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

Social Manufacturing for High-end Apparel Customization

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2018年第2期5卷 489-500页

作者： Xiuqin Shang Fei-Yue Wang Gang Xiong Timo R. Nyberg Yong Yuan Sheng Liu Chao Guo Sen Bao State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Science at Aalto University Aalto FI-00076 Finland Qingdao Academy of Intelligent Industries Qingdao 266109 China IEEE

Social manufacturing(SM), a novel distributed,collaborative and intelligent manufacturing mode, is proposed and developed for high-end apparel customization. The main components of SM cloud are designed, and its research topics are summarized. Then, SM's key technologies are studied. 3D technologies for apparel customization, like 3D modeling, 3D fitting mirror and 3D customization, are developed to improve the customization precision and user experience. Information based collaborative management is realized to share, communicate,and handle the information efficiently among all groups and individuals of SM cloud. Suppliers' evaluation mechanism is designed to support the optimal decisions making. Next, SM cloud is constructed in five layers for high-end apparel *** using SM cloud based crowd-sourcing, social resources can be allocated rationally and utilized efficiently, consumer can customize the product in any processes like innovation, design,making, marketing and service, and traditional apparel enterprise can be upgraded into SM mode for keeping it competitive in the future customization markets.

关键词： Index Terms-Big data collaborative management social man-ufacturing cloud 3D apparel customization.

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

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

Urban Trip Generation Forecasting Based on Gradient Boosting Algorithm

学校读者我要写书评

暂无评论

Urban Trip Generation Forecasting Based on Gradient Boosting...

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Zhishuai Li Gang Xiong Yu Zhang Meng Zheng Xisong Dong Yisheng Lv State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China Beijing Municipal Institute of City Planning and Design Beijing China

The four-step transportation model plays an important role in urban planning. The quality of the first phase, i.e. trip generation, determines the performance of the global course. The majority of trip generation forecasting models highly rely on mathematical derivation and have many predictor variables during the prediction, which leads to low accuracy of results and requires laboriously hand-crafted design of input vectors. This paper is the first to introduce the gradient boosting decision tree (GBDT) algorithm for trip generation prediction, and harmonizes such a powerful machine learning method with traditional urban planning requirements to achieve better prediction performance. Unlike the commonly used linear regression method, GBDT can automatically perform feature selection and model the non-linear relationships between input and output variables. Experimental results on real-world residential travel census in Beijing prove that the GBDT model significantly outperforms the baseline and can forecast the trip generation more accurately.

关键词： Machine learning algorithms Urban planning Transportation Predictive models Prediction algorithms Feature extraction Boosting

Compare contact model-based control and contact model-free learning: A survey of robotic peg-in-hole assembly strategies

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xu, Jing Hou, Zhimin Liu, Zhi Qiao, Hong State Key Laboratory of Tribology Beijing Key Laboratory of Precision/Ultra-Precision Manufacturing Equipment Control Department of Mechanical Engineering Tsinghua University Beijing100084 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

In this paper, we present an overview of robotic peg-in-hole assembly and analyze two main strategies: Contact model-based and contact model-free strategies. More specifically, we first introduce the contact model control approaches, including contact state recognition and compliant control two steps. Additionally, we focus on a comprehensive analysis of the whole robotic assembly system. Second, without the contact state recognition process, we decompose the contact modelfree learning algorithms into two main subfields: Learning from demonstrations and learning from environments (mainly based on reinforcement learning). For each subfield, we survey the landmark studies and ongoing research to compare the different categories. We hope to strengthen the relation between these two research communities by revealing the underlying links. Ultimately, the remaining challenges and open questions in the field of robotic peg-in-hole assembly community are discussed. The promising directions and potential future work are also considered. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

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

3D Deep Learning for 3D Printing of Tooth Model

学校读者我要写书评

暂无评论

3D Deep Learning for 3D Printing of Tooth Model

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Liu, Yiwen Shang, Xiuqin Shen, Zhen Hu, Bin Wang, Zhihai Xiong, Gang State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing University of Technology Faculty of Information Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Chinese Academy of Sciences Beijing China Beijing University of Technology Faculty of Information Beijing China

ISBN: (纸本)9781728128535

Recently, with the development of both 3D sensors and 3D virtual network that bring the needs of interaction with the real world, many 3D applications burst out. However, it is difficult to understanding these three-dimensional scenes with a fixed program. Then, a data-driven method is required to process these 3D data, which brings a strong demand of 3D Deep Learning in 3D data. Towards this goal, with an end-to-end deep learning, the experiment is based on PointNet++, a well proposed method for feature extraction. The experiment optimizes the network structure and parameters to improve the classification results. Finally, the network is applied to tooth model for classification and identification so that the dental model can be found from different perspectives. © 2019 IEEE.

关键词： 3D printers

Energy Analysis of a CPG-controlled Miniature Robotic Fish

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2018年第2期15卷 260-269页

作者： Junzhi Yu Shifeng Chen Zhengxing Wu Xingyu Chen Ming Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China School of lnformation and Electrical Engineering Shandong Jianzhu University Jinan 250101 China

Bionic robotic fish has a significant impact on design and control of innovative underwater robots capable of both rapid swimming and high maneuverability. This paper explores the relationship between Central Pattern Generator （CPG） based locomotion control and energy consumption of a miniature self-propelled robotic fish. To this end, a real-time energy measurement system compatible with the CPG-based locomotion control is firstly built on an embedded system. Then, tests are conducted on the untethered actual robot. The results indicate that different CPG feature parameters involving amplitude, frequency, and phase lag play distinct roles in energy consumption under different swimming gaits. Specifically, energy consumption is positively correlated with the changes in the amplitude and frequency of CPGs, whereas the phase lag of CPGs has little influence on the energy consumption. It may offer important inspiration for improving energy efficiency and locomotion performance of versatile swimming gaits.

关键词： bionic robotic fish energy analysis Central Pattern Generator （CPG） swimming motion control