检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Xinyu Wang, Li Jiang, Zhiqiang Dai, Kun Xie, Tao Yang, Lei Yu, Wenhao Shen, Yang Li, Jun The School of Vehicle and Mobility Tsinghua University Beijing100084 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150006 China

Local Feature Matching, an essential component of several computer vision tasks (e.g., structure from motion and visual localization), has been effectively settled by Transformer-based methods. However, these methods only integrate long-range context information among keypoints with a fixed receptive field, which constrains the network from reconciling the importance of features with different receptive fields to realize complete image perception, hence limiting the matching accuracy. In addition, these methods utilize a conventional handcrafted encoding approach to integrate the positional information of keypoints into the visual descriptors, which limits the capability of the network to extract reliable positional encoding message. In this study, we propose Feature Matching with Reconciliatory Transformer (FMRT), a novel Transformer-based detector-free method that reconciles different features with multiple receptive fields adaptively and utilizes parallel networks to realize reliable positional encoding. Specifically, FMRT proposes a dedicated Reconciliatory Transformer (RecFormer) that consists of a Global Perception Attention Layer (GPAL) to extract visual descriptors with different receptive fields and integrate global context information under various scales, Perception Weight Layer (PWL) to measure the importance of various receptive fields adaptively, and Local Perception Feed-forward Network (LPFFN) to extract deep aggregated multi-scale local feature representation. Besides, we introduce a novel Axis-Wise Position Encoder (AWPE) that perceives positional encoding as two independent keypoints encoding tasks along the row and column dimensions and utilizes two parallel network branches to decouple the X- and Y -coordinate information of keypoints, so that boosting the capability of the network to model position information for different images. Extensive experiments demonstrate that FMRT yields extraordinary performance on multiple benchmarks, including pos

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Effect of filament winding process parameters on interlaminar performance for CF/PP thermoplastic composite 4

Effect of filament winding process parameters on interlamina...

引用

4th International Conference on Graphene and Novel Nanomaterials, GNN 2022

作者： Chang, C. Geng, H.B. Feng, Y. Han, Z.Y. Sun, S.Z. State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China Inner Mongolia Aerospace Honggang Machinery Corporation Limited Hohhot010020 China Wuhu Robot Technology Research Institute Harbin Institute of Technology Wuhu241000 China

This paper focuses on the in-situ consolidation process of thermoplastic composites by winding, aiming to explore the influence of key process parameters on samples' quality. During the consolidation of thermoplastic composites, they need to go through resin melting-bonding-consolidation process, in which each parameter affects the interlaminar bond strength. Through preliminary simulation and experiments, the process parameters were selected. In this paper, wound NOL ring samples made of carbon fiber reinforced polypropylene thermoplastic composite prepregs were obtained with a hot gas assisted filament winding equipment. The influence rule of winding temperature, winding tension and winding speed on the interlaminar shear strength were analyzed based on response surface methodology. Through the analysis, in the range of the experiments winding tension and temperature had more effect on the shear strength while speed's influence was small. With the increase of tension and temperature, the interlaminar shear strength increased, but after reaching a certain value, the laminar shear strength decreased instead. © Published under licence by IOP Publishing Ltd.

关键词： Filament winding

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Derivation of Quintic Spline Interpolation and Its Applications to 3-D Collision-Free Trajectory Generation

A Comprehensive Derivation of Quintic Spline Interpolation a...

引用

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

作者： Boyu Ma Chunyu Zhou Yang Liu Baoshan Niu Feiyang Wen Sijiang Liu Zongwu Xie State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China Key Laboratory of Modern Mechanisms and Equipment Design of the State Ministry of Education Tianjin University Tianjin China

ISBN: (数字)9798350372601

ISBN: (纸本)9798350372618

For trajectory generation, quintic spline interpolation can ensure the zero velocities and accelerations of both the starting and ending points, presenting advantages not achievable by cubic spline interpolation. Due to the scarcity of quintic spline interpolation in existing research and applications, and considering its relatively intricate implementation process, this article presents a comprehensive derivation for its solution. Moreover, a three-dimensional (3-D) collision-free smooth trajectory scheme using quintic spline interpolation is proposed to generate collision-free and sufficiently smooth trajectories. Finally, two case studies are conducted to validate the effectiveness of quintic spline interpolation and the trajectory generation scheme in planning motion trajectories for robotic agents in a 3-D map with several obstacles.

关键词： Interpolation Real-time systems Trajectory Safety Planning Splines (mathematics) Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

Automated Adherent Cell Injection Method Based on Double-micropipettes Operation

Automated Adherent Cell Injection Method Based on Double-mic...

引用

第42届中国控制会议

作者： Zhaotong Chu Linxuan Cai MaoSheng Cui Zuqi Wang Yidi Zhang Minghui Li Qili Zhao Mingzhu Sun Xin Zhao Yaowei Liu Institute of Robotics and Automatic Information System The Tianjin Key Laboratory of Intelligent RoboticsNankai University Tianjin Academy of Agriculture Science Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University

Microinjection of adherent cells is a technique of inserting glass pipette into adherent cells and injecting few exogenous substances into adherent cells,which is widely used in the field of cell *** in this field usually inject adherent cells manually,however,the microinjection operation is complicated,which requires a lot of energy and takes a lot of *** existing automated microinjection method only uses one injection micropipette to inject,compared with the manual injection method,the microinjection process is consistent not optimized,and the injection efficiency cannot be greatly *** this paper,an automated adherent cell injection method based on double-micropipettes operation is ***,the adherent cell injection process based on double-micropipettes operation is ***,this paper solves the key technologies of automated injection of adherent cells based on double-micropipettes operation were introduced,including adherent cell detection,injection path planning and double-micropipettes ***,the experiment of adherent cell microinjection based on double-micropipettes operation,the operation of two micropipettes was carried *** experimental results show that the success rate of injection can reach 60% and the injection speed of this method can reach 35 cells/minute,which is 75% higher than that of manual injection with single pipette(20 cells/minute) and 40% higher than that of automated adherent cell injection with single pipette(25 cells/minute).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Map Construction Method Based on Brain-Inspired SLAM

Semantic Map Construction Method Based on Brain-Inspired SLA...

引用

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

作者： Hangpiao Zhao Fengzhen Tang The State Key Laboratory of Robotics Shenyang Institute of Automation Shenyang China The University of Chinese Academy of Sciences Shenyang Institute of Automation Beijing China

ISBN: (数字)9798331506056

ISBN: (纸本)9798331506063

Simultaneous localization and mapping (SLAM) is one of the core techniques for robots to move autonomously in unknown environments. Rat-SLAM, inspired by the navigation mechanism of the animal brain, provided nice performance in many environments. However, the experience map constructed by RatSLAM excluded semantic information, which is considered to play an important role in human environmental cognition and spatial navigation. In this paper, we propose a method to construct semantic experience map, combining the state-of-the-art deep neural network and RatSLAM. In our method, YOLOv5 is utilized to extract semantic information from the environmental images. The information of static objects, such as road signs, is selected to be incorporated into the experience map, being more closely to the brain navigation. To avoid the same object being repeatedly marked, we propose a semantic dynamic island mechanism, which only marks the center of the island in the experience map. The proposed method is verified on KITTI datasets, showing that it can successfully realize the construction of semantic experience map. The semantic experience maps are more intuitive and understandable by human, facilitating human-robot interaction, i. e. helping robots to fulfil more complex tasks for human.

关键词： YOLO Simultaneous localization and mapping Navigation Roads Semantics Human-robot interaction Detectors Data mining Intelligent systems Robots

来源：评论

学校读者我要写书评

暂无评论

SLAM-Based Joint Calibration of Differential RSS Sensor Array and Source Localization 49

SLAM-Based Joint Calibration of Differential RSS Sensor Arra...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Fu, Linya Qiao, Xu Huang, Shoudong Mao, Guoqiang Lin, Zhiyun Li, Youfu Kong, He Robotics Institute Uni. of Technology Sydney Sydney Australia Xidian University State Key Laboratory of Integrated Services Networks China City University of Hong Kong Department of Mechanical Engineering China Southern Uni. of Sci. and Tech. Shenzhen Key Laboratory of Control Theory and Intelligent Systems Shenzhen China Southern Uni. of Sci. and Tech. Guangdong Prov. Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Shenzhen China

ISBN: (纸本)9798350331820

Sensor arrays generating differential received signal strength (DRSS) measurements have found many applications in robotics. However, accurate calibration of these sensor arrays remains a challenge. Most existing methods are impractical in that they assume to know signal source positions or certain parameters (i.e., path loss exponent), and try to estimate the others. In this paper, we adopt graph simultaneous localization and mapping (SLAM) as a general framework for jointly estimating the source positions and parameters of the DRSS sensor array. Our contributions are twofold. On the one hand, by using a Fisher information matrix approach, we conduct a systematic observability analysis of the corresponding SLAM setup for the calibration problem. On the other hand, we propose an effective procedure to select the initial value which is fed to Levenberg-Marquardt iterations for further improving optimization accuracy and convergence. Extensive simulation and hardware experiments show that the proposed method renders high-quality calibration results. All the codes and data are publicly available at https://***/SUSTech2022/DRSS-sensor-array-calibration. © 2023 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

TGCN-P: A TCN-GCN Network With Weighted Graph Constructed by Pearson Correlation Coefficient for Human Motion Tracking

TGCN-P: A TCN-GCN Network With Weighted Graph Constructed by...

引用

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

作者： Xiaoyu Li Jingnan Wang Binhua Huang Chengliang Liu Yiwen Liu Yupo Zhang Zhengkun Yi Xinyu Wu Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen

Neural networks based on graph convolution are simple and effective network structures that have better performance in some fields compared to traditional convolutional networks. However, when graph convolution networks (GCN) are applied to other fields, how to transform data or features into graph edges is a challenge needed to be studied. In previous studies of non-Euclidean spatial data such as relationship studies, people achieve graph construction by indicating the connection or not of nodes with binary values. However, when graph network is applied to some multi-sensor data scenarios, especially human motion tracking tasks, binarization is obviously not the best solution for the weights of edges. In addition, relying on manual graph construction may ignore some cross-space sensor relationships, which makes the update information of nodes far away slower or unavailable. Therefore, we try to use Pearson correlation coefficient (PCC) as the estimation of node correlation, and construct a complete graph to enhance the connectivity of nodes, which achieve faster signal transmission at remote nodes. After combining it with the temporal convolutional network (TCN), we propose a new network structure TGCN-P. Experimentally, this approach is more effective compared to other baseline models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unified Vibration Suppression and Compliance Control for Flexible Joint Robot

引用

Transactions of Nanjing University of Aeronautics and Astronautics 2021年第3期38卷 361-372页

作者： CUI Shipeng SUN Yongjun LIU Yiwei LIU Hong State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001P.R.China

An adaptive control scheme is presented,which can simultaneously realize vibration suppression and compliance control for flexible joint robot(FJR).The proposed control scheme provides a unified formulation for both vibration suppression mode,where FJR tracks the desired position with little vibration,and compliance mode,in which FJR presents *** of designing multiple controllers and switching between them,both modes are integrated into a single controller,and the transition between two modes is smooth and *** stability of the closed-loop system is theoretically proven via the Lyapunov method,with the considering the dynamics uncertainties in both link side and motor *** results are presented to illustrate good performances of the proposed control scheme.

关键词： adaptive control scheme vibration suppression compliance flexible joint robot(FJR) stability

来源：评论

学校读者我要写书评

暂无评论

Two-Photon Image-Guided Automated 3D Locating of Micropipette Tip

Two-Photon Image-Guided Automated 3D Locating of Micropipett...

引用

第43届中国控制会议

作者： Zizhen Li Jie Li Qili Zhao Xin Zhao Mingzhu Sun National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases Engineering Research Center of Trusted Behavior Intelligence Ministry of Education Tianjin Key Laboratory of Intelligent Robotics (tikLIR) Institute of Robotics and Automatic Information System (IRAIS) Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The 21st century has been universally recognized by the scientific community as the era of neuroscience, with the patch clamp technique serving as a key to unraveling the intricate mysteries of brain science. Due to its advantages such as reduced sample damage and enhanced penetration capability, the application of two-photon microscope in deep imaging of live animals has become prevalent, making it a preferred choice over confocal microscope. At present, there exist a few near complete automation techniques of image-guided patching in vivo, which typically start from the micropipette tip appearing in the imaging field of view. The operational workflow for the step involving the installation of the micropipette until the micropipette tip becomes visible within the field of view has regrettably not been provided. However, it is crucial information that is of utmost importance to experimental personnel. In this paper, we present a comprehensive workflow for 3D locating of micropipette tip in a self-built two-photon microscope tailored for patch clamp experiments. Moreover, by fully incorporating the distinctive features of two-photon imaging, the study applies statistical methods to achieve automated execution of the corresponding workflow. The experimental results indicate that the process of micropipette tip locating takes an average of 58.4 ***, the method is not sensitive to parameter selection, allowing experimenters to obtain suitable parameters for different systems through simple testing. The automated 3D micropipette tip locating method proposed in this paper, with its versatility, holds great potential for seamless integration into commercial two-photon microscope systems. It significantly contributes to reducing the work burden on experimenters and minimizing the time required for experimental preparation.

关键词： 3D micropipette tip locating two-photon microscope automated method

来源：评论

学校读者我要写书评

暂无评论

SemanticTopoLoop: Semantic Loop Closure With 3D Topological Graph Based on Quadric-Level Object Map

arXiv

引用

arXiv 2023年

作者： Cao, Zhenzhong Liu, Jingtai The Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin300353 China The Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin300350 China

Loop closure, as one of the crucial components in SLAM, plays an essential role in correcting the accumulated errors. Traditional appearance-based methods, such as bag-of-words models, are often limited by local 2D features and the volume of training data, making them less versatile and robust in real-world scenarios, leading to missed detections or false positives detections in loop closure. To address these issues, we first propose a semantic loop closure method based on quadric-level object map topology, which represents scenes through the topological graph of quadric-level objects and achieves accurate loop closure at a wide field of view by comparing differences in the topological graphs. Next, in order to solve the data association problem between frame and map in loop closure, we propose a object-level data association method based on multilevel verification, which can associate 2D semantic features of current frame with 3D objects landmarks of map. Finally, we integrate these two methods into a complete object-aware SLAM system. Qualitative experiments and ablation studies demonstrate the effectiveness and robustness of the proposed object-level data association algorithm. Quantitative experiments show that our semantic loop closure method outperforms existing state-of-the-art methods in terms of precision, recall and localization accuracy metrics. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

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：