检索结果-内蒙古大学图书馆

High-precision Calibration of Camera and IMU on Manipulator for Bio-inspired Robotic System

Journal of Bionic engineering 2022年第2期19卷 299-313页

作者： Yinlong Zhang Wei Liang Sichao Zhang Xudong Yuan Xiaofang Xia Jindong Tan Zhibo Pang State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China Key Laboratory of Networked Control Systems Chinese Academy of SciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China The School of Computer Science and Technology Xidian UniversityXi’an 710071China Department of Mechanical Aerospace and Biomedical EngineeringUniversity of TennesseeKonxville 37996USA Department of Automation Technology ABB Corporate Research Sweden72178 VästerasSweden

Inspired by box jellyfish that has distributed and complementary perceptive system,we seek to equip manipulator with a camera and an Inertial Measurement Unit(IMU)to perceive ego motion and surrounding unstructured *** robot perception,a reliable and high-precision calibration between camera,IMU and manipulator is a critical *** paper introduces a novel calibration ***,we seek to correlate the spatial relationship between the sensing units and manipulator in a joint ***,the manipulator moving trajectory is elaborately designed in a spiral pattern that enables full excitations on yaw-pitch-roll rotations and x-y-z translations in a repeatable and consistent *** calibration has been evaluated on our collected visual inertial-manipulator *** systematic comparisons and analysis indicate the consistency,precision and effectiveness of our proposed calibration method.

关键词： Bio-inspired robotic system Monocular camera IMU Manipulator Calibration

来源：评论

学校读者我要写书评

暂无评论

A Multi-Agent Path Planning Strategy with Reconfigurable Topology in Unknown Environments

A Multi-Agent Path Planning Strategy with Reconfigurable Top...

引用

IEEE International Conference on automation Science and engineering (CASE)

作者： Hao Sun Junyan Hu Li Dai Boli Chen Department of Electronic and Electrical Engineering University College London UK Department of Computer Science Durham University UK School of Automation Beijing Institute of Technology Beijing China

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Safety-guaranteed trajectories are important for multi-agent systems to work in an unknown constrained environment. To address this issue, this paper proposes a cooperative path planning strategy for a swarm of agents such that they can achieve a target formation and handle unknown obstacles during complex tasks. By considering the sensing range and agent dimension, a group of artificial potential field functions are designed aiming at enabling agents reconfiguration (e.g., split and merge) for reinforced flexibility. A distributed path planning scheme is then developed to achieve formation tracking while avoiding any potential collisions. Theoretical analysis using the Lyapunov theory is given to guarantee the performance of the system. Finally, numerical simulations are carried out to verify the effectiveness of the proposed algorithm and its superiority against conventional methods.

关键词： Target tracking computer aided software engineering automation Numerical simulation Trajectory Topology Sensors Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning

Fine-grained Category Discovery under Coarse-grained supervi...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： An, Wenbin Tian, Feng Chen, Ping Tang, Siliang Zheng, Qinghua Wang, QianYing School of Automation Science and Engineering Xi'an Jiaotong University China School of Computer Science and Technology MOEKLNNS Lab Xi'an Jiaotong University China Department of Engineering University of Massachusetts Boston United States College of Computer Science and Technology Zhejiang University China Lenovo Research

Novel category discovery aims at adapting models trained on known categories to novel categories. Previous works only focus on the scenario where known and novel categories are of the same granularity. In this paper, we investigate a new practical scenario called Fine-grained Category Discovery under Coarse-grained supervision (FCDC). FCDC aims at discovering fine-grained categories with only coarse-grained labeled data, which can adapt models to categories of different granularity from known ones and reduce significant labeling cost. It is also a challenging task since supervised training on coarse-grained categories tends to focus on inter-class distance (distance between coarse-grained classes) but ignore intra-class distance (distance between fine-grained sub-classes) which is essential for separating fine-grained categories. Considering most current methods cannot transfer knowledge from coarse-grained level to fine-grained level, we propose a hierarchical weighted self-contrastive network by building a novel weighted self-contrastive module and combining it with supervised learning in a hierarchical manner. Extensive experiments on public datasets show both effectiveness and efficiency of our model over compared methods. Code and data are available at https://***/Lackel/Hierarchical_Weighted_SCL. © 2022 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

GSLB: The Graph Structure Learning Benchmark 37

GSLB: The Graph Structure Learning Benchmark

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Li, Zhixun Wang, Liang Sun, Xin Luo, Yifan Zhu, Yanqiao Chen, Dingshuo Luo, Yingtao Zhou, Xiangxin Liu, Qiang Wu, Shu Yu, Jeffrey Xu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Department of Automation University of Science and Technology of China China School of Cyberspace Security Beijing University of Posts and Telecommunications China Department of Computer Science University of California Los Angeles United States Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University United States

ISBN: (纸本)9781713899921

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

An Insight Into Communication Technologies Utilized in Smart Metering Systems

An Insight Into Communication Technologies Utilized in Smart...

引用

Proceedings of the International Convention MIPRO

作者： David Bač nar Lolita Leytner Nino Stojković Jonatan Lerga Department of Computer Engineering Faculty of Engineering University of Rijeka Rijeka Croatia Automation and Computer Engineering Department Polytech Angers University of Angers Angers France Department of Automation and Electronics Faculty of Engineering University of Rijeka Rijeka Croatia

ISBN: (数字)9789532331035

ISBN: (纸本)9781665484343

This paper presents an insight into the smart metering field. The paper address specifics of different network hierarchy structures (wide area networks, neighborhood area networks, and home area networks) and topologies used for this purpose (mesh, point-to-point, virtual point-to-point, or broadcast networks). Next, we focus on listing and describing some of the most commonly used communication technologies (both wired and wireless, such as power line communication, public switched telephone network, digital subscriber line, radiofrequency, in-home radio frequency, wireless local area network, or mobile network communications), their characteristics, advantages, and disadvantages utilized for remote and smart metering.

关键词： Wireless communication Wide area networks Radio frequency Wireless LAN Network topology Power line communications Topology

来源：评论

学校读者我要写书评

暂无评论

Truth Table Based Intelligent Computing

Truth Table Based Intelligent Computing

引用

International Conference on Mixed Design of Integrated Circuits and Systems (MIXDES)

作者： Vladimir Hahanov Eugenia Litvinova Zaza Davitadze Svetlana Chumachenko David Devadze Abdullayev Vugar Hacimahmud Design Automation Department Kharkov National University of Radioelectronics Kharkov Ukraine Department of Computer Sciences Batumi Shota Rustaveli State University Batumi Georgia Computer Engineering Department Azerbaijan State Oil and Industry University Baku Azerbaijan

ISBN: (数字)9788363578268

ISBN: (纸本)9798350375701

Computing architectures for solving design and test problems and managing social processes based on monitoring and vector logical processing of big data as addresses are considered. A model of data structures in the form of a truth table is considered for solving combinatorial problems associated with technical diagnostics, monitoring, and control of cyber-physical and cyber-social space. The problem of transferring the von Neumann architecture into memory and replacing a powerful processor by read-write transactions on logical vectors to reduce energy and latency when simulation logical functionality of any dimension is considered. A truth table is proposed to describe the tested combinations of faults on the input lines. Representing functionality in the form of a structure of smaller elements reduces the memory for storing logical vectors by introducing connections between elements but complicates the simulation algorithm and increases the processing time of the logical circuit. Logic vector functionality from n-inputs has the advantage of simulating more input variables in parallel in a single clock cycle. If there are no memory restrictions, then representing the functionality as a single logical vector is more time efficient and simpler for the algorithm for in-memory simulation, as well as for executing functions in production. Therefore, the use of a logical vector instead of the structure of typical technological elements is a definite step towards smart data structures in-memory computing. If the speed of read-write transactions on memory approaches the performance of logic circuits in the processor, then the next step in the electronic technology market will be the transition from processor logic to vector logic in in-memory computing. Smart data structures for fault-free simulation are represented by a superposition of logical vectors of functionality included in the digital circuit. Examples are given of processing big data as truth table addresses for

关键词： Computational modeling Big Data Data structures In-memory computing Vectors Data models Logic

来源：评论

学校读者我要写书评

暂无评论

Dynamic Legged Ball Manipulation on Rugged Terrains with Hierarchical Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Zhu, Dongjie Yang, Zhuo Wu, Tianhang Ge, Luzhou Li, Xuesong Liu, Qi Li, Xiang Department of Automation Tsinghua University China School of Computer Science Beijing Institute of Technology China Faculty of Robot Science and Engineering Northeastern University United States

Advancing the dynamic loco-manipulation capabilities of quadruped robots in complex terrains is crucial for performing diverse tasks. Specifically, dynamic ball manipulation in rugged environments presents two key challenges. The first is coordinating distinct motion modalities to integrate terrain traversal and ball control seamlessly. The second is overcoming sparse rewards in end-to-end deep reinforcement learning, which impedes efficient policy convergence. To address these challenges, we propose a hierarchical reinforcement learning framework. A high-level policy, informed by proprioceptive data and ball position, adaptively switches between pretrained low-level skills such as ball dribbling and rough terrain navigation. We further propose Dynamic Skill-Focused Policy Optimization to suppress gradients from inactive skills and enhance critical skill learning. Both simulation and real-world experiments validate that our methods outperform baseline approaches in dynamic ball manipulation across rugged terrains, highlighting its effectiveness in challenging environments. Videos are on our website: ***. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Utilization of Distribution System Flexibility for Enhanced TSO-DSO Interoperability: A Novel Machine Learning-Based Optimal Power Flow Approach

arXiv

引用

arXiv 2025年

作者： Dindar, Burak Saner, Can Berk Çakmak, Hüseyin K. Hagenmeyer, Veit Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe76131 Germany Department of Electrical and Computer Engineering National University of Singapore Singapore117581 Singapore

Due to the transformation of the power system, the effective use of flexibility from the distribution system (DS) is becoming crucial for efficient network management. Leveraging this flexibility requires interoperability among stakeholders, including Transmission System Operators (TSOs) and Distribution System Operators (DSOs). However, data privacy concerns among stakeholders present significant challenges for utilizing this flexibility effectively. To address these challenges, we propose a machine learning (ML)-based method in which the technical constraints of the DSs are represented by ML models trained exclusively on non-sensitive data. Using these models, the TSO can solve the optimal power flow (OPF) problem and directly determine the dispatch of flexibility-providing units (FPUs)—in our case, distributed generators (DGs)-in a single round of communication. To achieve this, we introduce a novel neural network (NN) architecture specifically designed to efficiently represent the feasible region of the DSs, ensuring computational effectiveness. Furthermore, we incorporate various PQ charts rather than idealized ones, demonstrating that the proposed method is adaptable to a wide range of FPU characteristics. To assess the effectiveness of the proposed method, we benchmark it against the standard AC-OPF on multiple DSs with meshed connections and multiple points of common coupling (PCCs) with varying voltage magnitudes. The numerical results indicate that the proposed method achieves performant results while prioritizing data privacy. Additionally, since this method directly determines the dispatch of FPUs, it eliminates the need for an additional disaggregation step. By representing the DSs technical constraints through ML models trained exclusively on nonsensitive data, the transfer of sensitive information between stakeholders is prevented. Consequently, even if reverse engineering is applied to these ML models, no sensitive data can be extracted. This allows

关键词： Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Wide-Swing CMOS Multiplier for AC Source Signal Tracking and Modulation

引用

Circuits, Systems, and Signal Processing 2024年第9期43卷 5377-5400页

作者： Wang, Wei Xu, Sendren Sheng-Dong Chen, Chi-Lin Chiu, Huang-Jen Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei 106335 Taiwan Graduate Institute of Automation and Control National Taiwan University of Science and Technology Taipei 106335 Taiwan Advanced Manufacturing Research Center National Taiwan University of Science and Technology Taipei 106335 Taiwan Himax Technologies Inc. Taipei 100507 Taiwan

The multiplier is a pervasive critical component today. However, most of them are difficult to be integrated into an integrated circuit. In this study, we proposed a novel analog multiplier for AC power application, using CMOS process to realize the analog voltage multiplication function of double-ended input and single-ended output. Under the working voltage of 3.3 V, the multiplier can operate with a wide input voltage range of 0–1.6 V (about 48.8% of the working voltage) and a wide output voltage range of 0–2.56 V (about 77.5% of the working voltage). The multiplier is implemented through the current difference between two NMOSs operating in the linear region and the saturation region, respectively. Compared with the existing technique, the proposed analog multiplier has a wider input and output range, and better linearity. It is suitable for AC power signal tracking and modulation. Finally, the United Microelectronics Corporation 0.18 μm 1P4M CMOS standard process was used for physical implementation. Moreover, there is not any BJT or special device used. It was measured that the analog multiplier circuit consumes about 0.56 mW at a working voltage of 3.3 V. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： AC power signal modulation AC source signal tracking Analog integrated circuit (IC) design Analog multipliers Circuits and systems

来源：评论

学校读者我要写书评

暂无评论

Adaptability of collision warning for motor vehicle drivers: Can consciousness recognition improve the warning accuracy?

Advances in Transportation Studies

引用

Advances in Transportation Studies 2021年第Special issue 2期2021卷 3-14页

作者： Zhang, T. Wang, H. Patnaik, S. College of Mechanical Engineering and Automation Northeastern University Shenyang110819 China College of Applied Technology Shenyang University Shenyang110044 China Department of Computer Science and Engineering SOA University Bhubaneswar751030 India

Aiming at the problems of poor risk identification ability and high false alarm rate in current vehicle collision warning technology, the self-adaptability of vehicle driver collision warning is proposed: Can consciousness recognition improve the warning accuracy? Construct an adaptive collision warning model, and quantify the impact of each vehicle's collision with an adaptive weight distribution method. The collision speed, the collision safety factor and the lateral offset related to the collision process are used as the weight distribution index to calibrate the model parameters. The maximum similarity recursive algorithm is used to estimate the characteristics of the current vehicle driving state. The maximum braking deceleration threshold is used to determine the degree of collision risk between the own vehicle and the following vehicle. The collision risk levels of the two workshops are divided into three levels: Safety, critical value, and danger. The signal detection principle is adopted to modularize the initial information of the collision warning system, and the driving state assessment threshold adaptation category of the collision warning system is alarmed according to the actual situation. Experiments have verified that when the vehicle collision risk level is the critical value, the DR value of the model in this paper is 0.06 larger than the value of the NCM model, and it takes 3s-6s more time for the driver to take anti-collision and obstacle avoidance measures. Compared with the area under the ROC curve of the NCM model, the local algorithm has high warning accuracy and low false alarm rate. © 2021, Aracne Editrice. All rights reserved.

关键词： Collision avoidance

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：