检索结果-内蒙古大学图书馆

Semi-Autonomous Navigation Based on Local Semantic Map for Mobile Robot

Journal of Shanghai Jiaotong university(Science) 2025年第1期30卷 27-33页

作者： ZHAO Yanfei XIAO Peng WANG Jingchuan GUO Rui Department of Automation Institute of Medical RoboticsShanghai Jiao Tong UniversityShanghai200240China State Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240China State Grid Intelligence Technology Co. Ltd.Jinan250013China

Mobile robots represented by smart wheelchairs can assist elderly people with mobility *** paper proposes a multi-mode semi-autonomous navigation system based on a local semantic map for mobile robots,which can assist users to implement accurate navigation(e.g.,docking)in the environment without prior *** order to overcome the problem of repeated oscillations during the docking of traditional local path planning algorithms,this paper adopts a mode-switching method and uses feedback control to perform docking when approaching semantic *** last,comparative experiments were carried out in the real *** show that our method is superior in terms of safety,comfort and docking accuracy.

关键词： semi-autonomous navigation mobile robot semantic map voice interaction

来源：评论

学校读者我要写书评

暂无评论

Design and fabrication of accelerometer based on atomic force microscope measurement principle

引用

IEEE Sensors Journal 2025年第10期25卷 16965-16972页

作者： Miao, Bin Guo, Hongji Wang, Dingyi Xiong, Wen Feng, Changkun Xu, Zhan Fang, Siyuan Zhan, Hanwenyu Yu, Peng Li, Jiadong University of Science and Technology of China School of Nano-Tech and Nano-Bionics Hefei230026 China Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang Institute of Automation Shenyang110016 China Huazhong University of Science and Technology National Laboratory of Precision Gravity Surveying Wuhan China Chinese Academy of Sciences Key Laboratory of Multifunctional Nanomaterials and Smart Systems Suzhou Institute of Nano-Tech and Nano-Bionics Suzhou215123 China

This paper introduces a new accelerometer based on the measurement principle of atomic force microscopy. Through the structural design of micro-cantilever arrays with different stiffness coefficients, both high resolution and large dynamic range of acceleration detection can be realized theoretically. The simulation results show that the acceleration sensor can achieve 700 ng-3 g acceleration detection. The experimental results show that the operating bandwidth of the accelerometer is 570 Hz, the background noise is 700 ng/√Hz, the bias instability is 10 ng, and the acceleration dynamic detection range is ±3 g. This scheme proves the feasibility of the accelerometer based on AFM principle, and provides a new way for the development and application of large dynamic range and high-resolution accelerometers. © 2001-2012 IEEE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Multi-Occupancy Activity Recognition Based on Deep Learning Models Fusing UWB Localisation Heatmaps and Nearby-Sensor Interaction

引用

IEEE Internet of Things Journal 2025年

作者： Anguita-Molina, Miguel Angel Cardoso, Pedro J. S. Rodrigues, Joao M. F. Medina-Quero, Javier Polo-Rodriguez, Aurora University of Granada Department of Computer Engineering Automation and Robotics 18071 Spain University of Algarve Nova Lincs and Institute of Engineering Faro8005-139 Portugal

Human Activity Recognition focuses on developing systems and techniques to recognise and categorise human actions automatically based on sensor data. This study combines ultra-wideband technology and binary sensors to describe and recognise daily activities in real-world environments with multiple occupants, ensuring accurate user localisation through non-invasive and privacy-respecting methods. A novel method that combines wearables with ultra-wideband technology, which allows the generation of heatmaps for accurate positioning, and binary sensors, which collect nearby interaction with daily activities in naturalistic conditions, is presented. A dataset comprised of real-world data collected from three individuals in a real-life environment (house) was compiled. Advanced deep learning models are implemented to effectively fuse spatiotemporal information, leading to an encouraging performance in recognition of daily activities. The promising results suggest that this approach could be viable for large-scale deployments in future smart environments. © 2014 IEEE.

关键词： Ultra-wideband (UWB)

来源：评论

学校读者我要写书评

暂无评论

Acceleration-level coordinated control of a dual-arm free-floating space robot under hard joint constraints

引用

Advances in Space Research 2025年第11期75卷 8122-8139页

作者： Xue, Zhihui Liu, Jinguo Zhang, Xin Zhou, Hao Li, Yangmin State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Kowloon999077 Hong Kong School of Electrical and Mechanical Engineering University of Portsmouth PortsmouthPO1 3DJ United Kingdom

Dual-arm space robots are becoming increasingly crucial in on-orbit servicing missions. The online motion control of a dual-arm redundant space robot with hard joint constraints presents significant challenges due to its free-floating base. In this article, we proposed an acceleration-level coordinated control framework to solve hard joint constraints and dynamic singularity. The proposed framework combines a task scheduling strategy to achieve saturation in the null space, so that different tasks can achieve trajectory tracking with minimal task scaling under given joint hard constraints. The framework can achieve efficient online control by sequentially abandoning the use of joints that exceed the joint constraint and reintroducing these commands at their saturation level by projecting them into the appropriate null space. Finally, we verify the tracking performance of the algorithm through numerical simulation and experimental research. By comparing the proposed algorithm with the quadratic programming and pseudo-inverse methods, the algorithm has shown excellent online motion control performance, with a computation time of approximately 1 ms within a single sampling period. © 2025 COSPAR

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Modular Robot Task Execution Framework for Industrial PCB Handling: A Behavior Tree Approach

Modular Robot Task Execution Framework for Industrial PCB Ha...

引用

International Conference on Autonomous Robots and Agents, ICARA

作者： Sharath Chandra Akkaladevi Markus Ganglbauer Kapil Deshpande Sebastian Ukleja Andreas Pichler Institute of Networked and Embedded Systems University of Klagenfurt Klagenfurt Austria Robotics and Automation Systems Profactor GmbH Steyr-Gleink Austria

ISBN: (数字)9798331509231

ISBN: (纸本)9798331509248

Handling printed circuit boards (PCBs) in industrial environments presents significant challenges due to design variability, high precision requirements, and the need for scalability. Traditional manual workflows are laborintensive and error-prone, while fixed robotic systems lack the adaptability to manage diverse PCB types and task variations. This paper proposes a Behavior Tree (BT)-based framework for automating PCB handling tasks, integrating advanced robotic skills such as detection, grasping, and precise placement. The framework is enhanced by a multimodal Vision System for robust pose estimation, an intuitive Human Interface for task reconfiguration, and a modular Robotic Manipulation Module for reliable execution. The BT-based architecture ensures modularity, and adaptability, addressing the demands of dynamic industrial workflows. Experimental validation demonstrates the framework's ability to handle PCB variability and execute precision-critical tasks efficiently, showcasing its potential for scalable deployment in industrial settings.

关键词： automation Service robots Scalability Machine vision Printed circuits Pose estimation Grasping Manuals Reliability engineering Robustness

来源：评论

学校读者我要写书评

暂无评论

Application of convolutional neural networks for ultrasonic signal classification in the measurement of oil slick thickness on ocean surface

引用

Journal of Cleaner Production 2025年 508卷

作者： Zhao, Jing Du, Hualong Meng, Fankun Zhang, Qifeng State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China

The application of Remotely Operated Vehicles (ROVs) integrated with ultrasonic transducers has been validated as a promising method for measuring the oil slick thickness at the sea surface. Nevertheless, the dynamic nature of sea waves and the ROV's movement often lead to the acquisition of numerous unusable ultrasonic signals, characterized by diminished signal-to-noise ratios (SNRs) or ambiguous reflections from water-oil interfaces, thereby significantly impacting measurement accuracy. To address this challenge, we proposed a novel signal classification framework leveraging a Convolutional Neural Network (CNN) architecture, specifically employing the Visual Geometry Group 16 (VGG16) model, to intelligently differentiate between unusable and useable ultrasonic signals reflected from oil slicks. Our methodology incorporated time-frequency analysis with deep feature extraction, facilitating a robust evaluation of signal quality under diverse environmental conditions. The experiments measuring oil slick thicknesses were conducted under both the calm (no wave) and the mimicked sea wave conditions (sine wave and chop wave). Compared traditional thresholding filtering methods, the proposed methodology exhibited a significant performance improvement, as indicated by a 68 % reduction in the mean relative error (RE) of the calculated thickness (decreasing from 7.47 % to 2.38 %) and a 74 % decrease in the standard deviation (STD) (from 1.40 to 0.36) under calm sea conditions. Furthermore, both RE and STD demonstrated a decreasing trend in the presence of wave conditions. By integrating advanced deep learning algorithms with ultrasonic sensing technologies, this research has the potential to significantly improve the accuracy of oil slick thickness measurements. This advancement offers critical support for the development of oil spill response and environmental remediation strategies. © 2025

关键词： Remotely operated vehicles

来源：评论

学校读者我要写书评

暂无评论

Embedding Soft Material Channels for Tactile Sensing of Complex Surfaces - Light Propagation Modelling

引用

IEEE Sensors Journal 2025年第10期25卷 17230-17238页

作者： Hu, Jian Chen, Jian Back, Junghwan Zhao, Tianrui Dasgupta, Prokar Liu, Hongbin State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence and Robotics Hk Institute of Science and Innovation Chinese Academy of Sciences Hong Kong King's College London School of Biomedical and Imaging Science London United Kingdom Centre of Ai and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Hong Kong Haptron Scientific Ltd. Shenzhen China School of Biomedical and Imaging Science King's College London London United Kingdom Mrc Centre for Transplantation Nihr Biomedical Research Centre King's College London London United Kingdom Guy's and St. Thomas' Nhs Foundation Trust Urology London United Kingdom

In previous work, "Embedding Softness into Structure ENabling distributed tactile sensing of high-order Curved Surfaces"(ESSENCE) technology, a general principle for accurate and robust tactile sensing on arbitrary surfaces, has been developed. Each tactel consists of a soft material sensing channel, a light source, and an optical receiver. Force applied on the tactel is transformed through the channel to cause an axial protrusion of the soft material. By measuring the change in light intensity caused by the protrusion, the magnitude of the force can be determined. However, multiple receivers share a single light source, resulting in lighting conditions in the region of interest (ROI) to vary from place to place, which in turn affects the consistency of sensing performance. To overcome this challenge, a freeform reflective funnel of the light source that is coated with a layer of high reflective material is designed to reshape the light distribution. Theoretical analysis and experimental results show that the proposed method improves the sensing consistency. For a 3 by 3 array-type sensor, the standard deviations of the force measuring range, linearity and sensitivity before and after using the freeform surface are 0.29N and 0.08N, 4.58% and 4.04%, 0.016 N-1 and 0.007 N-1, respectively. © 2001-2012 IEEE.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Golden Jackal Optimization Algorithm for Mobile Robotic Path Planning

An Adaptive Golden Jackal Optimization Algorithm for Mobile ...

引用

2024 International Conference on Mechatronics and Intelligent Control, ICMIC 2024

作者： Chen, Siwen Zheng, Xiujuan Shanghai United Imaging Healthcare Co. Ltd. Shanghai China Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education Wuhan University of Science and Technology Wuhan China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

Given the shortcomings of the traditional Golden Jackal Optimization (GJO) algorithm, including limited accuracy and slow convergence speed in solving mobile robot path planning problems, an improved adaptive Golden Jackal Optimization (IAGJO) method is proposed. Firstly, a nonlinear adaptive energy strategy is presented to adjust the energy decay pattern, balancing global and local search. Secondly, an enhanced position update mechanism based on Cauchy and Gaussian mutation increases population diversity and guide the search based on optimal individuals, thereby facilitating efficient exploration of unknown regions and avoiding local optima. Finally, the IAGJO algorithm is applied to mobile robot path planning (MRPP), demonstrating that the IAGJO achieves shorter path lengths and higher search efficiency, exhibiting significant advantages over existing methods. © 2025 SPIE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Research Progress on Industrial Robots: A Review

引用

Recent Patents on Mechanical Engineering 2025年

作者： Shinde, Vilas B. Pawar, Padmakar J. Gadakh, Vijay S. Department of Automation & Robotics Engineering Amrutvahini College of Engineering Sangamner Ahmednagar Savitribai Phule Pune University Maharashtra Pune422 608 India Department of Robotics & Automation Engineering K. K. Wagh Institute of Engineering Education and Research Nashik Savitribai Phule Pune University Maharashtra Pune422 003 India

The success of the fourth and upcoming fifth industrial resolution lies majorly in automation and robotics. Industrial robots perform various manufacturing-related tasks due to their autonomy, flexibility, and autonomous work in a complex environment. Applications including drilling, material transfer, loading and unloading machines, processing, assembling, and inspection, welding, spray painting, machining, and so on are common. The present work comprehensively summarizes all the pertinent work related to the industrial robot, such as inverse kinematics problems, robot design, programming, scheduling, motion planning, and trajectory planning. In addition, the present work discusses various optimization algorithms employed in industrial robots. Furthermore, several recommendations for future research have been addressed. © 2024 Bentham Science Publishers.

关键词： Unloading

来源：评论

学校读者我要写书评

暂无评论

Human-Like Robot Impedance Regulation Skill Learning from Human-Human Demonstrations

arXiv

引用

arXiv 2025年

作者： Li, Chenzui Wu, Xi Liu, Junjia Teng, Tao Chen, Yiming Calinon, Sylvain Caldwell, Darwin Chen, Fei Department of Mechanical and Automation Engineering T-Stone Robotics Institute The Chinese University of Hong Kong Hong Kong Idiap Research Institute Martigny Switzerland Department of Advanced Robotics Istituto Italiano di Tecnologia Genoa16163 Italy

Humans are experts in collaborating with others physically by regulating compliance behaviors based on the perception of their partners’ states and the task requirements. Enabling robots to develop proficiency in human collaboration skills can facilitate more efficient human-robot collaboration (HRC). This paper introduces an innovative impedance regulation skill learning framework for achieving HRC in multiple physical collaborative tasks. The framework is designed to adjust the robot compliance to the human partner’s states while adhering to reference trajectories provided by human-human demonstrations. Specifically, electromyography (EMG) signals from human muscles are collected and analyzed to extract limb impedance, representing compliance behaviors during demonstrations. Human endpoint motions are captured and represented using a probabilistic learning method to create reference trajectories and corresponding impedance profiles. Meanwhile, an LSTM-based module is implemented to develop task-oriented impedance regulation policies by mapping the muscle synergistic contributions between two demonstrators. Finally, we propose a whole-body impedance controller for a human-like robot, coordinating joint outputs to achieve the desired impedance and reference trajectory during task execution. Experimental validation was conducted through a collaborative transportation task and two interactive Tai Chi pushing hands tasks, demonstrating superior performance from the perspective of interactive forces compared to a constant impedance control method. Copyright © 2025, The Authors. All rights reserved.

关键词： Electromyography

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：