检索结果-内蒙古大学图书馆

Anchor-based spatio-temporal attention 3D convolutional networks for dynamic 3D point cloud sequences

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Guangming Chen, Muyao Liu, Hanwen Yang, Yehui Liu, Zhe Wang, Hesheng The Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Computer Science and Technology University of Cambridge

With the rapid development of measurwement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, but deep learning methods for dynamic 3D point cloud sequences are underexplored. Therefore, developing efficient and accurate perception method compatible with these advanced instruments is pivotal to autonomous driving and service robots. An Anchor-based Spatio-Temporal Attention 3D Convolution operation (ASTA3DConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on the spatio-temporal attention mechanism. Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points. The proposed method makes better use of the structured information within the local region and learns spatio-temporal embedding features from dynamic 3D point cloud sequences. Anchor-based Spatio-Temporal Attention 3D Convolutional Neural Networks (ASTA3DCNNs) are built for classification and segmentation tasks based on the proposed ASTA3DConv and evaluated on action recognition and semantic segmentation tasks. The experiments and ablation studies on MSRAction3D and Synthia datasets demonstrate the superior performance and effectiveness of our method for dynamic 3D point cloud sequences. Our method achieves the state-of-the-art performance among the methods with dynamic 3D point cloud sequences as input on MSRAction3D and Synthia datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

Optimize Student Learning via Random Forest-Based Adaptive Narrative Game

学校读者我要写书评

暂无评论

Optimize Student Learning via Random Forest-Based Adaptive N...

IEEE International Conference on automation Science and engineering (CASE)

作者： Ryan Hare Ying Tang Wei Cui Joleen Liang Department of Electrical and Computer Engineering Rowan University Glassboro USA State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Smart Education Qingdao Academy of Intelligent Industries Qingdao China Squirrel AI Learning Shanghai China

ISBN: (数字)9781728169040

ISBN: (纸本)9781728169057

This paper presents an adaptive narrative game system that focuses on sequential logic design. The system adapts a random forest machine learning model to estimate a student's current level of domain knowledge relative to the problem presented to him through his game-playing behavior data, such as time taken to find solutions, errors in solutions, and emotional indicators. Hints, prompts, and/or individualized lessons are then offered to the player to guide their learning in a positive and productive direction. Our preliminary pilot study demonstrates that the model can make accurate classifications, from which proper assistance can then be provided to individual students as they play.

关键词： Games Databases Forestry Education Problem-solving Presses Artificial intelligence

Cascade Terminal Sliding Mode Control of a Deployable Cable Driven Robot

学校读者我要写书评

暂无评论

Cascade Terminal Sliding Mode Control of a Deployable Cable ...

International Conference on Control, Instrumentation, and automation

作者： S. A. Khalilpour R. Khorrambakht M. J. Harandi H. D. Taghirad Philippe Cardou Advanced Robotics and Automated Systems Faculty of Electrical and Computer Engineering K.N. Toosi University of Technology Tehran Iran Department of Mechanical Engineering Robotics Laboratory Laval University Quebec City QC Canada

ISBN: (数字)9781728158150

ISBN: (纸本)9781728158167

Most control systems used for cable-driven parallel manipulators employ a simple inner control loop for controlling the driving force of the actuators. By this means the effects of some nonlinear uncertainties of the actuator and power transmission systems are significantly reduced, and in turn, this helps the outer user-specified position control loop to perform more accurately. However, this positive impact on performance relies on non achievable assumptions that the inner control loop is fast and accurate enough, and its dynamics can be totally ignored. The main contribution of this paper is to analyze the stability of the system as a whole, considering both inner and outer loop controllers. The outer loop controller proposed in here is a finite time robust sliding mode whose stability is analyzed through the Lyapunov direct method. A deployable cable-driven parallel robot, as the case study, is also considered in this paper, which is characterized by several intrinsic kinematic and dynamic uncertainties. Finally, the performance and effectiveness of the proposed robust controller is evaluated through some simulations and experiments in order to verify the effectiveness and the characteristics of the cascade controller structure in practice.

关键词： Robots Mathematical model Actuators Jacobian matrices Force Uncertainty Kinematics

Online multi-object tracking and segmentation with GMPHD filter and mask-based affinity fusion

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Song, Young-Min Yoon, Young-Chul Yoon, Kwangjin Jeon, Moongu Lee, Seong-Whan Pedrycz, Witold The School of Electrical Engineering and Computer Science Gwangju Institute of Technology Gwangju61005 Korea Republic of The Robotics Laboratory Hyundai Motor Company Gyeonggi-do 16082 Korea Republic of SI Analytics Co. Ltd. Daejeon34051 Korea Republic of The Department of Artificial Intelligence Korea University Seoul02841 Korea Republic of The Department of Brain and Cognitive Engineering Korea University Seoul02841 Korea Republic of The Department of Electrical and Computer Engineering University of Alberta EdmontonABT6R 2H5 Canada The Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia The Systems Research Institute Polish Academy of Sciences Warsaw01-447 Poland

In this paper, we propose a highly practical fully online multi-object tracking and segmentation (MOTS) method that uses instance segmentation results as an input. The proposed method is based on the Gaussian mixture probability hypothesis density (GMPHD) filter, a hierarchical data association (HDA), and a mask-based affinity fusion (MAF) model to achieve high-performance online tracking. The HDA consists of two associations: segment-to-track and track-to-track associations. One affinity, for position and motion, is computed by using the GMPHD filter, and the other affinity, for appearance is computed by using the responses from a single object tracker such as a kernalized correlation filter. These two affinities are simply fused by using a score-level fusion method such as min-max normalization referred to as MAF. In addition, to reduce the number of false positive segments, we adopt mask IoU-based merging (mask merging). The proposed MOTS framework with the key modules: HDA, MAF, and mask merging, is easily extensible to simultaneously track multiple types of objects with CPU-only execution in parallel processing. In addition, the developed framework only requires simple parameter tuning unlike many existing MOTS methods that need intensive hyperparameter optimization. In the experiments on the two popular MOTS datasets, the key modules show some improvements. For instance, ID-switch decreases by more than half compared to a baseline method in the training sets. In conclusion, our tracker achieves state-of-the-art MOTS performance in the test sets. Copyright © 2020, The Authors. All rights reserved.

关键词：

A registration-aided domain adaptation network for 3D Point cloud based place recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Qiao, Zhijian Hu, Hanjiang Shi, Weiang Chen, Siyuan Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Mechanical Engineering Carnegie Mellon University United States Department of Computer Science and Technology University of Cambridge United Kingdom

In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance. However, it is time-consuming and effort-costly to obtain high-quality point cloud data for place recognition model training and ground truth for registration in the real world. To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed. A structure-aware registration network is introduced to help to learn features with geometric information and a 6-DoFs pose between two point clouds with partial overlap can be estimated. The model is trained through a synthetic virtual LiDAR dataset through GTA-V with diverse weather and daytime conditions and domain adaptation is implemented to the real-world domain by aligning the global features. Our results outperform state-of-the-art 3D place recognition baselines or achieve comparable on the real-world Oxford RobotCar dataset with the visualization of registration on the virtual dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

Roadmap on soft robotics: multifunctionality, adaptability and growth without borders

学校读者我要写书评

暂无评论

Multifunctional Materials 2022年第3期5卷 032001-032001页

作者： Mazzolai, Barbara Mondini, Alessio Del Dottore, Emanuela Margheri, Laura Carpi, Federico Suzumori, Koichi Cianchetti, Matteo Speck, Thomas Smoukov, Stoyan K. Burgert, Ingo Keplinger, Tobias Siqueira, Gilberto De Freitas Vanneste, Felix Goury, Olivier Duriez, Christian Nanayakkara, Thrishantha Vanderborght, Bram Brancart, Joost Terryn, Seppe Rich, Steven I. Liu, Ruiyuan Fukuda, Kenjiro Someya, Takao Calisti, Marcello Laschi, Cecilia Sun, Wenguang Wang, Gang Wen, Li Baines, Robert Patiballa, Sree Kalyan Kramer-Bottiglio, Rebecca Rus, Daniela Fischer, Peer Simmel, Friedrich C Lendlein, Andreas Bioinspired Soft Robotics Laboratory Istituto Italiano di Tecnologia Italy Department of Industrial Engineering University of Florence Via di S. Marta 3 Florence50139 Italy Department of Mechanical Engineering Tokyo Institute of Technology Ookayama Meguro Tokyo152-8550 Japan The BioRobotics Institute Scuola Superiore Sant’Anna Pisa56025 Italy Department of Excellence in Robotics & AI Scuola Superiore Sant’Anna Pisa56025 Italy Plant Biomechanics Group & Botanic Garden and Cluster of Excellence livMatS @ FIT University of Freiburg Germany Active and Intelligent Materials Laboratory Queen Mary University of London LondonE1 4NS United Kingdom Wood Materials Science Institute for Building Materials ETH Zurich Zurich8093 Switzerland Cellulose and Wood Materials Laboratory Empa Swiss Federal Laboratories for Materials Science and Technology Dübendorf8600 Switzerland University of Lille Inria CNRS Centrale Lille UMR 9189 CRIStAL LilleF-59000 France Dyson School of Design Engineering Imperial College London United Kingdom Vrije Universiteit Brussel and imec Brussels Belgium Thin-Film Device Laboratory RIKEN 2-1 Hirosawa Saitama Wako351-0198 Japan Center for Emergent Matter Science RIKEN 2-1 Hirosawa Saitama Wako351-0198 Japan Electrical and Electronic Engineering and Information Systems The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan The BioRobotics Institute Scuola Superiore Sant’Anna Italy Lincoln Institute for Agri-food Technology University of Lincoln Lincoln United Kingdom Department of Mechanical Engineering National University of Singapore Singapore School of Mechanical Engineering and Automation Beihang University Beijing100191 China Department of Mechanical Engineering and Materials Science Yale University New HavenCT06511 United States CSAIL MIT Schwarzman College of Computing United States Max Planck Institute for Intelligent Systems Heisenbergstr. 3 Stuttgart70569 Germany Institute of Physical Chemistry

Soft robotics aims at creating systems with improved performance of movement and adaptability in unknown, challenging, environments and with higher level of safety during interactions with humans. This Roadmap on Soft robotics covers selected aspects for the design of soft robots significantly linked to the area of multifunctional materials, as these are considered a fundamental component in the design of soft robots for an improvement of their peculiar abilities, such as morphing, adaptivity and growth. The roadmap includes different approaches for components and systems design, bioinspired materials, methodologies for building soft robots, strategies for the implementation and control of their functionalities and behavior, and examples of soft-bodied systems showing abilities across different environments. For each covered topic, the author(s) describe the current status and research directions, current and future challenges, and perspective advances in science and technology to meet the challenges. © 2022 The Author(s). Published by IOP Publishing Ltd.

关键词： Machine design

GardnerNet: An Interpretable Deep Learning Model for Quantitative Human Blastocyst Evaluation - A Retrospective Model Development and Validation Study

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Liu, Hang Chen, Longbin Shan, Guanqiao Sun, Chen Liao, Hongqing Lu, Changfu Zhang, Shuoping Dong, Shaonan Xu, Xinxin Yan, Qiuyun Gong, Fei Zhang, Zhuoran Dai, Changsheng Chen, Wenyuan Song, Haocong Chen, Lei Sun, Haixiang Wang, Shanshan Lin, Ge Sun, Yu Gu, Yifan Department of Mechanical and Industrial Engineering University of Toronto 5 King’s College Road TorontoONM5S 3G8 Canada Institute of Reproductive and Stem Cell Engineering School of Basic Medical Science Central South University 172 Tongzipo Road Hunan Province Changsha China Hengyang Nanhua-Xinghui Reproductive Health Hospital 30 Jiefang Road Hunan Province Hengyang China The second Affiliated Hospital Hengyang Medical School University of South China 30 Jiefang Road Hunan Province Hengyang City China Reproductive & Genetic Hospital of CITIC-Xiangya 567 Tongzipo Road Hunan Province Changsha China NHC Key Laboratory of Human Stem Cell and Reproductive Engineering School of Basic Medical Science Central South University 172 Tongzipo Road Hunan Province Changsha China Clinical Research Center for Reproduction and Genetics in Hunan Province Reproductive & Genetic Hospital of CITIC-Xiangya 567 Tongzipo Road Hunan Province Changsha China School of Science and Engineering The Chinese University of Hong Kong-Shenzhen 2001 Longxiang Boulevard Longgang District Shenzhen China Institute of Robotics and Intelligent Systems Dalian University of Technolgy 2 Linggong Road Liaoning Province Dalian China Department of Computer Science University of Toronto 40 St George Street TorontoONM5S 2E4 Canada Center for Reproductive Medicine and Obstetrics and Gynecology Nanjing Drum Tower Hospital Nanjing University Medical School 321 Zhongshan Road Jiangsu Province Nanjing China National Engineering and Research Center of Human Stem Cell 8 Luyun Road Jiangsu Province Changsha China Department of Electrical and Computer Engineering 10 King’s College Road TorontoONM5S 3G8 Canada Institute of Biomedical Engineering University of Toronto 164 College Street TorontoONM5S 3G9 Canada

Background: Selecting the blastocyst with the highest potential for live birth from a cohort is crucial for the success of in vitro fertilization (IVF). While the Gardner and Schoolcraft morphological grading system, commonly known as the Gardner grading system, is widely used by embryologists worldwide, blastocysts having similar or the same inner cell mass (ICM) and trophectoderm (TE) grades cause challenges for embryologists in decision-making. Furthermore, human assessment is subjective and inconsistent in predicting which blastocysts have higher potential to result in live birth. This study aims to develop an interpretable, quantitative method aligned with the Gardner grading system, providing continuous scores that correlate with live birth outcomes, thereby assisting embryologists in improving blastocyst selection. Methods: In this retrospective study, we developed GardnerNet, an interpretable deep learning model that outputs expansion degree grade and continuous scores quantifying a blastocyst's ICM morphology and TE morphology, based on the Gardner grading system. The continuous ICM and TE scores were calculated by weighting each base grade's predicted probability and summing the predicted probabilities. To represent each blastocyst's overall potential for live birth, we combined the ICM and TE scores using their odds ratios (ORs) for live birth. We further assessed the correlation between the ICM score, TE score, and the OR-combined score (adjusted for expansion degree) with live birth rates by applying GardnerNet to blastocysts with known live birth outcomes. To test its generalizability, we also applied GardnerNet to an external IVF institution, accounting for variations in imaging conditions, live birth rates, and embryologists' experience levels. Findings: GardnerNet was developed using data from 2760 blastocysts with majority-voted grades for expansion degree, ICM, and TE. The model achieved mean area under the receiver operating characteristic curve

关键词： Risk assessment

Can Primal Methods Outperform Primal-dual Methods in Decentralized Dynamic Optimization?

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yuan, Kun Xu, Wei Ling, Qing Department of Electrical and Computer Engineering University of California Los Angeles Department of Automation University of Science and Technology of China. School of Data and Computer Science Guangdong Province Key Laboratory of Computational Science Sun Yat-Sen University NSF China Grants Fundamental Research Funds Central Universities Asilomar Conference on Signals Systems and Computers Pacific Grove61573331 and 61973324 United States

In this paper, we consider the decentralized dynamic optimization problem defined over a multi-agent network. Each agent possesses a time-varying local objective function, and all agents aim to collaboratively track the drifting global optimal solution that minimizes the summation of all local objective functions. The decentralized dynamic optimization problem can be solved by primal or primal-dual methods, and when the problem degenerates to be static, it has been proved in literature that primal-dual methods are superior to primal ones. This motivates us to ask: are primal-dual methods necessarily better than primal ones in decentralized dynamic optimization? To answer this question, we investigate and compare convergence properties of the primal method, diffusion, and the primal-dual approach, decentralized gradient tracking (DGT). Theoretical analysis reveals that diffusion can outperform DGT in certain dynamic settings. We find that DGT and diffusion are significantly affected by the drifts and the magnitudes of optimal gradients, respectively. In addition, we show that DGT is more sensitive to the network topology, and a badly-connected network can greatly deteriorate its convergence performance. These conclusions provide guidelines on how to choose proper dynamic algorithms in various application scenarios. Numerical experiments are constructed to validate the theoretical analysis. Copyright © 2020, The Authors. All rights reserved.

关键词： Diffusion

Parallel Dispatch:A New Paradigm of electrical Power System Dispatch

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2018年第1期5卷 311-319页

作者： Jun Jason Zhang Fei-Yue Wang Qiang Wang Dazhi Hao Xiaojing Yang David Wenzhong Gao Xiangyang Zhao Yingchen Zhang Department of Electrical and Computer Engineering Ritchie School of Engineering and Computer Science University of Denver Denver 80210 CO USA State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Science (SKL-MCCS CASIA) Beijing 100190 China Research Center of Computational Experiments and Parallel Systems The National University of Defense Technology Changsha 410073 China State Grid Tianjin Electric Power Company Tianjin 300010 China School of Automation Science and Electrical Engineering Beihang University Beijing 100191 China National Renewable Energy Laboratory Golden CO 80401 USA IEEE

Modern power systems are evolving into sociotechnical systems with massive complexity, whose real-time operation and dispatch go beyond human capability. Thus,the need for developing and applying new intelligent power system dispatch tools are of great practical significance. In this paper, we introduce the overall business model of power system dispatch, the top level design approach of an intelligent dispatch system, and the parallel intelligent technology with its dispatch applications. We expect that a new dispatch paradigm,namely the parallel dispatch, can be established by incorporating various intelligent technologies, especially the parallel intelligent technology, to enable secure operation of complex power grids,extend system operators' capabilities, suggest optimal dispatch strategies, and to provide decision-making recommendations according to power system operational goals.

关键词： ACP knowledge automation power dispatch parallel dynamic programming parallel intelligence paralle learning situational awareness