检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Lu, Xiangri Ma, Hongbin Zhang, Jingcheng State Key Laboratory of Intelligent Decision and Control for Complex Systems Beijing Institute ofTechnology Beijing China Institute of Pattern Recognition and Intelligent Systems School of Automation Beijing Institute ofTechnology China Institute of Navigation Guidance and Control School of Automation Beijing Institute of

Recent work has shown that the activation function of the convolutional neural network can meet the Lipschitz condition, then the corresponding convolutional neural network structure can be constructed according to the scale of the data set, and the data set can be trained more deeply, more accurately and more effectively. In this article, we have accepted the experimental results and introduced the core block N − Gauss, N − Gauss, and Swish (Conv1, Conv2, FC1) neural network structure design to train MNIST, CIFAR10, and CIFAR100 respectively. Experiments show that N − Gauss gives full play to the main role of nonlinear modeling of activation functions, so that deep convolutional neural networks have hierarchical nonlinear mapping learning capabilities. At the same time, the training ability of N − Gauss on simple one-dimensional channel small data sets is equivalent to the performance of ReLU and Swish. Copyright © 2021, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Robust control of Feeding Speed for Coal Mine Tunnel Drilling Machines

Robust Control of Feeding Speed for Coal Mine Tunnel Drillin...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Xiao Liu Luefeng Chen Min Wu Weihua Cao Chengda Lu Witold Pedrycz School of Automation China University of Geosciences Wuhan China School of Automation the Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems and the Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland Department of Computer Engineering Istinye University Sariyer/Istanbul Turkey

ISBN: (数字)9798350340266

ISBN: (纸本)9798350340273

Changes in coal seam hardness cause fluctuations in the feed resistance at the drill bit during the drilling process, leading to unstable feeding speed. This paper proposes a robust dynamic output feedback controller to suppress disturbances caused by the variations in coal seam hardness in the feed system. Firstly, an unknown parameter measuring coal seam hardness is introduced, and an uncertain model of the feeding system is established based on the finite element model of the drill string. By designing weighted functions based on industrial field requirements and constructing a generalized plant, the controller achieves loop shaping, reducing the low-frequency impact of coal seam hardness variations on the feed system and suppressing the systems resonance peak. Simulation results demonstrate that the controller effectively suppresses parameter variations and external disturbances caused by changes in coal seam hardness, achieving stable control of the drilling speed.

关键词： Drilling Robust control Uncertainty Robust stability Simulation Coal Resonance

来源：评论

学校读者我要写书评

暂无评论

Stick-Slip Vibration Suppression Based on Multi-modal Analysis and Equivalent - Input-Disturbance Method

Stick-Slip Vibration Suppression Based on Multi-modal Analys...

引用

Asian control Conference

作者： Lingfeng Mu Hengyu Huang Haitao Song Zhejiaqi Ma Chengda Lu Min Wu School of Future Technology China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China School of Automation China University of Geosciences Wuhan China CCTEG Xi 'an Research Institute (Group) Co. Ltd. Xi'an China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

This work investigates the active suppression of stick-slip vibration based on the multi-modal analysis and equivalent-input-disturbance (EID) method. By building a lumped parameter model with a high degree of freedom, the multi-modal properties of the vibration are examined. The multi-modal disturbance signals of the drilling string system are analyzed using the variational modal decomposition method. The EID method is used to design a vibration suppression controller. The parameters in the EID method are adjusted based on the primary modal frequencies to obtain the equivalent disturbance at the appropriate frequency. According to the simulation results, the proposed approach improves the effectiveness of active vibration suppression of the drill string, which is of some significance in guiding the drilling operation.

关键词： Vibrations Drilling Accuracy Perturbation methods Modal analysis Simulation Buildings

来源：评论

学校读者我要写书评

暂无评论

Efficient Multi-Robot Coverage of an Unknown Environment

Efficient Multi-Robot Coverage of an Unknown Environment

引用

第40届中国控制会议

作者： Zihao Chen Zhihong Peng Lei Jiao Yuanyuan Gui School of Automation Beijing Institute of Technology China State Key Laboratory of Intelligent Control and Decision of Complex System

This paper discusses the complete area coverage of multi-robots in unknown environments. Finding the optimal solution for the problem of area coverage with multiple robots has been proven to be NP-hard. This paper proposes the Multiagent Node Backtracking Area Coverage（MANBAC） algorithm, which uses improved BCD local area coverage method, and the node backtracking method that is based on the A* algorithm to achieve complete coverage of the entire unknown *** with the area coverage of a single robot, use multi robots can greatly improve the efficiency of area *** with the existing coverage algorithms in known area, this study can be applied to a wider range of area scenarios which are not known.

关键词： Area coverage Unknow environment Multirobot

来源：评论

学校读者我要写书评

暂无评论

Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learning

arXiv

引用

arXiv 2022年

作者： Zhang, Lu Qi, Lu Yang, Xu Qiao, Hong Yang, Ming-Hsuan Liu, Zhiyong State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China The School of Artificial Intelligence University of Chinese Academy of Sciences China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences China University of California Merced United States

This paper tackles the problem of novel category discovery (NCD), which aims to discriminate unknown categories in large-scale image collections. The NCD task is challenging due to the closeness to the real world scenarios, where we have only encountered some partial classes and images. Unlike other works on the NCD, we leverage the prototypes to emphasize the importance of category discrimination and alleviate the issue with missing annotations of novel classes. Concretely, we propose a novel adaptive prototype learning method consisting of two main stages: prototypical representation learning and prototypical self-training. In the first stage, we obtain a robust feature extractor, which could serve for all images with base and novel categories. This ability of instance and category discrimination of the feature extractor is boosted by self-supervised learning and adaptive prototypes. In the second stage, we utilize the prototypes again to rectify offline pseudo labels and train a final parametric classifier for category clustering. We conduct extensive experiments on four benchmark datasets, and demonstrate the effectiveness and robustness of the proposed method with the state-of-the-art performance. The source code and trained models will be made available at this github site. Copyright © 2022, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Resource Scheduling Base on Bayesian Cramer-Rao Lower Bound for Multi-Target Tracking in Netted Colocated MIMO Radar systems

Resource Scheduling Base on Bayesian Cramer-Rao Lower Bound ...

引用

第40届中国控制会议

作者： Sijian Liao Zhihong Peng Junqi Cai School of Automation Beijing Institute of Technology China State Key Laboratory of Intelligent Control and Decision of Complex System

In this paper, an effective joint beam selection and power allocation（JBSPA） method is proposed to solve the online resource scheduling problem for multi-target tracking in distributed MIMO radar system. Overall target tracking performance can be improved by optimizing radar system beam selection and power allocation, since each MIMO radar can generate a timevarying beam, and adjust the quality of the observed signal by controlling the transmit power of each beam. In our method the feedback information of the target tracking period is used to complete the optimal radar-targets assignment and power allocation,the objective function is formulated based on the Bayesian Cramér-Rao lower bound, as the formulated JBSPA problem is nonconvex, a three steps solution method based on reward matrix is proposed to solve it effectively. Numerical results show that the proposed JBSPA method can deliver better performance than the competitors in overall MTT performance.

关键词： Resource Scheduling BCRLB Target Tracking Power Allocation MIMO Radar systems

来源：评论

学校读者我要写书评

暂无评论

Learning Latent Causal Factors from the Intricate Sensor Feedback of Contact-Rich Robotic Assembly Tasks

SSRN

引用

SSRN 2023年

作者： Chen, Yurou Yu, Jiyang Lin, Zhenyang Shen, Liancheng Liu, Zhiyong The State Key Lab of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China Beijing Institute of Spacecraft System Engineering China Academy of Space Technology Beijing China

Achieving precise robotic assembly is paramount for safety and performance in industrial settings. Conventional assembly methods require tedious manual adjustment of many parameters, and it is challenging to meet the assembly requirements with tight clearance. Robot learning has been at the forefront of research, showing potential for automation and intelligence in robotic operations. However, intricate information such as force feedback is indispensable for high-precision robot assembly tasks, and current learning methods grapple with processing this complex observation data due to discontinuous force changes during operation and the inherent noise from the force sensor. To alleviate the low learning efficiency from the problematic observations, we propose introducing the concept of latent causal factors that cause the sensor observations and truly matter in assembly tasks. This paper analyses the impact of discontinuous and noisy observations and offers two ways to infer causal factors. Based on the implied latent factors, we propose a method that learns high-precision assembly policies from interacting with the environment. The algorithm's performance is evaluated in simulated and real-world nut assembly environments, demonstrating significant improvements over the previous methods. This research also underscores the promise of causal inference in addressing intricate industrial challenges%. © 2023, The Authors. All rights reserved.

关键词： Robotic assembly

来源：评论

学校读者我要写书评

暂无评论

A-STC: auction-based spanning tree coverage algorithm for motion planning of cooperative robots

引用

Frontiers of Information Technology & Electronic Engineering 2019年第1期20卷 18-31页

作者： Guan-qiang GAO Bin XIN School of Automation Beijing Institute of Technology Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Advanced Innovation Center for Intelligent Robots and Systems

The multi-robot coverage motion planning(MCMP) problem in which every reachable area must be covered is common in multi-robot systems. To deal with the MCMP problem, we propose an efficient, complete, and off-line algorithm, named the "auction-based spanning tree coverage(A-STC)" algorithm. First, the configuration space is divided into mega cells whose size is twice the minimum coverage range of a robot. Based on connection relationships among mega cells, a graph structure can be obtained. A robot that circumnavigates a spanning tree of the graph can generate a coverage trajectory. Then, the proposed algorithm adopts an auction mechanism to construct one spanning tree for each robot. In this mechanism, an auctioneer robot chooses a suitable vertex of the graph as an auction item from neighboring vertexes of its spanning tree by heuristic rules. A bidder robot submits a proper bid to the auctioneer according to the auction vertexes' relationships with the spanning tree of the robot and the estimated length of its trajectory. The estimated length is calculated based on vertexes and edges in the spanning tree. The bidder with the highest bid is selected as a winner to reduce the makespan of the coverage task. After auction processes, acceptable coverage trajectories can be planned rapidly. Computational experiments validate the effectiveness of the proposed MCMP algorithm and the method for estimating trajectory lengths. The proposed algorithm is also compared with the state-of-the-art algorithms. The comparative results show that the A-STC algorithm has apparent advantages in terms of the running time and the makespan for large crowded configuration spaces.

关键词： Coverage motion planning Multi-robot system Auction algorithm Spanning tree coverage algorithm

来源：评论

学校读者我要写书评

暂无评论

Distributed Containment control of Markov Jump Multi-agent systems under Asynchronous Communications

Distributed Containment Control of Markov Jump Multi-agent S...

引用

第40届中国控制会议

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

This paper studies the distributed containment control issue for general Markov jump multi-agent systems. More specifically, a novel asynchronous mode-dependent communication scheme is proposed, which is based on observed communication mode information. By means of mode-dependent Lyapunov method, sufficient containment conditions are derived and communication protocol gains are further designed by convex optimization. A simulation example is finally presented to validate the correctness of our developed control scheme.

关键词： Distributed containment Markov jump multi-agent systems asynchronous communications

来源：评论

学校读者我要写书评

暂无评论

Real-Time Marker Localization Learning for GelStereo Tactile Sensing

Real-Time Marker Localization Learning for GelStereo Tactile...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Shujuan Liu Shaowei Cui Chaofan Zhang Yinghao Cai Shuo Wang University of Science and Technology Beijing State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Institute of Automation Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science Intelligence Technology Chinese Academy of Sciences Shanghai China

ISBN: (纸本)9781665481106

Visuotactile sensing technology is becoming more popular in tactile sensing, but the effectiveness of the existing marker detection/localization methods remains to be further explored. Instead of contour-based blob detection, this paper presents a learning-based marker localization network for GelStereo visuotactile sensing called Marknet. Specifically, the Marknet presents a grid regression architecture to incorporate the distribution of the GelStereo markers. Furthermore, a marker rationality evaluator (MRE) is modelled to screen suitable prediction results. The experimental results show that the Marknet combined with MRE achieves 93.90% precision for irregular markers in contact areas, which outperforms the traditional contour-based blob detection method by a large margin of 42.32%. Meanwhile, the proposed learning-based marker localization method can achieve better realtime performance beyond the blob detection interface provided by the OpenCV library through GPU acceleration, which we believe will lead to considerable perceptual sensitivity gains in various robotic manipulation tasks.

关键词： Location awareness Sensitivity Object detection Network architecture Predictive models Robot sensing systems Real-time systems

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：