检索结果-内蒙古大学图书馆

16th International Conference on Social Robotics, ICSR + InnoBiz 2024

作者： Xu, Yue Zhang, Yinlong Liu, Shuai Liu, Yuanhao Liang, Wei He, Hongsheng Shenyang University of Technology Shenyang110020 China Guangzhou Institute of Industrial Intelligence Guangzhou511458 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Department of Computer Science The University of Alabama TuscaloosaAL35487 United States

ISBN: (纸本)9789819611508

Accurately tracking the robotic arm and human joints is crucial to ensure safety during human-robot interaction. However, traditional pose tracking methods often exhibit insufficient performance and robustness in complex environments. The variations in the robotic arm’s environment and posture make it challenging for traditional methods to accurately capture the positions and posture of its joints. Specifically, when addressing challenges such as high similarity, occlusion, background complexity, and joint recognition failures, they often struggle to provide reliable and accurate results. To address these challenges, this paper proposes a human-robot pose tracking algorithm based on a new convolutional neural network model. To enhance detection accuracy, an improved color detection module is introduced to resolve joint misclassification. A geometric perception module is designed to accurately locate joints even under occlusion. Additionally, innovative iEMA and DBB modules are incorporated. The iEMA module employs edge detection technology to dynamically adjust thresholds for correct matching by improving the edge matching process. The DBB module refines the boundary box parameters for precise localization by introducing adaptive bounding box updates in real-time. This algorithm also integrates human pose recognition, enabling real-time pose recognition, thereby facilitating more intelligent and natural human-robot interaction. The algorithm has been rigorously evaluated on a custom-designed robotic arm platform. Experimental results validate the algorithm’s effectiveness and feasibility. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Symbiotic control of Uncertain Dynamical systems: Harnessing Synergy Between Fixed-Gain control and Adaptive Learning Architectures

引用

IEEE Transactions on Automatic control 2025年

作者： Yucelen, Tansel Sarsilmaz, Selahattin Burak Yildirim, Emre University of South Florida Department of Mechanical Engineering Laboratory for Autonomy Control Information and Systems TampaFL33620 United States Utah State University Department of Electrical and Computer Engineering LoganUT84322 United States

Both fixed-gain control and adaptive learning architectures aim to mitigate the effects of uncertainties. In particular, fixed-gain control offers more predictable closed-loop system behavior but requires the knowledge of uncertainty bounds. In contrast, while adaptive learning does not necessarily require such knowledge, it often results in less predictable closed-loop system behavior compared to fixed-gain control. To this end, this paper presents a novel symbiotic control framework that offers the strengths of fixed-gain control and adaptive learning architectures. Specifically, this framework synergistically integrates these architectures to mitigate the effects of uncertainties in a more predictable manner as compared to adaptive learning alone and it does not require any knowledge on such uncertainties. Both parametric and nonparametric uncertainties are considered, where we utilize neural networks to approximate the unknown uncertainty basis for the latter case. Counterintuitively, the proposed framework has the ability to achieve a desired level of closed-loop system behavior even with an insufficient number of neurons (e.g., when the neural network approximation error is large) or in the face of injudiciously selected adaptive learning parameters (e.g., high leakage term parameters). © 1963-2012 IEEE.

关键词： Closed loop control systems

来源：评论

学校读者我要写书评

暂无评论

Physics-Informed Learning Using Hamiltonian Neural Networks with Output Error Noise Models

arXiv

引用

arXiv 2023年

作者： Moradi, Sarvin Jaensson, Nick Tóth, Roland Schoukens, Maarten Control System group Eindhoven University of Technology Eindhoven Netherlands Eindhoven Artificial Intelligence Systems Institute Eindhoven Netherlands Processing and Performance of Materials Group Eindhoven University of Technology Eindhoven Netherlands Systems and Control Laboratory Institute for Computer Science and Control Budapest Hungary

In order to make data-driven models of physical systems interpretable and reliable, it is essential to include prior physical knowledge in the modeling framework. Hamiltonian Neural Networks (HNNs) implement Hamiltonian theory in deep learning and form a comprehensive framework for modeling autonomous energy-conservative systems. Despite being suitable to estimate a wide range of physical system behavior from data, classical HNNs are restricted to systems without inputs and require noiseless state measurements and information on the derivative of the state to be available. To address these challenges, this paper introduces an Output Error Hamiltonian Neural Network (OE-HNN) modeling approach to address the modeling of physical systems with inputs and noisy state measurements. Furthermore, it does not require the state derivatives to be known. Instead, the OE-HNN utilizes an ODE-solver embedded in the training process, which enables the OE-HNN to learn the dynamics from noisy state measurements. In addition, extending HNNs based on the generalized Hamiltonian theory enables to include external inputs into the framework which are important for engineering applications. We demonstrate via simulation examples that the proposed OE-HNNs results in superior modeling performance compared to classical HNNs. © 2023, CC BY-NC-SA.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

Consistent and Asymptotically Statistically-Efficient Solution to Camera Motion Estimation

arXiv

引用

arXiv 2024年

作者： Zeng, Guangyang Zeng, Qingcheng Li, Xinghan Mu, Biqiang Chen, Jiming Shi, Ling Wu, Junfeng The School of Data Science Chinese University of Hong Kong Shenzhen Shenzhen518172 China The College of Control Science and Engineering The State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China Key Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community. The existing works generally set out from the epipolar constraint and estimate the essential matrix, which is not optimal in the maximum likelihood (ML) sense. In this paper, we dive into the original measurement model with respect to the rotation matrix and normalized translation vector and formulate the ML problem. We then propose a two-step algorithm to solve it: In the first step, we estimate the variance of measurement noises and devise a consistent estimator based on bias elimination;In the second step, we execute a one-step Gauss-Newton iteration on manifold to refine the consistent estimate. We prove that the proposed estimate owns the same asymptotic statistical properties as the ML estimate: The first is consistency, i.e., the estimate converges to the ground truth as the point number increases;The second is asymptotic efficiency, i.e., the mean squared error of the estimate converges to the theoretical lower bound - Cramer-Rao bound. In addition, we show that our algorithm has linear time complexity. These appealing characteristics endow our estimator with a great advantage in the case of dense point correspondences. Experiments on both synthetic data and real images demonstrate that when the point number reaches the order of hundreds, our estimator outperforms the state-of-the-art ones in terms of estimation accuracy and CPU time. Copyright © 2024, The Authors. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Multi-scale discriminative regions attention network for fine-grained vehicle classification

Journal of Network Intelligence

引用

Journal of Network Intelligence 2021年第2期6卷 164-177页

作者： Rong, Wen-Zhong Han, Jin Cai, Ying-Hao Liu, Gen College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Fine-grained vehicle classification is a challenging task in computer vision due to the low intra-class variance. Some methods have been developed to improve the accuracy of fine-grained vehicle classification by improving the ability of discriminative features extraction, but there is still room for further improvement in the localization accuracy of vehicle discriminative regions. Based on deep convolutional neural networks, we focus on finding a more efficient structure that pays more attention to the discriminative image regions to enhance the ability of fine-grained vehicle classification. We propose a novel Multi-Scale Discriminative Regions Attention Network (MS-DRAN), which extracts feature maps through ResNet-50 backbone network and generates multi-scale feature maps by a Feature Pyramid Network (FPN). Then, MS-DRAN generates discriminative regions attention maps on the multi-scale feature maps. The attention maps from shallow layer perform pixel-level multiplication with the feature maps from deeper layer. By this way, the network gradually extracts a more discriminating feature maps for classification. We also design a multi-task loss function to associate the classification results for each scale and optimize the network parameter in training. Lastly, we validate the MS-DRAN on Stanford Cars-196 dataset and CompCars dataset and achieves 94.3% and 98.1% in accuracy, respectively. ©2021 ISSN 2414-8105 (Online).

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Optimizing Foundation Model Inference on a Many-Tiny-Core Open-Source RISC-V Platform

IEEE Transactions on Circuits and Systems for Artificial Int...

引用

IEEE Transactions on Circuits and systems for Artificial Intelligence 2024年第1期1卷 37-52页

作者： Viviane Potocnik Luca Colagrande Tim Fischer Luca Bertaccini Daniele Jahier Pagliari Alessio Burrello Luca Benini Integrated Systems Laboratory (IIS) of ETH Zürich ETZ Züurich Switzerland Department of Control and Computer Engineering Politecnico di Torino Turin Italy Department of Electrical Electronic and Information Engineering University of Bologna Bologna Italy

Transformer-based foundation models have become crucial for various domains, most notably natural language processing (NLP) or computer vision (CV). These models are predominantly deployed on high-performance GPUs or hardwired accelerators with highly customized, proprietary instruction sets. Until now, limited attention has been given to RISC-V-based general-purpose platforms. In our work, we present the first inference results of transformer models on an open-source many-tiny-core RISC-V platform implementing distributed Softmax primitives and leveraging ISA extensions for SIMD floating-point operand streaming and instruction repetition, as well as specialized DMA engines to minimize costly main memory accesses and to tolerate their latency. We focus on two foundational transformer topologies, encoder-only and decoder-only models. For encoder-only models, we demonstrate a speedup of up to 12.8 $\times$ between the most optimized implementation and the baseline version. We reach over 79% FPU utilization and 294 GFLOPS/W, outperforming State-of-the-Art (SoA) accelerators by more than 2 $\times$ utilizing the HW platform while achieving comparable throughput per computational unit. For decoder-only topologies, we achieve 16.1 $\times$ speedup in the Non-Autoregressive (NAR) mode and up to 35.6 $\times$ speedup in the Autoregressive (AR) mode compared to the baseline implementation. Compared to the best SoA dedicated accelerator, we achieve 2.04 $\times$ higher FPU utilization.

关键词： Frequency modulation Transformers computer architecture Computational modeling Kernel Artificial intelligence Hardware

来源：评论

学校读者我要写书评

暂无评论

Sequential fusion estimation for multisensor systems with non-Gaussian noises

引用

Science China(Information Sciences) 2020年第12期63卷 153-165页

作者： Liping YAN Chenying DI Q.M.Jonathan WU Yuanqing XIA Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of Technology Department of Electrical and Computer Engineering University of Windsor

The sequential fusion estimation for multisensor systems disturbed by non-Gaussian but heavytailed noises is studied in this paper. Based on multivariate t-distribution and the approximate t-filter,the sequential fusion algorithm is presented. The performance of the proposed algorithm is analyzed and compared with the t-filter-based centralized batch fusion and the Gaussian Kalman filter-based optimal centralized fusion. Theoretical analysis and exhaustive experimental analysis show that the proposed algorithm is effective. As the generalization of the classical Gaussian Kalman filter-based optimal sequential fusion algorithm, the presented algorithm is shown to be superior to the Gaussian Kalman filter-based optimal centralized batch fusion and the optimal sequential fusion in estimation of dynamic systems with non-Gaussian noises.

关键词： state estimation sequential fusion non-Gaussian disturbance heavy-tailed noise multivariate t-distribution

来源：评论

学校读者我要写书评

暂无评论

ActMAD: Activation Matching to Align Distributions for Test-Time-Training

ActMAD: Activation Matching to Align Distributions for Test-...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： M. Jehanzeb Mirza Pol Jané Soneira Wei Lin Mateusz Kozinski Horst Possegger Horst Bischof Institute for Computer Graphics and Vision TU Graz Austria Christian Doppler Laboratory for Embedded Machine Learning Institute of Control Systems KIT Germany Christian Doppler Laboratory for Semantic 3D Computer Vision

Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by adapting a trained model to distribution shifts occurring at test-time. We propose to perform this adaptation via Activation Matching (ActMAD): We analyze activations of the model and align activation statistics of the OOD test data to those of the training data. In contrast to existing methods, which model the distribution of entire channels in the ultimate layer of the feature extractor, we model the distribution of each feature in multiple layers across the network. This results in a more fine-grained supervision and makes ActMAD attain state of the art performance on CIFAR-100C and Imagenet-C. ActMAD is also architecture-and task-agnostic, which lets us go beyond image classification, and score 15.4% improvement over previous approaches when evaluating a KITTI-trained object detector on KITTI-Fog. Our experiments highlight that ActMAD can be applied to online adaptation in realistic scenarios, requiring little data to attain its full performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effect of Ignition Voltage Amplitude on Breakdown Delay Time of Ring Laser Discharge Gap

Effect of Ignition Voltage Amplitude on Breakdown Delay Time...

引用

International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE)

作者： Anton O. Sinelnikov Ilya A. Smetanin Bogdan A. Basov Egor A. Smetanin Uliana F. Bykanova Computer science and control systems department Laboratory of Technologies of Polymer Ferroelectrics Laboratory of Microelectronics and Nanotechnology Mechanical engineering technologies department Bauman Moscow State Technical University Moscow Russian Federation Department of Nanotechnology and Microsystems Engineering Department of Mechanics and Control Processes RUDN University Moscow Russian Federation

ISBN: (数字)9798331531836

ISBN: (纸本)9798331531843

The modern space industry requires autonomous and high-precision control systems for scientific and commercial missions. Strapdown inertial navigation systems based on laser gyroscopes play a key role in spacecraft control, especially in environments where satellite navigation is unavailable. In this paper, ring lasers with an active medium made of a helium-neon mixture, their design and operating modes are investigated. The influence of voltage on the ignition electrodes (4.2-5 kV) on the breakdown time of the active medium has been analyzed. It was found that increasing the voltage reduces the breakdown time, providing reliable activation of gyroscopes. The experimental results allowed to determine the optimal ignition parameters that increase operation reliability and reduce production losses. This contributes to the development of highly efficient spacecraft control systems, opening up new prospects for deep space exploration and control of satellite systems.

关键词： Space vehicles Breakdown voltage Electric breakdown Power lasers Ignition Ring lasers Laser modes control systems Gyroscopes Reliability

来源：评论

学校读者我要写书评

暂无评论

Analysis and control of Gene Regulation Network Models Using Kinetic Semi-Discretization

Analysis and Control of Gene Regulation Network Models Using...

引用

European control Conference (ECC)

作者： Mihály A. Vághy Irene Otero-Muras Gábor Szederkenyi Faculty of Information Technology and Bionics Pazmany Peter Catholic University Budapest Hungary Spanish Council for Scientific Research Carrer del Catedratic Agustin Escardino Benlloch Institute for Integrative Systems Biology Valencia Spain Systems and Control Laboratory ELKH Institute for Computer Science and Control (SZTAKI) Budapest

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

In this paper the exogenous control of gene reg-ulatory networks is investigated through the semi-discretized partial integro-differential equation (PIDE) describing the time-evolution of the network's probability density function. With an appropriate finite volume method the semi-discretized system is a mass-conservative linear compartmental model, and thus it preserves most qualitative properties of the solution of the PIDE, namely, it is nonnegative and mass conservative. These advantages combined with the newly investigated mesh-invariance of control allows us to efficiently determine the reachability set. The possibilities of this framework are demon-strated through an illustrative example from literature.

关键词： Solid modeling Analytical models Computational modeling Volume measurement Sociology Switches Mathematical models

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：