检索结果-内蒙古大学图书馆

A novel robotic visual perception framework for underwater operation

Frontiers of Information Technology & Electronic engineering 2022年第11期23卷 1602-1619页

作者： Yue LU Xingyu CHEN Zhengxing WU Junzhi YU Li WEN State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Ytech Kuaishou TechnologyBeijing 100085China State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and RoboticsCollege of EngineeringPeking UniversityBeijing 100871China School of Mechanical Engineering and Automation Beihang UniversityBeijing 100191China

Underwater robotic operation usually requires visual perception(e.g.,object detection and tracking),but underwater scenes have poor visual quality and represent a special domain which can affect the accuracy of visual *** addition,detection continuity and stability are important for robotic perception,but the commonly used static accuracy based evaluation(i.e.,average precision)is insufficient to reflect detector performance across *** response to these two problems,we present a design for a novel robotic visual perception ***,we generally investigate the relationship between a quality-diverse data domain and visual restoration in detection *** a result,although domain quality has an ignorable effect on within-domain detection accuracy,visual restoration is beneficial to detection in real sea scenarios by reducing the domain ***,non-reference assessments are proposed for detection continuity and stability based on object ***,online tracklet refinement is developed to improve the temporal performance of ***,combined with visual restoration,an accurate and stable underwater robotic visual perception framework is ***-overlap suppression is proposed to extend video object detection(VID)methods to a single-object tracking task,leading to the flexibility to switch between detection and *** experiments were conducted on the ImageNet VID dataset and real-world robotic tasks to verify the correctness of our analysis and the superiority of our proposed *** codes are available at https://***/yrqs/VisPerception.

关键词： Underwater operation Robotic perception Visual restoration Video object detection

来源：评论

学校读者我要写书评

暂无评论

PVTimesNet: A Hybrid Deep Learning Method for Enhancing Ultra-Short-Term PV Power Forecasting

PVTimesNet: A Hybrid Deep Learning Method for Enhancing Ultr...

引用

Chinese Automation Congress (CAC)

作者： Ji Wu Kai Wang Wenwen Ma Jingxin Zhang Shibo Wang China Electric Power Research Institute Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing China State Grid Shandong Electric Power Research Institute Jinan China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Accurate ultra-short-term photovoltaic (PV) power forecasting is crucial for the real-time scheduling of grid systems. However, the inherent variability of solar energy makes this task extremely challenging. To enhance PV power forecasting, this paper introduces a novel hybrid model named PVTimesNet, designed to harness the strengths of Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) for effective feature extraction. PVTimesNet consists of two parallel branches: the CNN1d branch, which captures correlations between multiple variables and adjacent time steps, and the LSTM branch, which learns the temporal dependencies within the PV power sequences. The features extracted by both branches are then concatenated and passed through a fully connected layer to generate multi-step PV power forecasts. Experimental results demonstrate that for forecast horizons of 1 to 4 hours, the proposed model significantly outperforms individual models and other CNN-LSTM hybrid structures. Additionally, it exhibits superior performance compared to related methods for longer forecast horizons.

关键词： Photovoltaic systems Deep learning Wind speed Predictive models Feature extraction Hybrid power systems Convolutional neural networks Forecasting Wind forecasting Long short term memory

来源：评论

学校读者我要写书评

暂无评论

An optimal trajectory planning algorithm for T-shaped acceleration curve with non-zero acceleration at the beginning and end

An optimal trajectory planning algorithm for T-shaped accele...

引用

Chinese Automation Congress (CAC)

作者： Yongxu Luo Gan Yahui Dai Xianzhong School of Automation Southeast University Key Laboratorty of Measurement and Control of Complex Systems of Engineering Ministry NanJing China

In order to solve the problem that T-type trajectory planning curve can not completely replace polynomial trajectory planning,this paper proposes an S-type programming algorithm based on the optimization algorithm with T-type acceleration. The algorithm solves the complex and cumbersome problem of time planning of T-shaped acceleration and deceleration curve with non-zero acceleration and velocity at the beginning and end. Taking into account the characteristics of fast acceleration of trajectory planning curve, it can not only solve the case where the initial and end velocities are not zero, but also solve the case where the initial and end accelerations are not zero. The algorithm is based on the analysis of the characteristics of acceleration stage, constant speed stage and deceleration stage. When the highest speed of the curve is determined, the time of all speed segments is also determined. The concept of maximum reachable speed of trajectory is proposed. The complex multivariate nonlinear programming is transformed into a single convex function. The algorithm is simplified by using the symmetry of the variation forms in acceleration stage and deceleration stage. The maximum achievable velocity is solved by dichotomy, Newton iterative method and gradient descent method. The experiment shows that the solving efficiency of Newton iterative method is 40% higher than that of dichotomy method. Compared with the quintic polynomial programming algorithm, the overall planning time is reduced by 9.6% and the tracking error is reduced by 15.9%.

关键词： Trajectory planning Tracking Motion segmentation Optimization methods Linearity Programming Trajectory

来源：评论

学校读者我要写书评

暂无评论

A Short-Term Wind Power Forecasting Method With Self-Supervised Contrastive Learning-Based Feature Extraction Model

A Short-Term Wind Power Forecasting Method With Self-Supervi...

引用

International Youth Conference on Energetics (IYCE)

作者： Nanyang Zhu Kaifeng Zhang Ying Wang Huiping Zheng Yanxia Pan Xueting Cheng Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing Jiangsu China State Grid Shanxi Electric Power Research Institute Shanxi China State Grid Shanxi Electric Power Company Shanxi China

ISBN: (数字)9798350372380

ISBN: (纸本)9798350372397

It is significant and challenging to forecast wind power through the knowledge learned from the historical meteorological variables and wind power itself. So far, this knowledge has been learned based on supervised learning, which is insufficient in capturing semantic dependencies between variables and cannot provide a stability model. This work proposed an unsupervised representation learning-based short-term wind power prediction method using sequences contrastive technique. This representation learning model is mainly composed of the input encoder module, feature extraction module, contrastive learning module, and regression module. The feature extraction module which fuses multiple encoders can extract abundant feature vectors from the multi-source embedding of the input encoder module. The loss function in the contrastive learning module attempts to distinguish positive pairs and negative pairs that are generated from the feature extraction module. Eventually, the regression model uses the fully learned representation matrix for the power estimation. In order to explore the feasibility of this method in wind power prediction, the benefits under different prediction intervals are studied separately through some classic evaluation criteria, and comparing the proposed representation learning-based forecasting with other state-of-the-art methods. The results show that the knowledge learned from this model can generate improved performance with reliability and effectiveness with a 6-hour prediction horizon, and allow the development of short-term wind power forecast.

关键词： Representation learning Supervised learning Stability criteria Contrastive learning Wind power generation Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Modified Artificial Potential Field Method Based on Subgoal Points for Mobile Robot 16th

A Modified Artificial Potential Field Method Based on Subgoa...

引用

16th International Conference on Intelligent Robotics and Applications, ICIRA 2023

作者： Mo, Jixue Gao, Changqing Liu, Fei Yang, Qingkai Fang, Hao Department of Mathematics and Theories Pengcheng Laboratory Shenzhen518055 China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen518055 China Industrial Training Center Shenzhen Polytechnic Shenzhen518055 China Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9789819964826

In this paper, a modified artificial potential field (MAPF) method was proposed for general mobile robot navigation system. This MAPF method can effectively solve the unreachable goal problem and the local minima problem of traditional APF method. The first key idea of MAPF method is to modify the repulsive force function and thus optimize the direction of total repulsive force;the second key idea is to generate a serials of subgoal points around obstacles with specific method, so as to help the robot escape from or keep away from local minima area. By comparing with other similar algorithms in simulation environment, the MAPF algorithm can generate shorter paths efficiently. More importantly, it also can generate effective paths in multi-obstacle environment where other algorithms cannot. Finally the simulation results verified the reasonability and practicability of the proposed MAPF method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Human-Robot Interaction Without Velocity measurement Using Off-Policy Reinforcement Learning

引用

IEEE/CAA Journal of Automatica Sinica 2022年第1期9卷 47-63页

作者： Yongliang Yang Zihao Ding Rui Wang Hamidreza Modares Donald C.Wunsch Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education School of Automation&Electrical EngineeringUniversity of Science and Technology BeijingBeijing 100083China School of Automation Beijng Institute TechnologyBeijing 100081China State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Mechanical Engineering Department Michigan State UniversityEast LansingMI 48824 USA Department of Electrical&Computer Engineering Missouri University of Science&TechnologyRollaMO 65401 USA

In this paper,we present a novel data-driven design method for the human-robot interaction(HRI)system,where a given task is achieved by cooperation between the human and the *** presented HRI controller design is a two-level control design approach consisting of a task-oriented performance optimization design and a plant-oriented impedance controller *** task-oriented design minimizes the human effort and guarantees the perfect task tracking in the outer-loop,while the plant-oriented achieves the desired impedance from the human to the robot manipulator end-effector in the ***-driven reinforcement learning techniques are used for performance optimization in the outer-loop to assign the optimal impedance *** the inner-loop,a velocity-free filter is designed to avoid the requirement of end-effector velocity *** this basis,an adaptive controller is designed to achieve the desired impedance of the robot manipulator in the task *** simulation and experiment of a robot manipulator are conducted to verify the efficacy of the presented HRI design framework.

关键词： Adaptive impedance control data-driven method human-robot interaction(HRI) reinforcement learning velocity-free

来源：评论

学校读者我要写书评

暂无评论

Design and locomotion characteristic analysis of a novel tensegrity hopping robot

Design and locomotion characteristic analysis of a novel ten...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Mo, Jixue Gao, Changqing Fang, Hao Yang, Qingkai Peng Cheng Laboratory Department of Strategic and Advanced Interdisciplinary Research Shenzhen518055 China Harbin Institute of Technology School of Mechanical Engineering and Automation Shenzhen518055 China Beijing Institute of Technology School of Automation Beijing100081 China Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing100081 China

ISBN: (纸本)9798350325706

In consideration of the poor locomotion ability of most traditional tensegrity robot, a novel tensegrity hopping robot powered by push-pull electromagnets was proposed with better locomotivity. It is able to conduct stable consecutive progressing action and turning action through hopping. This paper covers the structural design, theoretical modeling of the robot's hopping process, as well as its self-righting analysis, simulation and experimental verification. The average moving speed and relative moving speed were measured to be 0.334m/s and 0.641 body length/s respectively, which obviously surpass the general moving ability of most traditional tensegrity robot. In addition, the robot was also validated to have good self-righting characteristic for stable consecutive hopping. Thus this robot can be potentially applied for search, rescue, detection, etc. in outdoor and unstructured environment. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Social relation and physical lane aggregator:integrating social and physical features for multimodal motion prediction

引用

Journal of Intelligent and Connected Vehicles 2022年第3期5卷 302-308页

作者： Qiyuan Chen Zebing Wei Xiao Wang Lingxi Li Yisheng Lv The State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijingChina School of Artificial Intelligence University of Chinese Academy of SciencesBeijingChina Electrical and Computer Engineering Indiana University-Purdue University IndianapolisIndianapolisIndianaUSA Complex Systems Institute of AutomationChinese Academy of SciencesBeijingChina and School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijingChina

Purpose–The purpose of this paper aims to model interaction relationship of traffic agents for motion prediction,which is critical for autonomous *** is obvious that traffic agents’trajectories are influenced by physical lane rules and agents’social ***/methodology/approach–In this paper,the authors propose the social relation and physical lane aggregator for multimodal motion prediction,where the social relations of agents are mainly captured with graph convolutional networks and self-attention mechanism and then fused with the physical lane via the self-attention ***–The proposed methods are evaluated on the Waymo Open Motion Dataset,and the results show the effectiveness of the proposed two feature aggregation modules for trajectory ***/value–This paper proposes a new design method to extract traffic interactions,and the attention mechanism is used in each part of the model to extract and fuse different relational features,which is different from other methods and improves the accuracy of the LSTM-based trajectory prediction method.

关键词： Deep learning Machine learning Autonomous driving Trajectory prediction

来源：评论

学校读者我要写书评

暂无评论

Precise GPS-Denied UAV Self-Positioning via Context-Enhanced Cross-View Geo-Localization

arXiv

引用

arXiv 2025年

作者： Xu, Yuanze Dai, Ming Cai, Wenxiao Yang, Wankou School of Automation The Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Jiangsu Province Nanjing210096 China Advanced Ocean Institute of Southeast University Jiangsu Province Nantong226019 China Stanford University StanfordCA94305 United States

Image retrieval has been employed as a robust complementary technique to address the challenge of Unmanned Aerial Vehicles (UAVs) self-positioning. However, most existing methods primarily focus on localizing objects captured by UAVs through complex part-based representations, often overlooking the unique challenges associated with UAV self-positioning, such as fine-grained spatial discrimination requirements and dynamic scene variations. To address the above issues, we propose the Context-Enhanced method for precise UAV Self-Positioning (CEUSP), specifically designed for UAV self-positioning tasks. CEUSP integrates a Dynamic Sampling Strategy (DSS) to efficiently select optimal negative samples, while the Rubik’s Cube Attention (RCA) module, combined with the Context-Aware Channel Integration (CACI) module, enhances feature representation and discrimination by exploiting interdimensional interactions, inspired by the rotational mechanics of a Rubik’s Cube. Extensive experimental validate the effectiveness of the proposed method, demonstrating notable improvements in feature representation and UAV self-positioning accuracy within complex urban environments. Our approach achieves state-of-the-art performance on the DenseUAV dataset, which is specifically designed for dense urban contexts, and also delivers competitive results on the widely recognized University-1652 benchmark. Copyright © 2025, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Bearing Fault Diagnosis Under Variable Working Conditions Based on Domain Adaptation and Improved Depthwise Separable Convolution Network

Bearing Fault Diagnosis Under Variable Working Conditions Ba...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Zehui Kuang Fan Mao Xingyu Zhao Xiongbo Wan Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Future Technology China University of Geosciences Wuhan China Ministry of Education School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

Domain adaptation methods and appropriate feature extractors are usually applied to solve the problem that the variable working conditions of bearings affect the effectiveness of the fault diagnostic framework. However, the existing feature extractors are too complex to be deployed in real industries. In this paper, we propose a lightweight framework called improved depthwise separable convolution network (IDSCN) for the diagnosis of bearing faults in variable operating conditions. IDSCN is built on wavelet convolution and depthwise separable residual convolution (DSRC), where the wavelet convolution is used to extract frequency features from the source and target domains, and DSRC guarantees the performance of feature extraction with reduced parameters and computation. To minimise the distribution difference between the source and target domains, the local maximum mean difference is incorporated into the proposed framework. The performance of the proposed framework is validated on the Paderborn University dataset, involving a total of 6 transfer tasks. The experiment shows that the proposed framework achieves satisfactory results and outperforms other frameworks in bearing fault diagnosis.

关键词： Employee welfare Fault diagnosis Vibrations Industries Adaptation models Wavelet domain Convolution Frequency-domain analysis Feature extraction complexity theory

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：