检索结果-内蒙古大学图书馆

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

作者： Chengyang Li Yulai Zhang Zhiqiang Yu Xinming Liu Qing Shi Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing School of Medical Technology Beijing Institute of Technology Jiaxing China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing China Key Laboratory of Biomimetic Robots and Systems Beijing Institute of Technology Ministry of Education Beijing China Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This paper presents a robust visual SLAM system designed for small-scale quadruped robots (ViQu-SLAM) for accurate localization, especially to mitigate the issue of erroneous data association caused by moving objects in dynamic environments. The proposed approach leverages a selfadaptive framework that integrates semantic segmentation with alterations in the spatial location of categorized map points. Besides, combination of leg odometry derived from forward kinematics with IMU provides scale information for positional transformations between keyframes, thus optimizing the overall localization accuracy of quadruped robots. At last, we performed evaluation across various stages and the results demonstrate competitive performance, with 53.16% reduction in average absolute trajectory error compared to that of ORB-SLAM3 in dynamic benchmark datasets. As a result, ViQu-SLAM, including visual and IMU-fused leg odometry, exhibits promising results on a small quadruped robot, reducing positioning errors in dynamic scenes by an average of 29.36% compared to existing state-of-the-art methods.

关键词： Legged locomotion Location awareness Visualization Simultaneous localization and mapping Accuracy Semantic segmentation Heuristic algorithms Object detection Quadrupedal robots Odometry

来源：评论

学校读者我要写书评

暂无评论

OC3: A Reactive Velocity Level Motion Planner with Complementarity Constraint-based Obstacle Avoidance for Mobile Robots

OC3: A Reactive Velocity Level Motion Planner with Complemen...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Anirban Sinha Riddhiman Laha Nilanjan Chakraborty The Robotics And Autonomous Systems Lab at General Electric Research NY USA The Munich Institute of Robotics and Machine Intelligence TUM Germany The Mechanical Engineering Department Stony Brook University NY USA

This paper presents a novel real-time motion planning method for differential drive mobile robots. Reactive planners, in the context of mobile robots, are usually vulnerable to challenges like local minima, differential constraint satisfaction, and dynamic obstacles. To this end, we present the Off-Center point Complementarity Constraint (OC3) planner, which respects the differential constraints of robot kinematics, can handle dynamic obstacles, and is more robust to the local minima problem compared to traditional methods like artificial potential fields. Our OC3 planner utilizes a virtual contact mechanism at a distal off-center point of the robot for obstacle avoidance, thereby ensuring smooth maneuvers. We formulate the obstacle avoidance problem as a feasibility problem with complementarity constraints, and derive a closed-form solution. This enables fast online computation of collision-free waypoints for the robot off-center. Once a collision-free state of the off-center point is found, inverse velocity kinematics is used to compute the reference control input velocities (∈ ℝ 2 ) for the robot. We further show that OC3 can be used as a local planner in RRT type of sampling-based global planning framework to avoid the local minimum problem. Our extensive analysis through various case studies and rigorous simulation experiments, using the popular ROS based Turtlebot3 simulator, in the presence of static and dynamic obstacles, demonstrate the efficacy of our framework including real-time proficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Compensating for the Effect of Absence of Joint Movements in EMG-based Continuous Movement Decoding with a Deep Learning Approach 30

Compensating for the Effect of Absence of Joint Movements in...

引用

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Pan, Lizhi Ding, Zhongyi Li, Chengjun Zhao, Haifeng Mu, Ruinan Li, Jianmin Li, Jinhua Tianjin University Key Laboratory of Mechanism Theory and Equipment Design Ministry of Education School of Mechanical Engineering Tianjin300350 China Tianjin University Institute of Medical Robotics and Intelligent Systems Tianjin300350 China Chinese Academy of Sciences Key Laboratory of Space Utilization Technology and Engineering Center for Space Utilization Beijing100094 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9798350391916

In recent decades, human-machine interfaces (HMIs) based on electromyography (EMG) signals have become research hotspots in the fields of rehabilitation engineering, aerospace, and human factors engineering. However, the absence of joint movements can influence the performance of HMIs in the continuous movement decoding. Therefore, it has become an urgent problem to improve the quality of EMG signals with the absence of joint movements. In this study, a deep learning (DL) method is proposed based on the convolutional neural network (CNN) to compensate for the absence of joint movements in EMG-based continuous movement decoding. Ten able-bodied subjects were recruited to complete a series of movements with the metacarpophalangeal (MCP) and wrist joints unconstrained (MWJU) and constrained (MWJC). Half of the EMG signals for the constrained joint movements were compensated with the proposed CNN-based method (CNN-EMG), which were then compared with the other half of the constrained EMG signals (MWJC-EMG) and the signals without joint constraints (MWJU-EMG). The Pearson's correlation coefficient (r) and the normalized root mean square error (NRMSE) were employed as the indexes to quantify the performance of continuous movement decoding with three groups of EMG signals. Compared with the performance of MWJC-EMG, the average r values for wrist and MCP flexion/extension of CNN-EMG signals increased from 0.8 to 0.84 and from 0.49 to 0.66, respectively. Compared with the performance of MWJC-EMG signals, the average NRMSE values for wrist and MCP flexion/extension of CNN-EMG signals decreased from 0.21 to 0.19 and 0.31 to 0.26, respectively. The analysis results demonstrated that the proposed DL method can significantly improve the continuous movement decoding performance of HMIs through compensating the effect of absence of joint movements. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Robustness in Manipulability Assessment: The Pseudo-Ellipsoid Approach

Enhancing Robustness in Manipulability Assessment: The Pseud...

引用

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

作者： Erfan Shahriari Kim Kristin Peper Matej Hoffmann Sami Haddadin Chair of Robotics and Systems Intelligence Munich Institute of Robotics and Machine Intelligence Technical University of Munich (TUM) Germany Department of Mechanical Engineering Newman Laboratory for Biomechanics and Human Rehabilitation Massachusetts Institute of Technology (MIT) USA Department of Cybernetics Faculty of Electrical Engineering Czech Technical University in Prague (CTU) Czech Republic

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Manipulability analysis is a methodology employed to assess the capacity of an articulated system, at a specific configuration, to produce motion or exert force in diverse directions. The conventional method entails generating a virtual ellipsoid using the system’s configuration and model. Yet, this approach poses challenges when applied to systems such as the human body, where direct access to such information is limited, necessitating reliance on estimations. Any inaccuracies in these estimations can distort the ellipsoid’s configuration, potentially compromising the accuracy of the manipulability assessment. To address this issue, this article extends the standard approach by introducing the concept of the manipulability pseudo-ellipsoid. Through a series of theoretical analyses, simulations, and experiments, the article demonstrates that the proposed method exhibits reduced sensitivity to noise in sensory information, consequently enhancing the robustness of the approach.

关键词： Analytical models Visualization Accuracy Sensitivity analysis Noise Force Estimation Robustness Ellipsoids Standards

来源：评论

学校读者我要写书评

暂无评论

Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptation

arXiv

引用

arXiv 2023年

作者： Carrazco, Julio Ivan Davila Morerio, Pietro Del Bue, Alessio Murino, Vittorio Italian Institute of Technology Genoa Italy Department of Computer Science University of Verona Verona Italy Department of Computer Science and Technology Bioengineering Robotics and Systems Engineering University of Genova Genoa Italy Department of Marine Electrical Electronic and Telecommunications Engineering Robotics and Systems Engineering University of Genova Genoa Italy

This paper presents a classification framework based on learnable data augmentation to tackle the One-Shot Unsupervised Domain Adaptation (OS-UDA) problem. OS-UDA is the most challenging setting in Domain Adaptation, as only one single unlabeled target sample is assumed to be available for model adaptation. Driven by such single sample, our method LearnAug-UDA learns how to augment source data, making it perceptually similar to the target. As a result, a classifier trained on such augmented data will generalize well for the target domain. To achieve this, we designed an encoder-decoder architecture that exploits a perceptual loss and style transfer strategies to augment the source data. Our method achieves state-of-the-art performance on two well-known Domain Adaptation benchmarks, DomainNet and VisDA. The project code is available at https://***/IIT-PAVIS/LearnAug-UDA. © 2023, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

LipKernel: Lipschitz-Bounded Convolutional Neural Networks via Dissipative Layers

arXiv

引用

arXiv 2024年

作者： Pauli, Patricia Wang, Ruigang Manchester, Ian Allgöwer, Frank Institute for Systems Theory and Automatic Control University of Stuttgart Stuttgart70550 Germany Australian Centre for Robotics School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney Australia

We propose a novel layer-wise parameterization for convolutional neural networks (CNNs) that includes built-in robustness guarantees by enforcing a prescribed Lipschitz bound. Each layer in our parameterization is designed to satisfy a linear matrix inequality (LMI), which in turn implies dissipativity with respect to a specific supply rate. Collectively, these layer-wise LMIs ensure Lipschitz boundedness for the input-output mapping of the neural network, yielding a more expressive parameterization than through spectral bounds or orthogonal layers. Our new method LipKernel directly parameterizes dissipative convolution kernels using a 2-D Roesser-type state space model. This means that the convolutional layers are given in standard form after training and can be evaluated without computational overhead. In numerical experiments, we show that the run-time using our method is orders of magnitude faster than state-of-the-art Lipschitz-bounded networks that parameterize convolutions in the Fourier domain, making our approach particularly attractive for improving robustness of learning-based real-time perception or control in robotics, autonomous vehicles, or automation systems. We focus on CNNs, and in contrast to previous works, our approach accommodates a wide variety of layers typically used in CNNs, including 1-D and 2-D convolutional layers, maximum and average pooling layers, as well as strided and dilated convolutions and zero padding. However, our approach naturally extends beyond CNNs as we can incorporate any layer that is incrementally dissipative. Copyright © 2024, The Authors. All rights reserved.

关键词： Parameterization

来源：评论

学校读者我要写书评

暂无评论

Multi-microgrid Multi-energy Optimal Scheduling Strategy Based on Hybrid Energy Storage System and Sharing Technology

Multi-microgrid Multi-energy Optimal Scheduling Strategy Bas...

引用

Chinese Control and Decision Conference, CCDC

作者： Decai Zhang Huaiyu Wu Mian Hu Yang Chen Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education Wuhan University of Science and Technology Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

To effectively enhance the utilization of renewable energy in multi-microgrid systems while ensuring fair distribution of benefits among microgrids, this paper proposes a multi-microgrid multi-energy optimal scheduling strategy based on hybrid energy storage system (HESS) and sharing technology. Firstly, a novel multi-microgrid multi-energy shared energy storage system framework is designed, considering that a HESS is equipped with hydrogen storage system, electric boiler, heat storage tank, P2G devices and gas storage tank as well as coordinates the multi-energy sharing among microgrids. All microgrids and HESS are composed into a microgrid alliance for cooperative game. Secondly, the alternating direction method of multipliers (ADMM) is used to solve the optimal energy transaction volume and transaction price between each microgrid and HESS. Then, the asymmetric Nash negotiation (ANN) method is used to fairly distribute the benefits obtained by each subject. Finally, the simulation experiment shows that the proposed multi-microgrid multi-energy optimal scheduling strategy can not only meet the needs of various energy sources of microgrid, but also improve the utilization rate of renewable energy and the economic benefits of each subject.

关键词： Renewable energy sources Privacy Costs Simulation Microgrids Optimal scheduling Minimization

来源：评论

学校读者我要写书评

暂无评论

Distributed operational management of microgrids: a second order dual update approach

引用

IFAC-PapersOnLine 2023年第2期56卷 1540-1545页

作者： Giulio Ferro Michela Robba Federico Delfino Rabab Haider Anuradha M. Annaswamy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa Italy Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge MA 02141 USA Department of of Electrical Electronic Telecommunications Engineering and Naval Architecture University of Genova

This paper develops a Distributed Energy Management System (EMS) to optimally allocate electric and thermal power production in a polygenerative microgrid. The EMS problem is formulated as a multiperiod convex optimization problem and solved using AL-SODU, a new distributed algorithm based on the augmented Lagrangian method with second order dual updates. The proposed AL-SODU algorithm significantly outperforms state of the art algorithms employing first order dual updates, with 15-times speedup in convergence speed. A case study of the EMS based on AL-SODU is conducted on the Smart Polygeneration Microgrid (SPM) located on the Savona Campus of University of Genova (Italy). The EMS determines the optimal schedules for electric and thermal power plants every 15-minutes. This real time scheduling of the microgrid is enabled by the Al-SODU algorithm, which solves the scheduling problem in 1.86s.

关键词： Microgrids distributed control second order methods

来源：评论

学校读者我要写书评

暂无评论

A 5G-Based Switching Method between a Local Controller and an Edge Controller 6

A 5G-Based Switching Method between a Local Controller and a...

引用

6th International Conference on Intelligent robotics and Control engineering, IRCE 2023

作者： Wang, Xiulian Lin, Jinggao Jin, Xi Xia, Changqing Xu, Chi College of Automation and Electrical Engineering Shenyang Ligong University China Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9798350326338

With the rapid development of edge computing, industrial automation has evolved a two-layer distributed computing architecture, including local controllers communicating through wired networks and edge controllers communicating wirelessly. The edge controllers in existing studies use WIFI, which has a limited working distance and requires independent network deployment, so they are unsuitable for future large-scale complex industrial production. At present, 5G technology is undergoing rapid development in the field of industrial automation, with wide coverage and excellent mobility, gradually becoming suitable for future large-scale and complex industrial production scenarios. Therefore, this paper proposed an SW5G method based on 5G, which combined the local controller with the edge controller. The controllers were switched according to the constantly changing 5G network transmission delay, thereby optimizing the overall system control performance. Finally, simulation experiments demonstrated good control performance of SW5G in various network scenarios. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Signal Processing for Acoustic Emission Signature Analysis and Defect Detection

Signal Processing for Acoustic Emission Signature Analysis a...

引用

Digital Signal Processing and its Applications (DSPA), International Conference on

作者： Yeldos A. Altay Dmitry O. Kuzivanov Dinara A. Altay Alexey V. Fedorov Department of Robotics and Technical Means of Automation Satbayev University Almaty Kazakhstan Faculty of Control Systems and Robotics ITMO University Saint-Petersburg Russian Federation Department of Natural Sciences Military Engineering Institute of Radio Electronics and Communications Almaty Kazakhstan

This article presents the results of implementing a digital signal processing method for analyzing the acoustic emission (AE) signature and detecting defects such as cracks and pores. The signal processing method is based on a cascade connection of digital high-pass filters and ensures the selection of informative signals and increases the signal-to-interference ratio. In order to control the formation of defects in the process of selective laser melting, the paper presents the results of experimental testing of the cascade filtration method for detecting defects in the internal structure such as cracks and pores. The signal components recorded during the development of defects during the growth of additive manufacturing products were extracted. AE signatures were analyzed and statistical relationships were assessed. The relationship between the parameters of the AE signal and the values of laser radiation power has been identified, which characterizes the process of defect formation.

关键词：

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：