65% and 93.75%, respectively, and the results show that the method effectively reduces the domain differences caused by varying working conditions and improves the fault diagnosis accuracy of robot bearings under variable working conditions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of a Novel Self-Adaptive Ankle Rehabilitation Exoskeleton with Elastic Modules

Design and Evaluation of a Novel Self-Adaptive Ankle Rehabil...

引用

International Conference on advanced robotics and Mechatronics (ICARM)

作者： Meng Gao Junpeng Chen Mi Li Jian S. Dai Shenzhen Key Laboratory of Intelligent Robotics and Flexible Manufacturing Systems Southern University of Science and Technology Shenzhen China Centre for Robotics Research King's College London London United Kingdom Key Laboratory of Mechanism Theory and Equipment Design of the Ministry of Education Centre for Advanced Mechanisms and Robotics Tianjin University Tianjin China Chair Professor of Mechanisms and Robotics Centre for Robotics Research King's College London UK

This paper proposes a novel ankle rehabilitation exoskeleton based on the research of human gait cycle, aiming to assist patients with neurological injury to recover quickly. The mechanism consists of two frames equipped with ankle joints and toe joint. The lower limbs and musculature system are correlated to propose the model. Incorporating spring modules are provided on the instep, the bottom of toes and either sides of the ankles which cushions lower limbs and reduces energy consumption. Kinematics and stress analysis are conducted to verify the feasibility of the model. Besides, the simulation, which incorporates the elastic elements and springs, is presented. Finally, the modular facilitates could easy integration with other rehabilitation modules for a comprehensive system. Overall, this research provides theoretical and engineering technical support for developing lower limb rehabilitation robots with adaptive stability, diversified movement functions, and human-computer interaction safety and health under different conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Dynamic Locomotion Control of Quadruped Robot with Perception-Less Terrain Adaptation

引用

Cyborg and Bionic systems 2022年第1期2022卷 177-186页

作者： Lei Wang Libo Meng Ru Kang Botao Liu Sai Gu Zhihao Zhang Fei Meng Aiguo Ming Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of TechnologyBejing 100081China Beijing Advanced Imnovation Center for Intelligent Robots and Systems Beijing Institute of TechnologyBeijing 100081China Department of Mechanical Engineering and Itelligent Systerms The University of Electro-CommunicationsTokyo 182-8585Japan

In this paper,a parallel quadrupedal robot was designed that is capable of versatile dynamic locomotion and perception-less terrain ***,a quadrupedal robot with a symmetric legs and a powerful actuator was implemented for highly dynamic ***,a fast and reliable method based on generalized least square was proposed for estimating the terrain parameters by fusing the body,leg,and contact *** the basis of virtual model control(VMC)with the quadratic program(QP)method,the optimal foot force for terrain adaptation was ***,the results obtained by simulation and indoor and outdoor experiments demonstrate that the robot can achieve a robust and versa tile dynamic locomotion on uneven terrain,and the rejection of disturbances is reliable,which proves the effectiveness and robustness of this proposed method.

关键词： robot Robot terrain

来源：评论

学校读者我要写书评

暂无评论

Design and Simulation of a Helical Microrobot for Maximum Speed Enhancement by Physical Surface Modification

Design and Simulation of a Helical Microrobot for Maximum Sp...

引用

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

作者： Siyu Guo Maolin Wang Huaping Wang Shihao Zhong Yukang Qiu Yaozhen Hou Qing Shi Toshio Fukuda School of Mechatronical Engineering Intelligent Robotics Institute Beijing Institute of Technology Beijing China Key Laboratory of Biomimetic Robots and Systems (Beijing Institute of Technology) Ministry of Education Beijing China School of Medical Technology Beijing Institute of Technology Beijing China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing China

Magnetic helical microrobots have great potential in biomedical applications. However, improving their motion performance in the complex and variable in vivo fluid environment remains challenging. Previous researches mainly focus on optimizing the geometric parameter, the evolutionary structure design, and chemical modifications of the robots, with limited attention given to the impact of physical surface modifications on propulsion performance. To address this issue, we design the helical microrobot with different surface physical modifications, including dimpled and raised surfaces, to evaluate their effects on swimming performance. With ANSYS Fluent, we simulated their swimming process in water and found that microrobots with physically modified surfaces experience less resistance and exhibit a larger step-out frequency while swimming. Moreover, our findings suggest that helical microrobots with dimpled surfaces demonstrate superior swimming performance due to their larger gas-liquid interface area compared to those with raised surfaces.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Electromagnetic Manipulation of Micron-Scale Rotors on Unstructured Surfaces in Low Reynolds Numbers

Automated Electromagnetic Manipulation of Micron-Scale Rotor...

引用

International Conference on advanced robotics and Mechatronics (ICARM)

作者： Shihao Zhong Kailun Bai Yaozhen Hou Hen-Wei Huang Qing Shi Qiang Huang Huaping Wang Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing China Science and Technology on Space Physics Laboratory Beijing China Laboratory for Translational Engineering Harvard Medical School Cambridge MA USA Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing China Key Laboratory of Biomimetic Robots and Systems Beijing Institute of Technology Ministry of Education Beijing China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

The utilization of magnetic microrotors in low Reynolds number liquid environments holds great promise for a wide range of biomedical applications, owing to their ability to maneuver with flexibility. However, during the movement of the microrotors on solid unstructured surfaces, the interaction with neighboring walls has the potential to generate unpredictable disruptions in its motion. This study proposes an automated electromagnetic manipulation method for guiding micron-scale surface rotors along planar paths at low Reynolds numbers. To this end, we designed a magnetic field drive system using multistage electromagnets, and a double-helix rotor with micrometer-scale dimensions. Additionally, we developed a kinematic model for the microrotor that closely resembles that of wheeled mobile robots and employed a sliding mode motion controller to ensure high-precision path following. Results obtained from simulation and experimentation confirm the efficacy of our proposed method, demonstrating precise following of planar paths.

关键词： Visualization Mechatronics Rotors Kinematics Solids Electromagnets Magnetic fields Mobile robots Micromagnetics Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

Modeling Neural Representation of Social Recognition Information with Recurrent Neural Networks 17

Modeling Neural Representation of Social Recognition Informa...

引用

17th International Conference on Complex Medical Engineering, CME 2023

作者： Song, Fei Wang, Xinnian Zhan, Yang Tang, Fengzhen Si, Bailu State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China School of Life Sciences Division of Life Science and Medicine University of Science and Technology of China Hefei230026 China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China School of Systems Science Beijing Normal University Beijing100091 China Chinese Institute for Brain Research Beijing102206 China

ISBN: (纸本)9798350316117

Social recognition, the ability to differentiate between familiar and unfamiliar individuals, is crucial for animals' survival and reproduction. Neuroscience research has predominantly focused on investigating the brain regions and circuits that regulate social recognition. However, a lingering question pertains to the precise mechanisms underlying the social recognition process. To address this question, we employed a recurrent neural network (RNN) to determine whether an agent can recognize familiar individuals without involving higher-level decision-making processes. This approach takes into consideration that animal behavioral performance may not directly mirror complex cognitive functions. The RNN was trained using the full-FORCE learning paradigm. Our simulation results revealed three distinct subsets of neurons with specific functions: one dedicated to representing novel individuals and two others representing the same social individual in both unfamiliar and familiar states. We propose a hypothesis regarding the potential memory computing processes involved in these operations. © 2023 IEEE.

关键词： Animals

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：