检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Automation (ICRA)

作者： Karlo Koledić Igor Cvišić Ivan Marković Ivan Petrović University of Zagreb Faculty of Electrical Engineering and Computing Laboratory for Autonomous Systems and Mobile Robotics Zagreb Croatia

Autonomous localization in unknown environments is a fundamental problem in many emerging fields and the monocular visual approach offers many advantages, due to being a rich source of information and avoiding comparatively more complicated setups and multisensor calibration. Deep learning opened new venues for monocular odometry yielding not only end-to-end approaches but also hybrid methods combining the well studied geometry with specific deep components. In this paper we propose a monocular odometry that leverages deep depth within a feature based geometrical framework yielding a lightweight frame-to-frame approach with metrically scaled trajectories and state-of-the-art accuracy. The front-end is based on a multihypothesis matcher with perspective correction coupled with deep depth predictions that enables careful feature selection and tracking; especially of ground plane features that are suitable for translation estimation. The back-end is based on point-to-epipolar line minimization for rotation and unit translation estimation, followed by deep depth aided reprojection error minimization for metrically correct translation estimation. Furthermore, we also present a domain shift adaptation approach that allows for generalization over different camera intrinsic and extrinsic setups. The proposed approach is evaluated on the KITTI and KITTI-360 datasets, showing competitive results and in most cases outperforming other state-of-the-art stereo and monocular methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a Tomato Harvesting Robot: Peduncle Recognition and Approaching 3

Development of a Tomato Harvesting Robot: Peduncle Recogniti...

引用

3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2021

作者： Kounalakis, Nikolaos Kalykakis, Emmanouil Pettas, Manos Makris, Alexandros Kavoussanos, Manolis M. Sfakiotakis, Michael Fasoulas, John Hellenic Mediterranean University Control Systems and Robotics Laboratory School of Engineering Heraklion71410 Greece

ISBN: (纸本)9781665440585

Over the last decade there is a growing effort to incorporate robotic technologies in agriculture to reduce costs and increase yields and quality. In this paper we present the methods and tools developed for automated tomato harvesting by a greenhouse robot. The system is comprised of a 6-dof manipulator arm, a custom gripping/cutting end-effector, and a depth camera with dedicated vision processor. Deep learning algorithms are employed to locate ripe tomatoes and their peduncles, exploiting depth information from the acquired images to guide the manipulator arm towards the identified cutting points. Through extensive experiments in a realistic setting, the overall success rate of the detection and approach procedure was found to be 65%, with 92.6% accuracy of the vision processing in locating the correct cutting point. Suggestions for further improvement of the system's performance are also provided. © 2021 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multistable Soft Actuator for Physical Human-robot Interaction

Multistable Soft Actuator for Physical Human-robot Interacti...

引用

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

作者： Juncai Long Jituo Li Xiaojie Diao Chengdi Zhou Guodong Lu Yixiong Feng Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou China Zhejiang University Robotics Institute China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Collaboration with robots through physical contact offers a more intuitive, natural, and engaging operational experience, showcasing vast potential in the field of human-robot interaction. However, current physical interaction devices, such as collaborative robots and haptic feedback mechanisms, are limited by their singular modes of motion and feedback, hindering enhancements in interaction experiences. Herein, we present a multistable soft actuator capable of driving multimodal shape changes and passively conforming to user touch. This actuator can memorize and maintains any deformation with zero power consumption. Its structural mechanical properties can be dynamically adjusted to produce rich haptic feedback for the user, including changes in shape, elasticity, stiffness, and even sensations of rupture and weightlessness. Structurally, the mechanism consists of a network of pneumatic bistable units in series and parallel configurations, which can switch states under air pressure or external force, achieving extension, contraction, and omnidirectional bending. The input of air pressure can either impede or assist deformation, altering structural stiffness and resulting in varied loading curves. With its high safety in physical interactions, robust operability, and rich mechanical tactile feedback, the multistable soft actuator promises new design directions for physical human-robot interaction devices.

关键词： Training Actuators Shape Deformation System performance Force Human-robot interaction Tactile sensors Soft robotics Haptic interfaces

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

Model heat source using actual distribution of laser power density for simulation of laser processing

引用

Journal of Central South University 2022年第10期29卷 3277-3293页

作者： WANG Gen-wang DING Ye GUAN Yan-chao WANG Yang YANG Li-jun State Key Laboratory of Robotics and Systems Harbin Institute of TechnologyHarbin 150001China School of Mechatronics Engineering Harbin Institute of TechnologyHarbin 150001China

The model of heat source(MHS) which reflects the thermal interaction between materials and laser during processing determines the accuracy of simulation results. To acquire desirable simulations results, although various modifications of heat sources in the aspect of absorption process of laser by materials have been purposed, the distribution of laser power density(DLPD) in MHS is still modeled theoretically. However, in the actual situations of laser processing, the DLPD is definitely different from the ideal models. So, it is indispensable to build MHS using actual DLPD to improve the accuracy of simulation results. Besides, an automatic modeling method will be benefit to simplify the tedious pre-processing of simulations. This paper presents a modeling method and corresponding algorithm to model heat source using measured DLPD. This algorithm automatically processes original data to get modeling parameters and provides a step MHS combining with absorption models. Simulations and experiments of heat transfer in steel plates irradiated by laser prove the mothed and the step MHS. Moreover, the investigations of laser induced thermal-crack propagation in glass highlight the signification of modeling heat source based on actual DLPD and demonstrate the enormous application of this method in the simulation of laser processing.

关键词： heat source laser processing distribution of power density digital images processing heat transfer

来源：评论

学校读者我要写书评

暂无评论

New Software Bionic Haptic Actuator Design Based on Barometric Array

New Software Bionic Haptic Actuator Design Based on Baromet...

引用

International Conference on Applied Nonlinear Dynamics, Vibration, and Control, ICANDVC 2023

作者： Yu, Zige Li, Sai Lin, Mengying Hu, Hang Li, Yingying Lei, Qian Huang, Zixin School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan430205 China Hubei Key Laboratory of Digital Textile Equipment Wuhan Textile University Wuhan430200 China Institute of Robotics and Automatic Information Systems College of Artificial Intelligence Nankai University Tianjin300350 China

ISBN: (纸本)9789819705535

To address the limitations of single-point tactile perception in soft biomimetic actuators, such as fixed positioning, limited coverage area, low resolution at long distances from the geometric center, and challenges in maintaining high sensitivity and stability over a broad range, a novel soft biomimetic tactile actuator based on a pneumatic array is designed and manufactured. Using liquid silicone rubber and BMP280 pressure sensor, the actuator was crafted by an injection molding process. Silicone gel was injected into the pressure sensor array, and vacuum extraction created a sealed space within the sensor cavity. The pressure excitation applied on the surface of the actuator could be converted into electrical signals, enabling tactile pressure detection. An STM32 microprocessor is utilized for building haptic information acquisition and processing system, with sensitivity assessed using the Kalman filter algorithm. Experimental results show that the soft biomimetic tactile actuator has high sensitivity and minimal repetition error, which can effectively detects changes in tactile force output, mitigates noise interference, and enhances the precision and stability of physiological pressure data feedback in physiotherapy applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Bionics

来源：评论

学校读者我要写书评

暂无评论

The Collection of a Human Robot Collaboration Dataset for Cooperative Assembly in Glovebox Environments

arXiv

引用

arXiv 2024年

作者： Sharma, Shivansh Huang, Mathew Nair, Sanat Wen, Alan Petlowany, Christina Moore, Juston Wanna, Selma Pryor, Mitch Nuclear and Applied Robotics Group Department of Mechanical Engineering Advanced Research in Cyber Systems Los Alamos National Laboratory United States

Industry 4.0 introduced AI as a transformative solution for modernizing manufacturing processes. Its successor, Industry 5.0, envisions humans as collaborators and experts guiding these AI-driven manufacturing solutions. Developing these techniques necessitates algorithms capable of safe, real-time identification of human positions in a scene, particularly their hands, during collaborative assembly. Although substantial efforts have curated datasets for hand segmentation, most focus on residential or commercial domains. Existing datasets targeting industrial settings predominantly rely on synthetic data, which we demonstrate does not effectively transfer to real-world operations. Moreover, these datasets lack uncertainty estimations critical for safe collaboration. Addressing these gaps, we present HAGS: Hand and Glove Segmentation Dataset. This dataset provides challenging examples to build applications toward hand and glove segmentation in industrial human-robot collaboration scenarios as well as assess out-of-distribution images, constructed via green screen augmentations, to determine ML-classifier robustness. We study state-of-the-art, real-time segmentation models to evaluate existing methods. Our dataset and baselines are publicly available. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Development of Autonomous Underwater Robot for Navigation through Narrow Passages

Development of Autonomous Underwater Robot for Navigation th...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Luo, Yang Zhu, Xiyu Zhou, Yuchuan Li, You Xu, Zhihui Wei, Yan Ke, Wende Hu, Chengzhi Southern University of Science and Technology Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy Engineering Shenzhen518055 China Southern University of Science and Technology Guangdong Prov. Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Shenzhen518055 China

ISBN: (纸本)9781665481090

Autonomous Underwater Vehicle (AUV), also called autonomous underwater robot, refers to an underwater robot that can independently complete tasks such as autonomous navigation, autonomous obstacle avoidance, and autonomous operation without human intervention. In some complex and narrow detection scenarios, autonomous underwater robots need to have a small volume, a high level of autonomy, and good maneuverability. Here, we design a miniature autonomous underwater robot driven by propellers, which integrates a high-performance processor, camera module, high-precision inertial measurement unit (IMU), etc. The attitude and position information of the robot is obtained in real-time through the IMU, and the processor controls the motion state of the six propellers, achieving the motion in six degrees of freedom in space. The highly integrated design ensures the maximum length of the whole machine within 15 cm, the 3-way PID controller design ensures an efficient and stable attitude control, and the high-performance processor provides more possibilities for target tracking and recognition. The developed AUV in this study shows superior navigation performance through narrow passages. © 2022 IEEE.

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

Acquiring feedback into the manufacturing process design from Industrial policies

引用

Procedia CIRP 2024年 128卷 579-584页

作者： Alexios Papacharalampopoulos Manolis Toupalis Panagiotis Lagios Olga Maria Karagianni Panagiotis Stavropoulos Laboratory for Manufacturing Systems and Automation (LMS) Department of Mechanical Engineering and Aeronautics University of Patras Rio Patras 26504 Greece Gizelis Robotics Schimatari Viotias 32009 Kormatzini Area Greece

The regulatory and social framework of European industry can be demanding, i.e. in terms of achieving different strategies, such as Industry 4.0 and Industry 5.0. To study this co-existence of strategies, a circular cell is utilized herein. It has been implemented based on a specific design, meeting requirements for an automotive microfactory and under the concept of circular economy. The objective of the cell has been to address resources efficiency and partial digitalization of workflows towards human-in-the-loop remanufacturing parts of electric vehicles. The process chain includes removal and joining processes, the processed part has been of medium complexity, and the workflow has engaged several digital tools, as a result of the quality monitoring requirements. The cell has been operational and various qualitative metrics have been elaborated. Subsequently, feedback is extracted towards the design for future applications pertaining to both circular economy and Industry 5.0. As such, in addition to the environmental sustainability implied by the resources efficiency, the production resilience and the human-centricity of the jobs involved are also regarded as extra requirements. Also, the connection to the ecosystem is taken into consideration. Finally, guidelines for future designs are also extracted.

关键词： Manufacturing process Cell Industry 5.0 application design criteria

来源：评论

学校读者我要写书评

暂无评论

On the Machining of Aluminum Alloy Series 7 with EDM 1

引用

7th International Scientific-Technical Conference, MANUFACTURING 2022

作者： Balanou, Maria Karmiris-Obratański, Panagiotis Karkalos, Nikolaos E. Papazoglou, Emmanouil L. Markopoulos, Angelos P. School of Mechanical Engineering Laboratory of Manufacturing Technology National Technical University of Athens Athens Greece Faculty of Mechanical Engineering and Robotics Department of Manufacturing Systems AGH University of Science and Technology Cracow Poland

ISBN: (数字)9783031008054

ISBN: (纸本)9783031008047

Electrical Discharge Machining is a thermo-electrical non-conventional machining process, which is widely used in machining difficult-to-cut materials in complex shapes and geometries, regardless their mechanical properties. Aluminum series 7 alloys are the strongest wrought aluminum alloy with extensive utilization in numerous modern applications. In the current study, an experimental investigation of machining Al7075 with EDM and brass electrode is presented. Full-scale experiments were conducted, with control parameters the pulse-on current and the pulse-on time, while, as the machining performance indexes, the Material Removal Rate (MRR), and the Tool Material Removal Rate (TMRR) were chosen and Surface Roughness (SR) was estimated in terms of the maximum roughness Rz and the average surface roughness Ra. Finally, a statistical analysis was followed in order to assess how each machining parameter affects the machining results. © 2022, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Aluminum alloy ANOVA Electrical discharge machining

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：