检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Tang, Chufeng Chen, Hang Li, Xiao Li, Jianmin Zhang, Zhaoxiang Hu, Xiaolin State Key Laboratory of Intelligent Technology and Systems THU-Bosch JCML Center BNRist Institute for AI Department of Computer Science and Technology Tsinghua University China Institute of Automation CAS University of Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics HKISI CAS China

Tremendous efforts have been made on instance segmentation but the mask quality is still not satisfactory. The boundaries of predicted instance masks are usually imprecise due to the low spatial resolution of feature maps and the imbalance problem caused by the extremely low proportion of boundary pixels. To address these issues, we propose a conceptually simple yet effective post-processing refinement framework to improve the boundary quality based on the results of any instance segmentation model, termed BPR. Following the idea of looking closer to segment boundaries better, we extract and refine a series of small boundary patches along the predicted instance boundaries. The refinement is accomplished by a boundary patch refinement network at higher resolution. The proposed BPR framework yields significant improvements over the Mask R-CNN baseline on Cityscapes benchmark, especially on the boundary-aware metrics. Moreover, by applying the BPR framework to the "PolyTransform + SegFix" baseline, we reached 1st place on the Cityscapes leaderboard. Code is available at https://***/tinyalpha/BPR. Copyright © 2021, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Residual Squeeze-and-Excitation Network with Multi-scale Spatial Pyramid Module for Fast Robotic Grasping Detection

Residual Squeeze-and-Excitation Network with Multi-scale Spa...

引用

IEEE International Conference on robotics and automation (ICRA)

作者： Hu Cao Guang Chen Zhijun Li Jianjie Lin Alois Knoll Chair of Robotics Artificial Intelligence and Real-Time Systems Technische Universität München München Germany State Key Laboratory of Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Tongji University Shanghai China University of Science and Technology of China China

This paper proposes an efficient, fully convolutional neural network to generate robotic grasps by using 300×300 depth images as input. Specifically, a residual squeeze-and-excitation network (RSEN) is introduced for deep feature extraction. Following the RSEN block, a multi-scale spatial pyramid module (MSSPM) is developed to obtain multi-scale contextual information. The outputs of each RSEN block and MSSPM are combined as inputs for hierarchical feature fusion. Then, the fused global features are upsampled to perform pixel-wise learning for grasping pose estimation. The experimental results on Cornell and Jacquard grasping datasets indicate that the proposed method has a fast inference speed of 5ms while achieving high grasp detection accuracy of 96.4% and 94.8% on Cornell and Jacquard, respectively, which strikes a balance between accuracy and running speed. Our method also gets a 90% physical grasp success rate with a UR5 robot arm.

关键词： automation Conferences Pose estimation Grasping Manipulators Feature extraction Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

PublicGarbageNet : A Deep Learning Framework for Public Garbage Classification

PublicGarbageNet : A Deep Learning Framework for Public Garb...

引用

Chinese Control Conference (CCC)

作者： Ming Zeng Xiangzhe Lu Wenkang Xu Tongxi Zhou Yinbo Liu Institute of Robotics and Automation Systems School of Electrical and Information Engineering Tianjin University Tianjin P. R. China

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

Intelligent garbage classification is an important technique for garbage harmless, reducing and recycling treatment. In this paper, we propose a public garbage classification algorithm based on the CNN architecture, namely PublicGarbageNet. The proposed algorithm is a multi-task classification algorithm in which one task identifies four major categories of domestic garbage, and the other task achieves recognition of 10 subclasses garbage. The two classification tasks are related to each other, and the joint loss function is helpful to improve the accuracy of garbage recognition. Considering the fact that the existing garbage datasets are incomplete in classes and small in quantity, we constructed a new pubic garbage dataset including 10 subclasses and a total of 10624 images. In order to obtain better performance, systematically studies such as backbone optimization selection, data augmentation, learning rate optimization, and label smoothing have been made, and finally the accuracy of the optimized model reaches 96.35%.

关键词： Training Task analysis Plastics Metals Glass Machine learning Smoothing methods

来源：评论

学校读者我要写书评

暂无评论

An Easy-implemented Optimization Method of Trajectory Planning Based on Polynomial Interpolation

An Easy-implemented Optimization Method of Trajectory Planni...

引用

第40届中国控制会议

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

Firstly,the forward kinematics and inverse kinematics of a five axis manipulator are ***,an easyimplemented optimization method of trajectory planning based on seventh order polynomial interpolation is *** proposed optimization method can capture the time optimal trajectory,while the actuators specifications including speed,acceleration of motor can be guaranteed as ***,simulation results validate the effectiveness and efficiency of proposed optimization *** research provides an insight for the application of trajectory optimization on the controller with low computing capability and real-time requirement.

关键词： Trajectory planning Optimization method Polynomial interpolation Manipulator

来源：评论

学校读者我要写书评

暂无评论

A surgical dataset from the da Vinci Research Kit for task automation and recognition

arXiv

引用

arXiv 2021年

作者： Mariani, Andrea Rivas-Blanco, Irene Pérez-Del-Pulgar, Carlos J. Tortora, Giuseppe Reina, Antonio J. Dept. Systems Engineering and Automation University of Malaga Malaga Spain The BioRobotics Institute Dept. Excellence in Robotics & AI Scuola Superiore Sant’Anna Pisa Italy Smart Medical Theatre Lab ABzero srl Pisa Italy

The use of large datasets is essential in surgical robotics to advance in the field of recognition and automation of surgical tasks. Furthermore, public datasets allow the comparison of different algorithms and methods to evaluate their performance. The objective of this work is to provide a complete dataset of three common training surgical tasks performed with the da Vinci Research Kit (dVRK). The dataset contains a total of 206 trials performed by twelve different subjects. For each trial, the dataset includes 154 kinematic variables from the dVRK (both master and slave sides) together with the associated video recorded with a camera. All the data has been carefully timestamped and provided in a readable csv format. A MATLAB interface integrated with ROS for using and replicating the data is also provided. Copyright © 2021, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

A Novel Fractional Order Impedance Control and Its Performance Analysis

A Novel Fractional Order Impedance Control and Its Performan...

引用

第33届中国控制与决策会议

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

In traditional impedance control model,the contact force can be reduced ***,there exists a tracking error at the stable state due to the existence of stiffness,which is not conducive to tackle tasks based on high performance position control for ***,this paper proposes a novel dynamic interaction model:fractional order impedance control,to address this ***,an integral item is added into the traditional impedance model to eliminate the tracking ***,the idea of fractional order is introduced to make the orders of inertia,damping,and stiffness change from integers to fractions to achieve more significant compliant ***,simulation results validate the advantages of proposed fractional order impedance control and it can be also employed to absorb/increase,hold/keep,and dissipate/decrease system energy to achieve jumping,bouncing and friendly contact,***,stability analysis and three criterions of choosing and tuning 6 classic parameters in the proposed fractional order impedance control are both given out.

关键词： Dynamic interaction Compliance control Fractional order Impedance control Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Hair Direction Detection*

Hair Direction Detection*

引用

WRC Symposium on Advanced robotics and automation (WRC SARA)

作者： Peng Ba Pengyi Wang Hongde Wu Qian Yang Yongqiang Feng Junchen Wang Yida David Hu Changsheng Li Wenyong Liu Shaolong Kuang Bai-Quan Su Medical Robotics Laboratory School of Intelligent Engineering and Automation Beijing University of Posts and Telecommunications Beijing China Plastic Surgery Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China School of Mechanical Engineering and Automation Beihang University Beijing China Brigham and Women’s Hospital Harvard Medical School Boston MA USA School of Mechatronical Engineering Beijing Institute of Technology Beijing China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing China Key Laboratory for Biomechanics and Mechanobiology of Chinese Education Ministry Beijing Advanced Innovation Centre for Biomedical Engineering School of Biological Science and Medical Engineering Beihang University Beijing China School of Health Science and Environmental Engineering Shenzhen University of Technology Shenzhen China

ISBN: (数字)9798331506100

ISBN: (纸本)9798331506117

Hair direction is an important external feature of hair, and recognising hair direction is a prerequisite for processing hair. In this paper, a new algorithm is proposed and systematically verified experimentally for the problem of recognising hair direction. The main goal of this paper is to develop an algorithm that can identify hair direction in a complex image environment. A curve segment analysis method based on image skeletonisation is adopted, which is based on skeleton extraction, intersection identification, curve segmentation and direction prediction. In addition, this paper combines the technique of non-maximal value suppression and PCA analysis to improve the accuracy and stability of the estimation. In the experimental design, this paper chooses a representative image dataset to verify the effectiveness of this paper's algorithm. The experimental process includes the steps of image preprocessing, skeletonisation processing, intersection detection and merging, and direction prediction. The experimental results show that the method in this paper can accurately and effectively identify the hair direction. The main contribution of this paper is to propose a new hair direction recognition method and experimentally verify its effectiveness and accuracy in complex backgrounds.

关键词： Hair Image segmentation Accuracy Three-dimensional displays Merging Prediction algorithms Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Optimization of Simulation Parameters of Input Shaper Based on Genetic Algorithm

Optimization of Simulation Parameters of Input Shaper Based ...

引用

Advanced Technologies in Intelligent Control, Environment, Computing & Communication Engineering (ICATIECE), International Conference on

作者： Tao Yi Quanshen Pei Deying Li Shugong Wei Danping Jia Hualiang Zhang Hunan University of Information Changsha China School of Information Science and Engineering Shenyang University of Technology Shenyang China College of Physics and Electronic Engineering Guangxi Normal University for Nationalities Chongzuo China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9781665493970

In the motion control system, input shaper is often used to suppress the residual oscillation of high-precision positioning system, but the selection of input shaper parameters is difficult. In view of the difficulty of selecting input shaper parameters, this paper proposes to use genetic algorithm to select the parameters of input shaper. Firstly, the input shaper is designed in the light of the three-loop mathematical model of motor; Secondly, because the genetic algorithm directly optimizes the output of the motor and the algorithm can reduce the influence of the deviation of generator parameters on the parameter selection of the input shaper to a certain extent, the parameters of the input shaper are selected by the genetic algorithm to optimize the output of the motor; In the finish, a comparative experiment between a system with input shaper and a system with simple PID control is carried out. The results show that the optimized system can obtain higher robustness and smaller tracking deviation.

关键词： Vibrations Tracking Mathematical models Robustness Decoding Rigidity Motion control

来源：评论

学校读者我要写书评

暂无评论

Weakly Aligned Feature Fusion for Multi-modal Object Detection

arXiv

引用

arXiv 2022年

作者： Zhang, Lu Liu, Zhiyong Zhu, Xiangyu Song, Zhan Yang, Xu Lei, Zhen Qiao, Hong The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100086 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China The Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong The Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China

To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, depth, etc. However, multi-modal data often suffer from the position shift problem, i.e. the image pair is not strictly aligned, making one object has different positions in different modalities. For the deep learning method, this problem makes it difficult to fuse multi-modal features and puzzles the CNN training. In this paper, we propose a general multi-modal detector named Aligned Region CNN (AR-CNN) to tackle the position shift problem. Firstly, a region feature alignment module with adjacent similarity constraint is designed to consistently predict the position shift between two modalities and adaptively align the cross-modal region features. Secondly, we propose a novel RoI jitter strategy to improve the robustness to unexpected shift patterns. Thirdly, we present a new multi-modal feature fusion method, which selects the more reliable feature and suppresses the less useful one via feature re-weighting. Additionally, by locating bounding boxes in both modalities and building their relationships, we provide novel multi-modal labelling named KAIST-Paired. Extensive experiments on 2D and 3D object detection, RGB-T and RGB-D datasets demonstrate the effectiveness and robustness of our method. Copyright © 2022, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Keep off the grass: Permissible driving routes from radar with weak audio supervision

arXiv

引用

arXiv 2020年

作者： Williams, David Martini, Daniele De Gadd, Matthew Marchegiani, Letizia Newman, Paul Oxford Robotics Institute Dept. Engineering Science University of Oxford Automation and Control Dept. Electronic Systems Aalborg University

Reliable outdoor deployment of mobile robots requires the robust identification of permissible driving routes in a given environment. The performance of LiDAR and vision-based perception systems deteriorates significantly if certain environmental factors are present e.g. rain, fog, darkness. Perception systems based on Frequency-Modulated Continuous Wave scanning radar maintain full performance regardless of environmental conditions and with a longer range than alternative sensors. Learning to segment a radar scan based on driveability in a fully supervised manner is not feasible as labelling each radar scan on a bin-by-bin basis is both difficult and time-consuming to do by hand. We therefore weakly supervise the training of the radarbased classifier through an audio-based classifier that is able to predict the terrain type underneath the robot. By combining odometry, GPS and the terrain labels from the audio classifier, we are able to construct a terrain labelled trajectory of the robot in the environment which is then used to label the radar scans. Using a curriculum learning procedure, we then train a radar segmentation network to generalise beyond the initial labelling and to detect all permissible driving routes in the environment. Copyright © 2020, The Authors. All rights reserved.

关键词： Landforms

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：