检索结果-内蒙古大学图书馆

Sampling methods for efficient training of graph convolutional networks: A survey

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Xin Yan, Mingyu Deng, Lei Li, Guoqi Ye, Xiaochun Fan, Dongrui State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100086 China Department of Precision Instrument Center for Brain Inspired Computing Research Tsinghua University Beijing100084 China School of Computer Science and Technology University of Chinese Academy of Sciences

—Graph Convolutional Networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations. Although GCN performs well compared with other methods, it still faces challenges. Training a GCN model for large-scale graphs in a conventional way requires high computation and storage costs. Therefore, motivated by an urgent need in terms of efficiency and scalability in training GCN, sampling methods have been proposed and achieved a significant effect. In this paper, we categorize sampling methods based on the sampling mechanisms and provide a comprehensive survey of sampling methods for efficient training of GCN. To highlight the characteristics and differences of sampling methods, we present a detailed comparison within each category and further give an overall comparative analysis for the sampling methods in all categories. Finally, we discuss some challenges and future research directions of the sampling methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

Towards High-accuracy and Low-latency Spiking Neural Networks with Two-Stage Optimization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Ziming Zhang, Yuhao Lian, Shuang Cui, Xiaoxin Yan, Rui Tang, Huajin College of Computer Science and Technology Zhejiang University Hangzhou310027 China Research Center for Intelligent Computing Hardware Zhejiang Lab Hangzhou311100 China School of Integrated Circuits Peking University Beijing100871 China College of Computer Science Zhejiang University of Technology Hangzhou310014 China State Key Laboratory of Brain-Machine Intelligence Zhejiang University Hangzhou310027 China

Spiking neural networks (SNNs) operating with asynchronous discrete events show higher energy efficiency with sparse computation. A popular approach for implementing deep SNNs is ANN-SNN conversion combining both efficient training of ANNs and efficient inference of SNNs. However, the accuracy loss is usually non-negligible, especially under few time steps, which restricts the applications of SNN on latencysensitive edge devices greatly. In this paper, we first identify that such performance degradation stems from the misrepresentation of the negative or overflow residual membrane potential in SNNs. Inspired by this, we decompose the conversion error into three parts: quantization error, clipping error, and residual membrane potential representation error. With such insights, we propose a two-stage conversion algorithm to minimize those errors respectively. Besides, We show each stage achieves significant performance gains in a complementary manner. By evaluating on challenging datasets including CIFAR-10, CIFAR- 100 and ImageNet, the proposed method demonstrates the stateof- the-art performance in terms of accuracy, latency and energy preservation. Furthermore, our method is evaluated using a more challenging object detection task, revealing notable gains in regression performance under ultra-low latency when compared to existing spike-based detection algorithms. Codes are available at https://***/Windere/snn-cvt-dual-phase. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

The Combination of Two Control Strategies for Series Hybrid Electric Vehicles

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2019年第2期6卷 596-608页

作者： Can Luo Zhen Shen Simos Evangelou Gang Xiong Fei-Yue Wang State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Cloud Computing Center Chinese Academy of Sciences IEEE Department of Electrical and Electronic Engineering Imperial College London Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Qingdao Academy of Intelligent Industries

With most countries paying attention to the environment protection, hybrid electric vehicles have become a focus of automobile research and development due to the characteristics of energy saving and low emission. Power follower control strategy(PFCS) and DC-link voltage control strategy are two sorts of control strategies for series hybrid electric vehicles(HEVs). Combining those two control strategies is a new idea for control strategy of series hybrid electric vehicles. By tuning essential parameters which are the defined constants under DClink voltage control and under PFCS, the points of minimum mass of equivalent fuel consumption(EFC) corresponding to a series of variables are marked for worldwide harmonized light vehicles test procedure(WLTP). The fuel economy of series HEVs with the combination control schemes performs better compared with individual control scheme. The results show the effects of the combination control schemes for series HEVs driving in an urban environment.

关键词： DC-Link voltage control power follower control strategy series hybrid electric vehicles tuning

Bionic Soft Fingers with Hybrid Variable Stiffness Mechanisms for Multimode Grasping

学校读者我要写书评

暂无评论

Bionic Soft Fingers with Hybrid Variable Stiffness Mechanism...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Xiangbo Wang Tianran Zhang Hongze Yu Zhenwei Wen Lide Fang Huaping Liu Fuchun Sun Lixue Tang Bin Fang College of Quality and Technical Supervision Hebei University Baoding China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China School of Mechanical Engineering & Automation Beihang University Beijing China International School Beijing University of Posts and Telecommunications Beijing China Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Tsinghua University Beijing China School of Biomedical Engineering Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application Capital Medical University Beijing China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This paper presents a novel Bionic Soft Finger (BSF) that aims to overcome the limitations of conventional rigid manipulators in terms of adaptability and safety, as well as the challenges faced by soft hands regarding carrying capacity and stability. The BSF design uses a hybrid variable stiffness mechanism combining memory alloy actuators with particle jamming to achieve the desired bending angle and actuator stiffness. Our innovative approach utilizes a bionic finger design that incorporates a memory alloy skeleton and a water-cooled recirculation system, leading to a substantial reduction in the time required for each operation. Through the integration of particle jamming, we have enhanced the overall stiffness and performance of the manipulator, enabling load capacities of up to 3N per finger and more than twice the stiffness of a normal condition. Additionally, our design enables multimode grasping and incorporates a liquid metal strain sensor (METT) for real-time monitoring of finger bending angles. Comparative analyses demonstrate that our design exhibits superior stiffness and enables five-mode grasping in comparison to pneumatic actuators. We believe that bionic soft fingers present a promising solution for enhancing adaptability, safety, and performance in human-robot interaction applications.

关键词： Metals Grasping Bending Manipulators Stability analysis Skeleton Real-time systems

Dynamical causality under invisible confounders

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yan, Jinling Zhang, Shao-Wu Zhang, Chihao Huang, Weitian Shi, Jifan Chen, Luonan MOE Key Laboratory of Information Fusion Technology School of Automation Northwestern Polytechnical University Xi’an710072 China Key Laboratory of Systems Biology Shanghai Institute of Biochemistry and Cell Biology Center for Excellence in Molecular Cell Science Chinese Academy of Sciences Shanghai200031 China NCMIS CEMS RCSDS Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China School of Mathematics Sciences University of Chinese Academy of Sciences Beijing100049 China School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China Guangdong Institute of Intelligence Science and Technology Hengqin Guangdong Zhuhai519031 China Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China State Key Laboratory of Medical Neurobiology MOE Frontiers Center for Brain Science Institutes of Brain Science Fudan University Shanghai200032 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Key Laboratory of Systems Health Science of Zhejiang Province School of Life Science Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Chinese Academy of Sciences Hangzhou310024 China

Causality inference is prone to spurious causal interactions, due to the substantial confounders in a complex system. While many existing methods based on the statistical methods or dynamical methods attempt to address misidentification challenges, there remains a notable lack of effective methods to infer causality, in particular in the presence of invisible/unobservable confounders. As a result, accurately inferring causation with invisible confounders remains a largely unexplored and outstanding issue in data science and AI fields. In this work, we propose a method to overcome such challenges to infer dynamical causality under invisible confounders (CIC method) and further reconstruct the invisible confounders from time-series data by developing an orthogonal decomposition theorem in a delay embedding space. The core of our CIC method lies in its ability to decompose the observed variables not in their original space but in their delay embedding space into the common and private subspaces respectively, thereby quantifying causality between those variables both theoretically and computationally. This theoretical foundation ensures the causal detection for any high-dimensional system even with only two observed variables under many invisible confounders, which is actually a long-standing problem in the field. In addition to the invisible confounder problem, such a decomposition actually makes the intertwined variables separable in the embedding space, thus also solving the non-separability problem of causal inference. Extensive validation of the CIC method is carried out using various real datasets, and the experimental results demonstrates its effectiveness to reconstruct real biological networks even with unobserved confounders. © 2024, CC BY-NC-ND.

关键词： Time series

Adaptive model predictive control of mobile robot with local path refitting

学校读者我要写书评

暂无评论

Adaptive model predictive control of mobile robot with local...

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Liquan Jiang Yuanlong Xie Zhihui Jiang Jie Meng Wenbin Li State Key Laboratory of New Textile Materials and Advanced Processing Technologies Wuhan Textile University Wuhan China School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan China School of Computer Science Yangtze University Jingzhou China Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan China

ISBN: (纸本)9781665409858

Path planning and tracking control are important modules of mobile robots, which have outstanding advantages in improving the flexibility of mobile robots. However, in the existing applications, these two modules are usually processed separately, which makes the obstacle avoidance process of the mobile robot uncontrollable and reduces the adaptability of the application scenario. In order to realize collision-free high-precision trajectory tracking control of mobile robots in dynamic scenes, this paper proposes an adaptive MPC control method based on curvature constraints, which can improve the safety of operation and reduce the chattering caused by unreasonable paths in the process of operation. Firstly, according to the kinematic constraints of general mobile robots, the constraint model of mobile robot path planning is constructed. At the same time, the adaptive parameter adjustment rules are adopted to realize the balance between the calculation efficiency and the control cycle. Finally, a smooth safe path is obtained by re-fitting the planned path and reprocessing the nodes with excessive curvature. Compared with traditional methods, the proposed method has better advantages.

关键词： Industrial electronics Electric potential Trajectory tracking Kinematics Safety Planning Mobile robots

Cross-Domain Dual-Functional OFDM Waveform Design for Accurate Sensing/Positioning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Fan Mao, Tianqi Liu, Ruiqi Han, Zhu Chen, Sheng Wang, Zhaocheng Beijing National Research Center for Information Science and Technology Department of Electronic Engineering Tsinghua University Beijing100084 China Tsinghua Shenzhen International Graduate School Shenzhen518055 China The State Key Laboratory of CNS/ATM Beijing Institute of Technology Beijing100081 China The MIIT Key Laboratory of Complex-field Intelligent Sensing Beijing Institute of Technology Beijing100081 China The Wireless and Computing Research Institute ZTE Corporation Beijing100029 China The State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen518055 China The Department of Electrical and Computer Engineering University of Houston HoustonTX77004 United States The Department of Computer Science and Engineering Kyung Hee University Seoul446-701 Korea Republic of The School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom

Orthogonal frequency division multiplexing (OFDM) has been widely recognized as the representative waveform for 5G wireless networks, which can directly support sensing/positioning with existing infrastructure. To guarantee superior sensing/positioning accuracy while supporting high-speed communications simultaneously, the dual functions tend to be assigned with different resource elements (REs) due to their diverse design requirements. This motivates optimization of resource allocation/waveform design across time, frequency, power and delay-Doppler domains. Therefore, this article proposes two cross-domain waveform optimization strategies for effective convergence of OFDM-based communications and sensing/positioning, following communication- and sensing-centric criteria, respectively. For the communication-centric design, to maximize the achievable data rate, a fraction of REs are optimally allocated for communications according to prior knowledge of the communication channel. The remaining REs are then employed for sensing/positioning, where the sidelobe level and peak-to-average power ratio are suppressed by optimizing its power-frequency and phase-frequency characteristics for sensing performance improvement. For the sensing-centric design, a 'locally' perfect auto-correlation property is ensured for accurate sensing and positioning by adjusting the unit cells of the ambiguity function within its region of interest (RoI). Afterwards, the irrelevant cells beyond RoI, which can readily determine the sensing power allocation, are optimized with the communication power allocation to enhance the achievable data rate. Numerical results demonstrate the superiority of the proposed waveform designs. Copyright © 2023, The Authors. All rights reserved.

关键词： Orthogonal frequency division multiplexing

Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Xinzhu Guo, Di Liu, Huaping Sun, Fuchun Department of Computer Science and Technology Tsinghua University Beijing100084 China State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

— In visual semantic navigation, the robot navigates to a target object with egocentric visual observations and the class label of the target is given. It is a meaningful task inspiring a surge of relevant research. However, most of the existing models are only effective for single-agent navigation, and a single agent has low efficiency and poor fault tolerance when completing more complicated tasks. Multi-agent collaboration can improve the efficiency and has strong application potentials. In this paper, we propose the multi-agent visual semantic navigation, in which multiple agents collaborate with others to find multiple target objects. It is a challenging task that requires agents to learn reasonable collaboration strategies to perform efficient exploration under the restrictions of communication bandwidth. We develop a hierarchical decision framework based on semantic mapping, scene prior knowledge, and communication mechanism to solve this task. The results of testing experiments in unseen scenes with both known objects and unknown objects illustrate the higher accuracy and efficiency of the proposed model compared with the single-agent model. Copyright © 2021, The Authors. All rights reserved.

关键词： Navigation

Deep Learning-Based Object Pose Estimation: A Comprehensive Survey

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Jian Sun, Wei Yang, Hui Zeng, Zhiwen Liu, Chongpei Zheng, Jin Liu, Xingyu Rahmani, Hossein Sebe, Nicu Mian, Ajmal The National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering the State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China The School of Architecture and Art Central South University Changsha410082 China The Department of Automation Tsinghua University Beijing100084 China The School of Computing and Communications Lancaster University LA1 4YW United Kingdom The Department of Information Engineering and Computer Science University of Trento Trento38123 Italy The Department of Computer Science The University of Western Australia WA6009 Australia

Object pose estimation is a fundamental computer vision problem with broad applications in augmented reality and robotics. Over the past decade, deep learning models, due to their superior accuracy and robustness, have increasingly supplanted conventional algorithms reliant on engineered point pair features. Nevertheless, several challenges persist in contemporary methods, including their dependency on labeled training data, model compactness, robustness under challenging conditions, and their ability to generalize to novel unseen objects. A recent survey discussing the progress made on different aspects of this area, outstanding challenges, and promising future directions, is missing. To fill this gap, we discuss the recent advances in deep learning-based object pose estimation, covering all three formulations of the problem, i.e., instance-level, category-level, and unseen object pose estimation. Our survey also covers multiple input data modalities, degrees-of-freedom of output poses, object properties, and downstream tasks, providing the readers with a holistic understanding of this field. Additionally, it discusses training paradigms of different domains, inference modes, application areas, evaluation metrics, and benchmark datasets, as well as reports the performance of current state-of-the-art methods on these benchmarks, thereby facilitating the readers in selecting the most suitable method for their application. Finally, the survey identifies key challenges, reviews the prevailing trends along with their pros and cons, and identifies promising directions for future research. We also keep tracing the latest works at Awesome-Object-Pose-Estimation. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking