检索结果-内蒙古大学图书馆

Grasp State Assessment of Deformable Objects Using Visual-Tactile Fusion Perception

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Cui, Shaowei Wang, Rui Wei, Junhang Li, Fanrong Wang, Shuo State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Further Technology Universty of Chinese Academy of Sciences Beijing100190 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China

Humans can quickly determine the force required to grasp a deformable object to prevent its sliding or excessive deformation through vision and touch, which is still a challenging task for robots. To address this issue, we propose a novel 3D convolution-based visual-tactile fusion deep neural network (C3D-VTFN) to evaluate the grasp state of various deformable objects in this paper. Specifically, we divide the grasp states of deformable objects into three categories of sliding, appropriate and excessive. Also, a dataset for training and testing the proposed network is built by extensive grasping and lifting experiments with different widths and forces on 16 various deformable objects with a robotic arm equipped with a wrist camera and a tactile sensor. As a result, a classification accuracy as high as 99.97% is achieved. Furthermore, some delicate grasp experiments based on the proposed network are implemented in this paper. The experimental results demonstrate that the C3D-VTFN is accurate and efficient enough for grasp state assessment, which can be widely applied to automatic force control, adaptive grasping, and other visual-tactile spatiotemporal sequence learning problems. Copyright © 2020, The Authors. All rights reserved.

关键词： Deformation

Capsule Network-Based Text Sentiment Classification

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2020年第5期53卷 698-703页

作者： Bingyang Chen Zhidong Xu Xiao Wang Long Xu Weishan Zhang School of Computer Science and Technology China University of Petroleum Qingdao 266580 China School of security National Defence University PLA China Beijing 100091 China Beijing 100091 China Qingdao Academy of Intelligent Industries Shandong Qingdao 266109 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China

To improve text sentiments classification issues, such as information loss and insensitivity to spatial information, this paper proposes a text sentiment classification model based on the capsule network (T-Caps), which uses the Transformer to extract low-level text features. The method iteratively updates capsule network parameters through optimized dynamic routing algorithms and global parameter sharing, and it obtains the relationship between local features of the text and the overall emotional polarity to save the information integrity of text features. By comparing with multiple models, we find that the Transformer has the strongest feature extraction capability. The experimental results show that our model is capable of extracting more discriminative semantic features and yields a significant performance gain compared to other baseline methods.

关键词： Sentiment classification Capsule network Transformer Deep learning Attention

Multi-view adaptive fusion network for 3D object detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Guojun Tian, Bin Zhang, Yachen Chen, Long Cao, Dongpu Wu, Jian State Key Laboratory of Automotive Simulation and Control Jilin University Changchun130022 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China School of Data and Computer Science Sun Yat-Sen University Guangzhou510275 China Lab University of Waterloo Canada College of Automotive Engineering Jilin University China

3D object detection based on LiDAR-camera fusion is becoming an emerging research theme for autonomous driving. However, it has been surprisingly difficult to effectively fuse both modalities without information loss and interference. To solve this issue, we propose a single-stage multi-view fusion framework that takes LiDAR Birds-Eye View, LiDAR Range View and Camera View images as inputs for 3D object detection. To effectively fuse multi-view features, we propose an Attentive Pointwise Fusion (APF) module to estimate the importance of the three sources with attention mechanisms which can achieve adaptive fusion of multi-view features in a pointwise manner. Besides, an Attentive Pointwise Weighting (APW) module is designed to help the network learn structure information and point feature importance with two extra tasks: foreground classification and center regression, and the predicted foreground probability will be used to reweight the point features. We design an end-to-end learnable network named MVAF-Net to integrate these two components. Our evaluations conducted on the KITTI 3D object detection datasets demonstrate that the proposed APF and APW module offer significant performance gain and that the proposed MVAF-Net achieves state-of-the-art performance in the KITTI benchmark. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

Micro/nanoliter droplet extraction by controlling acoustic vortex with miniwatt

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Han Yang, Jun Zhou, Yun Zheng, Jianfeng Cheng, Yong Bai, Bichao Zhang, Guoxin Lv, Yisheng CAS Key Laboratory of Noise and Vibration Institute of Acoustics Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China The National Center for Nanoscience and Technology Beijing100190 China School of Mechanical Engineering Changzhou University Changzhou213164 China Institute of Mechanics School of Civil Engineering & Mechanics Yanshan University Qinhuangdao066004 China Al-ion Battery Research Center Department of Electrical Engineering and Automation Shandong University of Science and Technology Qingdao266580 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Micro/nanoliter droplet is capable of achieving versatile applications with tiny volume and substantial surface energy, which is a big plus over bulk liquid. Yet, the contradiction of elaborate manipulation and enough power is still a challenge. Here, we unleash the potential of our miniwatt aspirators pumping up liquid and creating droplets with the help of acoustic vortex beams, inspired by the power mechanism that spirals are significant for most mollusks that live in water. These droplet aspirators produce very large interface deformations by small radiation pressures with orbit angular momentum from spiral-electrode transducers. The precisely contactless manipulation of physical, chemical and biological objects at micrometric down to nanometric scales, promises tremendous development in fields as diverse as microrobotics, nanoreactors, or nanoassemblies. Copyright © 2021, The Authors. All rights reserved.

关键词： Vortex flow

Back Cover: PD-L1 Aptamer-Functionalized Metal–Organic Framework Nanoparticles for Robust Photo-Immunotherapy against Cancer with Enhanced Safety (Angew. Chem. Int. Ed. 5/2023)

学校读者我要写书评

暂无评论

Angewandte Chemie International Edition 2023年第5期62卷

作者： Dr. Jingfang Zhang Dr. Wenzhe Li Dr. Yafei Qi Dr. Guorong Wang Prof. Lele Li Prof. Zhengyu Jin Prof. Jie Tian Prof. Yang Du Beijing Key Laboratory for Bioengineering and Sensing Technology School of Chemistry and Biological Engineering University of Science and Technology Beijing Beijing 100083 China CAS Key Laboratory for Biomedical Effects of Nanomaterials and Nanosafety and CAS Center for Excellence in Nanoscience National Center for Nanoscience and Technology Beijing 100190 China State Key Laboratory of Natural and Biomimetic Drugs School of Pharmaceutical Sciences Peking University Beijing 100191 China CAS Key Laboratory of Molecular Imaging Beijing Key Laboratory of Molecular Imaging the State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Department of Radiology Peking Union Medical College Hospital Peking Union Medical College and Chinese Academy of Medical Sciences Beijing 100730 China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of Medicine Beihang University Beijing 100191 China

Adaptive Dynamic Programming Method for Optimal Battery management of Battery Electric Vehicle

学校读者我要写书评

暂无评论

Adaptive Dynamic Programming Method for Optimal Battery Mana...

Data Driven control and Learning systems (DDCLS)

作者： Jiguang Xue Chunsheng Yan Dan Wang Jun Wang Jun Wu Zehua Liao Electric Power Research Institute of State Grid Liaoning Electric Power Co. Ltd Shenyang China LiaoNing Electric Power Development Stock Co. LTD Shenyang China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728159225

ISBN: (纸本)9781728159232

One of the main influencing factors of battery electric vehicle (BEV) application is the high-cost of the battery. We consider to apply the battery of BEV to smart residential environments when the BEV is idle, so that we can lower the utility cost. Therefore, an adaptive dynamic programming (ADP) method is designed to solve the optimal battery management, which avoids the dimension disaster of the complex nonlinear BEV system. First, the operation modes of the battery are analyzed, and the problem statement is carried out. Then, the corresponding self-learning optimization algorithm is developed based on ADP. Finally, numerical results by experiment simulations are used to verify the ADP algorithm.

关键词： Batteries Optimal control Dynamic programming Battery management systems Power grids Discharges (electric) Adaptation models

Enhanced rolling horizon evolution algorithm with opponent model learning: Results for the fighting game ai competition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tang, Zhentao Zhu, Yuanheng Zhao, Dongbin Lucas, Simon M. State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Queen Mary University of London LondonE1 4NS United Kingdom

The Fighting Game AI Competition (FTGAIC) provides a challenging benchmark for 2-player video game AI. The challenge arises from the large action space, diverse styles of characters and abilities, and the real-time nature of the game. In this paper, we propose a novel algorithm that combines Rolling Horizon Evolution Algorithm (RHEA) with opponent model learning. The approach is readily applicable to any 2-player video game. In contrast to conventional RHEA, an opponent model is proposed and is optimized by supervised learning with cross-entropy and reinforcement learning with policy gradient and Q-learning respectively, based on history observations from opponent. The model is learned during the live gameplay. With the learned opponent model, the extended RHEA is able to make more realistic plans based on what the opponent is likely to do. This tends to lead to better results. We compared our approach directly with the bots from the FTGAIC 2018 competition, and found our method to significantly outperform all of them, for all three character. Furthermore, our proposed bot with the policygradient-based opponent model is the only one without using Monte-Carlo Tree Search (MCTS) among top five bots in the 2019 competition in which it achieved second place, while using much less domain knowledge than the winner. Copyright © 2020, The Authors. All rights reserved.

关键词： Supervised learning

INDReview on Facial Expression Analysis and its Application in Education

学校读者我要写书评

暂无评论

INDReview on Facial Expression Analysis and its Application ...

Chinese Automation Congress (CAC)

作者： Qiang Li Xiwei Liu Xiaoyan Gong Sifeng Jing The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Institute of Smart Education Systems Qingdao Academy of Intelligent Industries BeiJing China

In recent years, with the rapid development of computer technology, facial expression recognition technology has gradually been applied to primary and secondary schools. This article first introduces the application of facial expression recognition in education. Then the development of facial expression recognition and the four basic processes of facial expressions are described. After that, the methods and algorithms used in face detection and localization of face expression recognition and classification are summarized, feature extraction and classification are summarized. Finally, the current application of facial expression recognition technology in education and the existing problems and future development are pointed out.

关键词： Face recognition Classification algorithms Feature extraction Education Hidden Markov models Face detection Face

An Enhanced Fault Diagnosis Method with Uncertainty Quantification Using Bayesian Convolutional Neural Network

学校读者我要写书评

暂无评论

An Enhanced Fault Diagnosis Method with Uncertainty Quantifi...

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Qihang Fang Gang Xiong Xiuqin Shang Sheng Liu Bin Hu Zhen Shen State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences China

ISBN: (数字)9781728169040

ISBN: (纸本)9781728169057

Fault diagnosis is a vital technique to pinpoint the machine malfunctions in manufacturing systems. In recent years, the deep learning techniques greatly improve the fault detection accuracy, but there still remain some problems. If one fault is absent in the training data or the fault signal is disturbed by severe noise interference, the fault classifier may misjudge the health state. This problem limits the reliability of the fault diagnosis in real applications. In this paper, we enhance the fault diagnosis method by using Bayesian Convolutional Neural Network (BCNN). A Shannon entropy-based method is presented to quantify the prediction uncertainty. The BCNN turns the deterministic predictions to probabilistic distributions and enhances the robustness of the fault diagnosis. The uncertainty quantification method helps to indicate the wrong predictions, detect unknown faults, and discover the strong disturbances. Then, a fine-tuning strategy is applied to enhance the model performance further. The potential usability of the proposed method in monitoring the motors of 3D printers is studied. And the experiment is conducted on a motor bearing dataset provided by Case Western Reserve University. The proposed BCNN achieves 99.82% fault classification accuracy over nine health conditions. Its robustness is verified by comparing the testing accuracy with three other methods on the noisy datasets. And the uncertainty quantification method successfully detects the outlier inputs.

关键词： Fault diagnosis Uncertainty Bayes methods Circuit faults Robustness Predictive models Noise measurement