检索结果-内蒙古大学图书馆

Accurate and Robust Eye Center Localization via Fully Convolutional Networks

IEEE/CAA Journal of Automatica Sinica 2019年第5期6卷 1127-1138页

作者： Yifan Xia Hui Yu Fei-Yue Wang the School of Creative Technologies University of PortsmouthPortsmouthPO1 2DJUK the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Eye center localization is one of the most crucial and basic requirements for some human-computer interaction applications such as eye gaze estimation and eye tracking. There is a large body of works on this topic in recent years, but the accuracy still needs to be improved due to challenges in appearance such as the high variability of shapes, lighting conditions, viewing angles and possible occlusions. To address these problems and limitations, we propose a novel approach in this paper for the eye center localization with a fully convolutional network(FCN),which is an end-to-end and pixels-to-pixels network and can locate the eye center accurately. The key idea is to apply the FCN from the object semantic segmentation task to the eye center localization task since the problem of eye center localization can be regarded as a special semantic segmentation problem. We adapt contemporary FCN into a shallow structure with a large kernel convolutional block and transfer their performance from semantic segmentation to the eye center localization task by *** experiments show that the proposed method outperforms the state-of-the-art methods in both accuracy and reliability of eye center localization. The proposed method has achieved a large performance improvement on the most challenging database and it thus provides a promising solution to some challenging applications.

关键词： Deep learning eye center localization eye gaze estimation eye tracking fully convolutional network (FCN) humancomputer interaction

来源：评论

学校读者我要写书评

暂无评论

Learning to Manipulate Tools Using Deep Reinforcement Learning and Anchor Information

Learning to Manipulate Tools Using Deep Reinforcement Learni...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Junhang Wei Shaowei Cui Peng Hao Shuo Wang School of Future Technology University of Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China

ISBN: (纸本)9781665481106

Endowing robots with tool manipulation skills helps them accomplish challenging tasks. While robots manipulate tools to achieve goals, the alignment of tools and targets is a noise-sensitive and contact-rich task. However, it is difficult to access the accurate pose of the tool and the target. When there is unknown noise in the observations, reinforcement learning can't be sure to perform well. In this paper, we define the easier-to-obtain accurate task-related information as anchor information and introduce a tool manipulation method based on reinforcement learning and anchor information, which can perform well when the observations include unknown noise. To evaluate the method, we build a simulated environment ToolGym, which includes four different kinds of tools and different noise sampling functions for each tool. Finally, we compare our method with baseline methods to show the effectiveness of the proposed method.

关键词： Deep learning Biomimetics Reinforcement learning Grasping Fasteners End effectors Task analysis

来源：评论

学校读者我要写书评

暂无评论

Editorial Special Issue on Adaptive Dynamic Programming and Reinforcement Learning

引用

IEEE Transactions on systems, Man, and Cybernetics: systems 2020年第11期50卷 3944-3947页

作者： Liu, Derong Lewis, Frank L. Wei, Qinglai School of Automation Guangdong University of Technology Guangzhou510006 China Uta Research Institute University of Texas at Arlington Fort WorthTX76118 United States State Key Laboratory of Management and Control for Complex Systems Istitute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

The past decade has witnessed a surge in research activities related to adaptive dynamic programming (ADP) and reinforcement learning (RL), particularly for control applications. Several books [item 1)–5) in the Appendix] and survey papers [item 6)–10) in the Appendix] have been published on the subject. Both ADP and RL provide approximate solutions to dynamic programming problems. In a 1995 article by Barto et al. [item 11) in the Appendix], they introduced the so-called “adaptive real-time dynamic programming,” which was specifically to apply ADP for real-time control. Later, in 2002, Murray et al. [item 12) in the Appendix] developed an ADP algorithm for optimal control of continuous-time affine nonlinear systems. On the other hand, the most famous algorithms in RL are the temporal difference algorithm [item 13) in the Appendix] and the Q-learning algorithm [item 14) and 15) in the Appendix].

关键词： Special issues and sections Reinforcement learning Learning systems control systems Dynamic programming Real-time systems Optimal control

来源：评论

学校读者我要写书评

暂无评论

Online progressive instance-balanced sampling for weakly supervised object detection

arXiv

引用

arXiv 2022年

作者： Chen, Minghao Tian, Yunong Li, Zhishuo Li, En Liang, Zize The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences 95 Zhongguancun East Road Beijing100190 China Yuquan Road Beijing100049 China Engineering Laboratory of Industrial Vision and Intelligent Equipment Technology Chinese Academy of Sciences 95 Zhongguancun East Road Beijing100190 China

Based on multiple instance detection networks (MIDN), plenty of works have contributed tremendous efforts to weakly supervised object detection (WSOD). However, most methods neglect the fact that the overwhelming negative instances exist in each image during the training phase, which would mislead the training and make the network fall into local minima. To tackle this problem, an online progressive instance-balanced sampling (OPIS) algorithm based on hard sampling and soft sampling is proposed in this paper. The algorithm includes two modules: a progressive instance balance (PIB) module and a progressive instance reweighting (PIR) module. The PIB module combining random sampling and IoU-balanced sampling progressively mines hard negative instances while balancing positive instances and negative instances. The PIR module further utilizes classifier scores and IoUs of adjacent refinements to reweight the weights of positive instances for making the network focus on positive instances. Extensive experimental results on the PASCAL VOC 2007 and 2012 datasets demonstrate the proposed method can significantly improve the baseline, which is also comparable to many existing state-of-the-art results. In addition, compared to the baseline, the proposed method requires no extra network parameters and the supplementary training overheads are small, which could be easily integrated into other methods based on the instance classifier refinement paradigm. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

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

arXiv

引用

arXiv 2022年

作者： Liu, Shujuan Cui, Shaowei Zhang, Chaofan Cai, Yinghao Wang, Shuo The University of Science and Technology Beijing China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Institute of Automation Chinese Academy of Sciences Beijing100190 China The Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China

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 real-time 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. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Network agenda setting and social cognition construction of the dengue fever epidemic event based on social media big data 2

Network agenda setting and social cognition construction of ...

引用

23rd Pacific Asia Conference on Information systems: Secure ICT Platform for the 4th Industrial Revolution, PACIS 2019

作者： Wang, Yuejiao Cao, Zhidong State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Science Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

This article collected dengue-related information in China from News, Apps, Forums, Microblog and WeChat. We extract the 100 highest frequency of agenda settings from News, and built agenda setting networks of the five platforms respectively. Social network analysis methods are used to reveal the characteristics of these five agenda setting networks and the QAP is used to test the correlation between them. The robustness analysis of the results is applied. We found that: the information dissemination in dengue can be roughly divided into three categories: epidemic situation and change, prevention and control measures, and epidemic outbreak area;The context of News has the highest similarity with Apps (correlation coefficient=0.9561, p © Proceedings of the 23rd Pacific Asia Conference on Information systems: Secure ICT Platform for the 4th Industrial Revolution, PACIS 2019.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Finding Patterns in Adversarial Training

Finding Patterns in Adversarial Training

引用

Chinese automation Congress (CAC)

作者： Yutong Wang Fei-Yue Wang The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

Adversarial training has become an universally accepted robust method to train networks defending against adversarial attacks. However, feeding networks with adversarial examples is a cumbersome process, and there is no clear explanation for the differences between networks with the same architecture that are learned by adversarial training and learned by natural training method. So in this paper, we focus on the patterns of network learned by adversarial training. For comparison, we visualize the weights and feature maps of networks learned by these two training methods on MNIST, and find some patterns of adversarially trained model that are important for defending against adversarial examples and that are unique to naturally trained model. First, we find that adversarially trained network denoises the noisy data caused by adversarial images and enhances the outlines of semantically informative content in feature maps. Second, we find that adversarial training performs model compression, making some of the channels of a convolutional layer have no activation on input images. Further observation shows that different from naturally trained model, which have different most activation channel corresponding to different input, adversarially trained model often has the same most activation channel regardless of input. This phenomenon also leads to a sparse network reducing 50% number of parameters and 87% computation costs, and the pruned network performs as good as original network after pruning the least activation channels without retraining. But the naturally trained counterpart loses more than 40% accuracy using the same pruning strategy.

关键词： Training Kernel Robustness Perturbation methods Visualization Computational modeling Noise reduction

来源：评论

学校读者我要写书评

暂无评论

Research on trajectory planning and motion control of 7-DoF sawyer manipulator 1

Research on trajectory planning and motion control of 7-DoF ...

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Luo, Kun Xiong, Gang Wang, Yuxiao Hu, Bin Liu, Sheng Chen, Shichao Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems Beijng China School of Artificial Intelligence University of Chinese Academy of Sciences Beijng China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Beijng China Qingdao Academy of Intelligent Industries Chinese Academy of Sciences Beijng China

ISBN: (纸本)9781665433372

Regarding human-machine collaborative task, generated trajectories of a robot manipulator should be able to avoid joint limits and singularities, but the 6 Degrees of Freedom(DoF) or lower DoF manipulators encounter difficulties in many schemes. In this paper, research is implemented on the methods of trajectory planning and motion control on the newly human-machine collaborative 7-DoF Sawyer manipulator. We try to pay more attention to these approaches and find a better combination between trajectory planners and motion controllers for Sawyer manipulator. First of all, comparison is proposed between the methods about trajectory planning in task space and joint space, drawing a conclusion that the latter has the advantage of quickness and smoothness on trajectories in real time. Next, we choose to plan trajectory in the joint space by interpolating positions and orientations. Three approaches, i.e., trapezoidal velocity trajectory, cubic polynomial trajectory and basic spline trajectory, are applied to interpolate positions. Experimental results show that it results in the smoothest trajectory using basic spline trajectory planning. We also compare linear and nonlinear orientation interpolations to address the angle wrapping issue, which leads to difficulties in smooth orientation interpolation between several waypoints. Combining polynomial trajectory planning methods with the proportional-derivative (PD) motion controller and the computed-torque motion controller, we focus on the performance of the two different combinations. It is found that trajectories with computed-torque controller have shorter path with a congruous convergence on joint position, and more accurate trajectories with less overshoots in position than others. © 2021 IEEE.

关键词： Motion control

来源：评论

学校读者我要写书评

暂无评论

Continuous-Time Linear Parallel control

Continuous-Time Linear Parallel Control

引用

Chinese automation Congress (CAC)

作者： Qinglai Wei Hongyang Li Fei-Yue Wang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

This paper presents a continuous-time linear parallel control by modeling the derivative of system control with respect to time. The framework and properties of continuous-time linear parallel control are first presented. Then, considering the controllability, the pole assignment theorems will be analyzed. Finally, two examples show the correctness of continuous-time linear parallel control.

关键词： control systems controllability control theory complex systems Adaptive control Numerical analysis Linear systems

来源：评论

学校读者我要写书评

暂无评论

Real-world Robot Reaching Skill Learning Based on Deep Reinforcement Learning

Real-world Robot Reaching Skill Learning Based on Deep Reinf...

引用

Chinese control and Decision Conference, CCDC

作者： Naijun Liu Tao Lu Yinghao Cai Rui Wang Shuo Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

Traditional programming method can achieve certain manipulation tasks with the assumption that robot environment is known and structured. However, with robots gradually applied in more domains, robots often encounter working scenes which are complicated, unpredictable, and unstructured. To overcome the limitation of traditional programming method, in this paper, we apply deep reinforcement learning (DRL) method to train robot agent to obtain skill policy. As policy trained with DRL on real-world robot is time-consuming and costly, we propose a novel and simple learning paradigm with the aim of training physical robot efficiently. Firstly, our method train a virtual agent in an simulated environment to reach random target position from random initial position. Secondly, virtual agent trajectory sequence obtained with the trained policy, is transformed to real-world robot command with coordinate transformation to control robot performing reaching tasks. Experiments show that the proposed method can obtain self-adaptive reaching policy with low training cost, which is of great benefits for developing intelligent and robust robot manipulation skill system.

关键词： Robot kinematics Training Task analysis Machine learning Trajectory Neural networks

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：