检索结果-内蒙古大学图书馆

Chinese automation Congress (CAC)

作者： Yinke Dou Gaochen Fan Liwei Kou Yu Zhang Shanxi Energy Internet Research Institute Taiyuan China College of Electrical and Power Engineering Taiyuan University of Technology Taiyuan China Department of Automation Taiyuan Institute of Technology Taiyuan China

In the realm of polar research and scientific expeditions, traditional ice-based buoys have long been employed for in-situ observations, yet their effectiveness is limited, particularly when it comes to comprehensive coverage of vast polar areas. Recognizing this challenge and capitalizing on the advantages offered by unmanned aerial vehicles (UAVs) for large-scale monitoring, we introduce the UAV-Buoy Cooperative Monitoring System (UBCMS). This innovative polar observation system integrates UAV technology with ice-based buoys, significantly enhancing in-situ monitoring of sea-ice-air physical parameters while facilitating extensive area surveillance. Through two field tests, we validate the UBCMS's efficiency, positioning it as a highly promising solution for long-term, large-scale, and three-dimensional environmental monitoring in polar regions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Multi-agent Navigation with Lightweight DRL Policy

arXiv

引用

arXiv 2024年

作者： Diao, Xingrong Wang, Jiankun Shenzhen Key Laboratory of Robotics Perception and Intelligence Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China Jiaxing Research Institute Southern University of Science and Technology Jiaxing314000 China

This article presents an end-to-end collision avoidance policy based on deep reinforcement learning (DRL) for multi-agent systems, demonstrating encouraging outcomes in real-world applications. In particular, our policy calculates the control commands of the agent based on the raw LiDAR observations. In addition, the number of parameters of the proposed basic model is 140,000, and the size of the parameter file is 3.5 MB, which allows the robot to calculate the actions from the CPU alone. We propose a multi-agent training platform based on a physics-enhanced simulator to further bridge the gap between simulation and the real world. The policy is trained on a policy-gradients-based RL algorithm in a dense and messy training environment. A novel reward function is introduced to address the issue of agents choosing suboptimal actions in some common scenarios. Although the data used for training is exclusively from the simulation platform, the policy can be successfully transferred and deployed in real-world robots. Finally, our policy effectively responds to intentional obstructions and avoids collisions. The website is aviliable in https://***/view/ xingrong2024efficient/%E9%A6%96%E9%A1%B5 Copyright © 2024, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Bi-level Allocation Model for Distribution Network Investment Decision Based on Multi-Index System and Reward Coefficient 8

A Bi-level Allocation Model for Distribution Network Investm...

引用

8th Asia Conference on Power and electrical engineering, ACPEE 2023

作者： Liu, Lin Lin, Keyao Yang, Siyu Lin, Yufang Huang, Xianan Shen, Yu Hong, Juhua Economic and Technological Research Institute of State Grid Fujian Electric Power Co. Ltd Energy Development Research Center Fuzhou China State Grid Fujian Electric Power Company Development Planning Department Fuzhou China Fuzhou University College of Electrical Engineering and Automation Fuzhou China Institute of State Grid Fujian Electric Power Co. Ltd Power Grid Development Planning Center Economic and Technological Research Fuzhou China

ISBN: (纸本)9798350345520

Aiming at the problems of unbalanced investment structure and insufficient means of resource allocation in distribution network investment allocation, a bi-level allocation method for distribution network investment decision based on multi-indicator system and reward coefficient is proposed. Considering the needs of investment allocation calculation and input-output efficiency evaluation, the distribution network investment allocation index system and input-output index system are constructed based on the basic indexes of distribution network investment evaluation. The index weights are determined based on the comprehensive subject-objective assignment method combining hierarchical analysis and variance coefficient method, and the index scores are calculated using interval triangular fuzzy affiliation theory. The reward coefficients are introduced to further characterize the relationship between investment allocation and input-output. The relationship between investment allocation and input-output is further portrayed by the introduction of reward coefficients, and a bi-level allocation model of "province-to-city"and "city-to-county"distribution network investment decision is established based on the combined scores of the two. Finally, the results show that the model constructed in this paper can improve the scientificity of distribution network investment allocation. © 2023 IEEE.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Contactless Interaction System Based on Facial Expression Recognition for Humanoid Piano Robot

Contactless Interaction System Based on Facial Expression Re...

引用

IEEE International Conference on robotics and Biomimetics

作者： Ling Zhong Wen Wang Shiqiang Zhu Shanshan Ji Changhai Zha Minhong Wan Jason Gu Zhejiang Lab Research Center for Intelligent Robotics Zhejiang Engineering Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

ISBN: (纸本)9781665481106

With the wide application of service robots in people's daily life, people are not only satisfied with robots accomplishing tasks independently but also hope that robots can maintain sustainable interaction with human beings. Especially in the field of music, robots need to be equipped with intelligent cognitive skills in decision-making, so that the audience can enjoy immersive appreciation and emotional resonance in the robots performance. Visual perception and natural language understanding are essential for robots to establish human-robot friendly relationships. To enrich the interactive ability of music robots, we design a contactless interaction system based on facial expression recognition, which consists of four modules: voice wake-up, face detection, facial expression recognition, and music mapping. When people wake up the music robot with specific words, the robot will customize appropriate music to perform according to the recognition results of the FER module. As a final step, the interaction system has been successfully applied to the piano humanoid robot independently developed by our team.

关键词： Industries Service robots Face recognition Humanoid robots Speech recognition Natural language processing Pensions

来源：评论

学校读者我要写书评

暂无评论

A Distance-Independent Wireless Charging System With Hybrid Topology and Control

A Distance-Independent Wireless Charging System With Hybrid ...

引用

Wireless Power Week (WPW)

作者： Chao Rong Bo Zhang Yanwei Jiang Jiali Zhou School of Electric Power South China University of Technology Guangzhou China College of Electrical Engineering and Automation Fuzhou University Fuzhou China HKU Shenzhen Institute of Research and Inovation Shenzhen China The Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong China

ISBN: (数字)9798350349139

ISBN: (纸本)9798350349146

This paper proposes a distance-independent wireless charging system that achieves constant current (CC) and constant voltage (CV) output through utilization of a reconfigurable topology, capable of seamlessly switching between a two-coil and a three-coil configuration. In order to enhance output adjustability and improve the efficiency of the charging process, this system combines the advantages of fractional-order and integer-order resonant circuits. In the two-coil configuration, the output of the inverter on the transmitter side is modulated as that of a fractional-order capacitor. By analyzing frequency characteristics of the fractional-order circuit, a control strategy of variable fractional order is introduced to achieve CC output against variations of transfer distance based on a mutual inductance recognition method. After transitioning to the three-coil configuration, the system inherently achieves a CV output by operating the inverter at a fixed frequency and forming an integer-order resonant circuit. In addition, in both mentioned configurations, the full-bridge (FB) mode and half-bridge (HB) mode of the inverter are utilized to minimize switching losses and broaden the range of soft-switching operation, catering to various load conditions. Finally, an experimental prototype is built to achieve CC and CV output within a wide charging range.

关键词： Wireless communication Inductance Inductive charging Resonant frequency RLC circuits Prototypes Switches

来源：评论

学校读者我要写书评

暂无评论

Distributed Feedback Optimization of Networked Nonlinear Systems Using Relative Output Measurements*

Distributed Feedback Optimization of Networked Nonlinear Sys...

引用

European Control Conference (ECC)

作者： Zhengyan Qin Tao Liu Tengfei Liu Zhong-Ping Jiang Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong HKU Shenzhen Institute of Research and Innovation Shenzhen China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China Department of Electrical and Computer Engineering New York University Brooklyn NY USA

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

This paper investigates the distributed feedback optimization problem of nonlinear multi-agent systems. In such systems, each agent can measure the relative outputs between itself and its neighbors but lacks access to their absolute states and internal controller states. By combining distributed optimization and singular perturbation methods, a novel distributed controller design is presented, that relies solely on each agent's real-time gradient values of its local objective function and its relative output measurements to neighboring agents. The boundedness of the closed-loop signals and the convergence of the agent outputs to the minimizer of the total cost are proved rigorously. A numerical example is conducted to validate the effectiveness of the proposed approach.

关键词： Costs Perturbation methods Europe Distributed feedback devices Linear programming Real-time systems Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Impact-Induced Frequency Up-Conversion Vibration Energy Harvester Based On Metal-Substrate Piezoelectric Thick Film

Impact-Induced Frequency Up-Conversion Vibration Energy Harv...

引用

Micro and Nanotechnology for Power Generation and Energy Conversion Applications (PowerMEMS)

作者： Kaijun Lin Manjuan Huang Xiaowei Feng Zhenming Li Wei Liu Huicong Liu School of Mechanical and Electrical Engineering Jiangsu Provincial Key Laboratory of Advanced Robotics Soochow University Suzhou CHINA Energy Storage and Electrotechnics Department China Electric Power Research Institute Limited Company Beijing CHINA

ISBN: (数字)9798350380200

ISBN: (纸本)9798350380217

This paper presents an impact-induced frequency up-conversion piezoelectric energy harvester (FUC-PEH) to improve low-frequency output performance. The FUC-PEH includes a high-frequency piezoelectric cantilever (HFPC) with resonant frequency of 210 Hz and a low-frequency S-shaped stainless-steel cantilever (LFSC) with resonant frequency of 30 Hz. The HFPC is manufactured using MEMS metal-substrate lead zirconate titanate (PZT) thick film technology. The peak open-circuit voltage of FUC-PEH reaches 54.6 V over a drive frequency range of 10 to 60 Hz, which is $80 \%$ higher than that of a single HFPC in resonant state. It is expected to replace primary batteries and used as the power source for wireless sensor nodes. In addition, the low-frequency I-shaped stainless-steel cantilever (LFC-I), II-shaped cantilever (LFC-II) and III-shaped cantilever (LFC-III) are fabricated to explore the influence of the stiffness of low-frequency cantilever, the size of proof mass and the gap distance on the output performance of FUC-PEH.

关键词： Wireless communication Vibrations Wireless sensor networks Resonant frequency Voltage Bandwidth Thick films Resonance Lead zirconate titanate Testing

来源：评论

学校读者我要写书评

暂无评论

Axis Kinematics Algorithm for Satellite Manipulator System in Orbital Motion

Axis Kinematics Algorithm for Satellite Manipulator System i...

引用

Space robotics (iSpaRo), International Conference on

作者： Junsik Kim Yuna Choi Youngjin Choi Donghoon Son Alejandro Astudillo Jan Swevers Jonghoon Park Daehee Won Department of Electrical and Electronic Engineering Hanyang University Ansan South Korea Department of Mechanical Engineering Pusan National University Pusan South Korea Department of Mechanical Engineering MECO Research Team KU Leuven Leuven Belgium Neuromeka Seoul South Korea Convergent Technology Research and Development Department Robotics Research and Development Group Korea Institute of Industrial Technology Ansan South Korea

ISBN: (数字)9798350367232

ISBN: (纸本)9798350367249

The paper presents a PoE (product of exponential)–based algorithm to compute the kinematics of general floating-base manipulators, e.g., satellite manipulators. This algorithm is referred to as axis kinematics in this paper which provides up to second-order kinematics including the Jacobian and its time-derivative in terms of spatial screws which are equivalent to the exponential coordinates in the Lie algebra $\mathfrak{s}\mathfrak{e}$(3). As input to the algorithm, an orbital motion of the satellite is derived through Keplerian orbit elements. The base body motion corresponding to the satellite is modeled as a new type of spatial screw that enables elliptic motion. Ultimately, the kinematics of the satellite manipulator system in an elliptical orbit motion is represented in terms of the PoE composed of a set of spatial screws. The proposed method is validated through a numerical example of a satellite manipulator system.

关键词： Space vehicles Jacobian matrices Satellites Algebra Robot kinematics Kinematics Fasteners

来源：评论

学校读者我要写书评

暂无评论

RelationGrasp: Object-Oriented Prompt Learning for Simultaneously Grasp Detection and Manipulation Relationship in Open Vocabulary

RelationGrasp: Object-Oriented Prompt Learning for Simultane...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Songting Liu Tat Joo Teo Zhiping Lin Haiyue Zhu Singapore Institute of Manufacturing Technology (SIMTech) Agency for ScienceTechnology and Research (A*STAR) School of Electrical & Electronic Engineering Nanyang Technological University (NTU) Singapore Robotics Automation & Unmanned SystemsCentre of Expertise Home Team Science and Technology Agency (HTX) Singapore Singapore Institute of Manufacturing Technology (SIMTech) Agency for Science Technology and Research (A*STAR) Singapore Singapore

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Autonomous robotic grasping under complex, clustered, and unstructured environments is a fundamental but challenging task. To achieve human-like rationality in dealing with the grasping task, the agent requires hybrid intelligence from multilateral aspects. This paper introduces RelationGrasp, a unified framework employing a transformer encoder-decoder structure to simultaneously achieve open-vocabulary object detection, manipulation relationship inference, and grasp pose detection. A unique object-oriented prompt learning mechanism is designed to seamlessly bridge the grasp pose and manipulation relationship branches, delivering high fidelity of object-grasp affiliation for object-aware grasping and grasp sequence planning. By formulating the relationship detection as an adjacency matrix regression task under multi-task learning, our framework significantly increases the relationship accuracy with reduced computational overhead. Moreover, to facilitate the robust and adaptive deployment of the proposed RelationGrasp to novel environments, we propose a consistency-based self-supervised adaptation strategy to adapt the pre-trained network to new scenarios and improve grasp accuracy on unseen objects. Our proposed network achieved state-of-the-art performance on various public dataset such as VMRD, OCID, etc., in both grasp detection and manipulation relationship classification, and real-world robot experiments has also been conducted to show the practical usages.

关键词： Learning systems Bridges Vocabulary Accuracy Grasping Object detection Transformers Multitasking Planning Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

SVM-based Extended Kalman Filter State Estimation of Biped Robot

SVM-based Extended Kalman Filter State Estimation of Biped R...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Gao, Chengzhi Xie, Ye Zhu, Shiqiang Huang, Guanyu Kong, Lingyu Xie, Anhuan Gu, Jianjun Zhang, Dan Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou311100 China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China Zhejiang University Zhejiang Hangzhou311100 China York University North YorkM3J 1P3 Canada Department of Electrical and Computer Engineering Dalhousie University HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9781665481090

At present, more and more attention has been paid to the exploration of biped robots. As the precondition of biped stable walking, the state estimation of robot has also received the attention of many experts. Biped robot has special motion characteristics, has a hybrid dynamic system and belongs to a floating base, so it must obtain the contact information of two feet before realizing the motion state estimation of the robot. The contribution of this paper is to introduce soft support vector machine to detect contact phase. This method based on support vector machine (SVM) eliminates the need for force sensors on two feet because they are vulnerable to the impact between the foot and the contact surface. In addition, precise dynamic modeling is not required. Furthermore, this paper uses SVM to obtain the touchdown information, and proposes a state estimation method using extended Kalman filter to combine motion estimation with IMU data. Finally, the touchdown detection algorithm and the state estimation algorithm are verified through experiments, and the accuracy and feasibility of the SVM method are proved through the touchdown detection experiments. Based on this, the full state estimation of the robot is realized through the state estimation experiments. © 2022 IEEE.

关键词： State estimation

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：