检索结果-内蒙古大学图书馆

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

作者： Kai Li Kun Qian Rui Liu Fang Fang Hai Yu Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing China State Grid Corporation of China Global Energy Interc onnection Research Institute Company Ltd Nanjing China

ISBN: (数字)9781728172934

ISBN: (纸本)9781728172941

Semantic information of objects and environment is a basis for robots to effectively complete complicated tasks. However, scene recognition methods based on image descriptors or convolutional neural networks often have misclassifications in actual environment. One reason is that highly complex environment has inconspicuous physical boundaries. In this paper, we propose a regional semantic learning method based on convolutional neural networks (CNNs) and conditional random fields (CRFs). The method combines global information obtained by scene classification network and local object information obtained by object detection network to train a CRF scene recognition model. Then the model can be used to infer the semantics of the region. After that, the regional semantic information is applied to build a sparse semantic map based on ORB-SLAM2. The proposed method was tested on a self-built environment dataset which contains four regional categories. Experimental results have demonstrated that the proposed method is effective and can obtain better classification results.

关键词： Feature extraction Semantics Erbium Training Three-dimensional displays Robots Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Attitude tracking control of a quadrotor based on linear active disturbance rejective control

Attitude tracking control of a quadrotor based on linear act...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent systems

作者： Jingdu Gao Yan Zhuang Jizhong Xiao Yiwen Zhao School of Control Science and Engineering Dalian University of Technology Dalian China Department of Electrical Engineering The City College City University of New York New York USA State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

A quadrotor is a typical multiple-input multiple-output (MIMO), underactuated, strong coupled nonlinear system with parameter uncertainty and unmodeled disturbance. To track the desired attitude and height, a linear active disturbance rejection control (LADRC) approach is utilized for the quadrotor control. LADRC has the capacity of estimating and compensating the generalized disturbance, and reduce the system to a unit gain double integrator, which is easily implemented and robust to environment disturbances. A simplified dynamic model of quadrotor is established using Newton-Euler equations. The design of LADRC is verified through numerical simulation and compared with PID controller. Simulation results indicate the LADRC can be used to achieve good performance in tracking the desired attitude and height.

关键词： Mathematical model control systems Observers Attitude control Aerodynamics Numerical models Propellers

来源：评论

学校读者我要写书评

暂无评论

Value capture and value creation in high-velocity networked environments

Value capture and value creation in high-velocity networked ...

引用

IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI

作者： Hannu Tuomisaari Juhana Peltonen Timo R Nyberg Xisong Dong Göte Nyman Business Innovation and Technology School of Science Aalto University Espoo Finland The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Behavioral Sciences University of Helsinki Finland

ISBN: (纸本)9781479905287

The core function of any profitable firm is capturing a share of the value that customer perceives in the firm's offering. Value capture is traditionally considered to relate to a competitive advantage at the firm level, but not the firm network level. However, the ever increasing role of information and knowledge in today's economy is profoundly changing how firms can create competitive advantages. Among these changes, we highlight reducing transaction costs in various areas of the economy, which drives the economy to organize more toward rapidly evolving networks or smaller firms. There is also an opposite trend for some internet firms to become larger due to economies of scale and due to network externalities. In this position paper, we examine the issue of value capture by firms that are increasingly small and operate in rapidly changing and evolving networks. We conclude by outlining future research on firm-level capabilities that are required to enable value capture in new forms of dynamic networks.

关键词： Economics Organizations Intellectual property Industries Communications technology Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Efficient Learning and control of String- Type Artificial Muscle Driven Robotic systems

Efficient Learning and Control of String- Type Artificial Mu...

引用

American control Conference (ACC)

作者： Jiyue Tao Sunil Kumar Rajendran Yunsong Zhang Feitian Zhang Dexin Zhao Tongsheng Shen The Department of Advanced Manufacturing and Robotics College of Engineering Peking University Beijing China The National Innovation Institute of Defense Technology Beijing China The BSS Technologies Inc. Takoma Park MD USA The Department of Advanced Manufacturing and Robotics The State Key Laboratory of Turbulence and Complex Systems College of Engineering Peking University Beijing China

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

This paper investigates the learning-based control of robotic systems driven by string-type artificial muscles. Due to the highly nonlinear dynamics of the actuators and the complicated mechanical structure, it is typically very challenging to design traditional model-based controllers that exhibit desired control performances. With the rapid development of machine learning techniques, deep reinforcement learning (DRL) algorithms have been utilized to control a variety of complex robotic systems. However, these DRL algorithms usually require a huge amount of training data and iterations to converge, which is generally unacceptable for the robotic systems of interest. Therefore, this paper designs an efficient learning-based control algorithm, aiming to improve the training efficiency for robotic systems driven by string-type artificial muscle actuators. Specially, two training improvements are proposed including imitation learning and data augmentation. This paper applies the proposed learning methods to three popular DRL algorithms and tests the control performances in three case studies using three string-type artificial muscle-driven robots, including a parallel robotic wrist, a two degrees-of-freedom (DOF) robotic eye and a robotic finger. Simulation results show that the proposed learning-based control methods significantly accelerate the convergence speed and improve the data efficiency in all the three case studies.

关键词： Artificial muscles Wrist Training Actuators Machine learning algorithms Imitation learning Fingers

来源：评论

学校读者我要写书评

暂无评论

Generalized Visual-Tactile Transformer Network for Slip Detection

引用

IFAC-PapersOnLine 2020年第2期53卷 9529-9534页

作者： Shaowei Cui Junhang Wei Xiaocan Li Rui Wang Yu Wang Shuo Wang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Future Technology University of Chinese Academy of Sciences Beijing 100049 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai 200031 China

Slip detection plays a vital role in robotic dexterous grasping and manipulation, and it has long been a challenging problem in the robotic community. Different from traditional tactile perception-based methods, we propose a Generalized Visual-Tactile Transformer (GVT-Transformer) network to detect slip based on visual and tactile spatiotemporal sequences. The main novelty of GVT-Transformer is its ability to address unaligned vision and tactile data in various formats captured by various tactile sensors. Furthermore, we train and test our proposed network on a public and our visual-tactile grasping datasets. The experimental results show that our method is more suitable for sliding detection tasks than previous visual-tactile learning methods and more versatile.

关键词： Information sensor fusion Perception sensing Intelligent robotics Deep neural networks Visual-tactile fusion perception

来源：评论

学校读者我要写书评

暂无评论

A registration-aided domain adaptation network for 3D Point cloud based place recognition

arXiv

引用

arXiv 2020年

作者： Qiao, Zhijian Hu, Hanjiang Shi, Weiang Chen, Siyuan Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Mechanical Engineering Carnegie Mellon University United States Department of Computer Science and Technology University of Cambridge United Kingdom

In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance. However, it is time-consuming and effort-costly to obtain high-quality point cloud data for place recognition model training and ground truth for registration in the real world. To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed. A structure-aware registration network is introduced to help to learn features with geometric information and a 6-DoFs pose between two point clouds with partial overlap can be estimated. The model is trained through a synthetic virtual LiDAR dataset through GTA-V with diverse weather and daytime conditions and domain adaptation is implemented to the real-world domain by aligning the global features. Our results outperform state-of-the-art 3D place recognition baselines or achieve comparable on the real-world Oxford RobotCar dataset with the visualization of registration on the virtual dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Improved Cascade Mask RCNN Single Character Detection Algorithm for Cast Pipe

Improved Cascade Mask RCNN Single Character Detection Algori...

引用

Big Data & Artificial Intelligence & Software Engineering (ICBASE), International Conference on

作者： Fuli Xu Yu Wang Yan Jiang Huaizhen Wang Yong Cui Ye Tao Yisheng Wang Qi Zhang School of Software Shenyang University of Technology Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Shanghai Ballsnow Intelligent Technology Co. Ltd Shanghai China Shenyang Zhongke Microcyber Technology Co. Ltd Shenyang China

Due to the interference of blurry background, character occlusion, and low background contrast in the Cast Pipe character images, the detection accuracy and real-time performance cannot meet the requirements of industrial scenes. To address these issues, this paper presents an improvement based on the Cascade Mask RCNN. Firstly, the Channel Attention Mechanism Module (Squeeze-and-Excitation, SE) is embedded into the ResNet structure. By constructing a bottleneck structure with two fully connected layers, the normalized weights are applied to each channel feature to enhance the network representation ability. Secondly, a bottom-up structure is introduced after the Feature Pyramid Networks (FPN) to transmit the strong localization information from lower-level features to higher-level semantic features. Thirdly, an adaptive pooling layer is added to allocate the candidate regions generated by the Region Proposal Network (RPN) to different scale feature maps. Additionally, skip connections are introduced between the bottom-level features and the highest-level features of each stage to reduce model parameters while retaining global representation capabilities. The improved algorithm is tested on a cast pipe dataset, achieving an average detection accuracy (mAP) of 98.7%, which is 2.7% higher than that of Cascade Mask RCNN. The accuracy indicates that the improved performance is superior to the original algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On stability of sampled-data extended state observer for networked systems

On stability of sampled-data extended state observer for net...

引用

Asian control Conference

作者： Yuan Huang Junzheng Wang Dawei Shi Jian Xue State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing P. R. China Harvard John A. Paulson School of Engineering & Applied Sciences Harvard University Cambridge MA USA

ISBN: (纸本)9781509015740;9781509015733

The problem of sampled-data state observation is considered in this work. A nonlinear continuous-time system with internal uncertainty and external disturbance is introduced, for which the sampled-data observation problem based on an extended state observer is formulated. We first introduce the framework of the observed system, in which the output measurement is sampled and transmitted to extended state observer periodically. Then based on this framework, the observation performance of the sampled-data extended state observer (SD-ESO) is investigated. For the observer considered, the uniformly ultimately bounded property has been guaranteed. Furthermore, a co-design method for the sample interval and high gain parameter of SD-ESO is provided to achieve the desired observation performance. The obtained theoretic results are validated through the numerical simulations.

关键词： Observers Uncertainty networked control systems Convergence Distributed databases Gold Australia

来源：评论

学校读者我要写书评

暂无评论

A Guide for Human Walking Model and control — Insights from Mechanical Property Analysis of Human Walking

A Guide for Human Walking Model and Control — Insights from...

引用

Chinese control and Decision Conference, CCDC

作者： Guangrong Chen Bowen Hou Sheng Guo Junzheng Wang Robotics Research Center Beijing Jiaotong University Beijing P.R. China Beijing Engineering and Technology Research Center of Rail Transit Line Safety and Disaster Prevention Beijing P.R. China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing P.R. China

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

This paper aims to establish the simplest human walking model and provide a guide for controlling biped robots. Firstly, a human motion capture system was utilized to sample the motion data of human walking and a representative subject was selected. Secondly, one of the simplest human walking model was set up. The mechanical property analysis of human walking was done based on the established walking model via fitting. Thirdly, the feasibility and effectiveness of proposed walking model were validated by numerical simulations. Finally, the intrinsical relationships among human walking, biped walking model and control were discussed to provide a guide and insight for controlling biped robots.

关键词： Legged locomotion Numerical models Force Analytical models Numerical simulation

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Trajectory Generation for Ground Robots beyond 2D Environment

arXiv

引用

arXiv 2023年

作者： Wang, Jingping Xu, Long Fu, Haoran Meng, Zehui Xu, Chao Cao, Yanjun Lyu, Ximin Gao, Fei State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China Huzhou Institute Zhejiang University Huzhou313000 China School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen518107 China Applicaion Innovation Laboratory Huawei Technologies Co. Ltd China

With the development of robotics, ground robots are no longer limited to planar motion. Passive height variation due to complex terrain and active height control provided by special structures on robots require a more general navigation planning framework beyond 2D. Existing methods rarely considers both simultaneously, limiting the capabilities and applications of ground robots. In this paper, we proposed an optimization-based planning framework for ground robots considering both active and passive height changes on the z-axis. The proposed planner first constructs a penalty field for chassis motion constraints defined in R3 such that the optimal solution space of the trajectory is continuous, resulting in a high-quality smooth chassis trajectory. Also, by constructing custom constraints in the z-axis direction, it is possible to plan trajectories for different types of ground robots which have z-axis degree of freedom. We performed simulations and real-world experiments to verify the efficiency and trajectory quality of our algorithm. Copyright © 2023, The Authors. All rights reserved.

关键词： Trajectories

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：