检索结果-内蒙古大学图书馆

An Interactive Robot System Using Zero-shot Chain-of-thought Prompting

Journal of Institute of Control, robotics and Systems 2025年第6期31卷 629-635页

作者： Kim, Min-Jo Park, Kyu Min Department of Intelligent Mechatronics Engineering Sejong University Korea Republic of Department of Artificial Intelligence and Robotics Sejong University Korea Republic of

With advancements in generative AI, its integration with robotics is accelerating rapidly. In particular, the development of large language models (LLMs) presents new possibilities for facilitating effective human-robot interaction (HRI) in various fields. This paper proposes a natural language-based interaction system that integrates LLMs with robots, aiming to enhance human-robot communication. The system recognizes voice commands and employs the chain-of-thought (CoT) prompting to transform implicit or abbreviated human commands, which are natural language-based, into executable robot action (motion) sequences. Instead of using fine-tuning methods that require additional training of the model, this study adopts prompt engineering techniques to enhance system efficiency. Furthermore, our proposed system can adapt to various operational environments through zero-shot reasoning capabilities. Experimental results demonstrate that the proposed system achieves high task decomposition accuracy and interaction (executing the decomposed task) success rate of 88.8% and 85.8% respectively, validating the potential of LLMs in robot control systems. © ICROS 2025.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Evaluation of modal parameters and static characteristics for composite mono leaf spring

引用

Noise and Vibration Worldwide 2021年第3期52卷 33-47页

作者： Samir Mohamed Mohamed Soliman, Ehab Mechatronics and Robotics Department Faculty of Engineering Egyptian Russian University Badr CityCairo11829 Egypt

The objective of this paper was to investigate and evaluate modal parameters and static characteristics for designed carbon/epoxy composite CFRP leaf spring made from carbon ﬁber-reinforced epoxy by comparing its finite element analysis FEA modal, harmonic and static results to that of conventional steel one under the same maximum full bump load. In ANSYS software, finite element modal, harmonic and static analysis for 3D models of conventional steel and designed composite mono leaf springs is carried out. FEA displacements for the steel and designed composite CFRP mono leaf springs at the maximum full bump load were 92.9 mm and 93.1 mm respectively. Compared to the steel mono leaf spring, the composite mono leaf spring has advantages;lower stresses, higher natural frequencies and higher safety in stresses of front and rear eyes. All these advantages let the composite leaf spring can be carried maximum full bump load with enough higher performance over steel one to avoid resonance and satisfy maximum stress failure criterion. © The Author(s) 2020.

关键词： Carbon

来源：评论

学校读者我要写书评

暂无评论

Prediction of directivity characteristics of piezoelectric macro-fiber composite interdigital transducers: a semi-analytical approach

e-Journal of Nondestructive Testing

引用

e-Journal of Nondestructive Testing 2024年第7期29卷

作者： Raorane, Siddhesh Ambrozinski, Lukasz Stepinski, Tadeusz Packo, Pawel Department of Robotics and Mechatronics Faculty of Mechanical Engineering and Robotics AGH University of Science and Technology Krakow30-059 Poland

The employment of guided waves for structural health monitoring applications has attracted substantial attention in recent years. Piezoelectric transducers are frequently employed in these systems for elastic wave generation and acquisition. Their dynamic properties, i.e., direction-dependent frequency characteristics such as directivity patterns, are an important feature for designing a reliable monitoring strategy. Although analysis of the transducer directivity pattern can be performed using finite element models, these usually tend to be computationally very expensive, especially for parametric and optimization studies. In this paper, a semi-analytical framework is proposed that can predict the far-field directivity patterns of complex transducers of arbitrary shape and structure mounted on a substrate. The framework described in this paper integrates analytical far-field predictions with a local finite element model evaluating the traction field produced by the transducer. Consequently, the FE model accurately captures near-field responses, whereas the analytical component predicts the far-field responses. The implementation of this semi-analytical framework requires the development of analytical and numerical approaches. The former includes computation of dispersion curves of the inspected plate, the stress and displacement profiles of wave modes, and ultimately, the excitability relations, while the latter includes estimation of the traction field between the transducer and the plate using the FE model. Owing to the popularity of piezoelectric macro-fiber composite (MFC) transducers, in this paper, we apply the proposed method to predict the directivity patterns of MFC M2807-P2 transducer. To validate the reliability of the proposed method, the predicted patterns are compared with experimental results obtained using Laser Doppler Vibrometer. © 2024, NDT. net GmbH and Co. KG. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Motion Control for an 8-DOF Robotic Mobile Manipulator 19

Vision-Based Motion Control for an 8-DOF Robotic Mobile Mani...

引用

19th Annual IEEE International Systems Conference, SysCon 2025

作者： Li, Yunze Lang, Haoxiang Wang, Ying Ontario Tech University Department of Automotive and Mechatronics Engineering OshawaON Canada Kennesaw State University Department of Robotics and Mechatronics Engineering MariettaGA United States

ISBN: (纸本)9798331508180

This paper introduces a visual servoing control strategy designed for a vision-based robotic mobile manipulation system. The system continuously updates the motion of both the mobile base and its integrated manipulator by utilizing visual feedback from a stereo camera. A detailed description of the system components is provided, including the mobile robot, the robotic manipulator, and the stereo vision system, along with the design of a visual servoing controller grounded in Lyapunov's stability theory. The controller operates by adjusting the movements of the mobile base and manipulator to minimize the disparity between the current and desired pose, ultimately guiding the system to achieve the target position and orientation. To validate the kinematic model and assess the performance of the proposed control strategy, experiments were conducted using the Husky mobile robot in conjunction with a 6-DOF UR5 robotic manipulator. The results from these experiments substantiate the effectiveness and robustness of both the robot model and the implemented control law. These findings confirm the potential of the proposed system in achieving reliable and precise mobile manipulation tasks. © 2025 IEEE.

关键词： Visual servoing

来源：评论

学校读者我要写书评

暂无评论

High-Performance Admittance Control of An Industrial Robot Via Disturbance Observer 48

High-Performance Admittance Control of An Industrial Robot V...

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Samuel, Kangwagye Haninger, Kevin Oh, Sehoon Dgist Department of Robotics and Mechatronics Engineering Daegu Korea Republic of Fraunhofer Ipk Department of Automation Berlin Germany

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

Safe physical interaction using admittance control on an industrial robot with inner-loop motion control remains challenging. This is partly due to the low intrinsic admittance and stability issues from inner-loop motion control limitations (e.g. bandwidth). To increase the admittance at an interaction point with the user/environment, this paper proposes a robust admittance control architecture. A disturbance observer (DOB) is used to improve effective inner-loop motion control, suppressing the effects of velocity disturbances. The DOB uses the robot's closed-loop task space velocity control as the nominal model, compensating disturbances between the commanded robot velocity and realized robot velocity output. An admittance controller uses measured force to generate robot velocity commands. Detailed analyses are carried out to theoretically evaluate the proposed control system. Experiments conducted on a COMAU RACER-7-1.4 industrial robot verify the effectiveness of the proposed admittance control scheme and stability in environmental contact. Moreover, the proposed method is simple to implement on the existing robot system. © 2022 IEEE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Representing Objects in Map Building Using A Semantic SLAM Scheme

Representing Objects in Map Building Using A Semantic SLAM S...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Yang, Yu Wang, Di Zheng, Weiqi Shanghai University Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronics Engineering and Automation Shanghai China

ISBN: (纸本)9781665465335

In order to make the robot understand the scene better and the human-robot interaction more friendly, a lightweight semantic SLAM system is proposed in this paper. Our system uses a LIDAR combined with a camera to obtain object location in SLAM and determines object information such as category with a CNN-based object detector. The object identities are represented in the form of joint probability distributions that are updated by Bayes' theorem. The FPA algorithm is used to obtain parameter valuation with maximum posterior probability so as to determine the modeling feature parameters of objects on the map. The similarity between objects is measured with the Bhattacharyya coefficient to avoid duplicate modeling of identified objects in map updating. The proposed system is simulated in Gazebo and an effective scheme balancing accuracy and computation cost is obtained. Finally, experiments on a small indoor robot demonstrate the effectiveness of our method. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Minimalistic Soft Exosuit for Assisting the Shoulder via Biomechanics-Aware Optimization 21

Minimalistic Soft Exosuit for Assisting the Shoulder via Bio...

引用

2022 IEEE-RAS 21st International Conference on Humanoid Robots, Humanoids 2022

作者： Joshi, Sagar Beck, Irene Seth, Ajay Santina, Cosimo Della Mechanical Maritime and Materials Engineering Faculty TU Delft Delft Netherlands Robotics and Mechatronics Department Munich Germany

ISBN: (纸本)9798350309799

Soft exosuits can help to prevent work-related musculoskeletal disorders by offloading human muscles through the application of external forces across the human joints. Many exosuits achieve this through tension producing elements called as exotendons. However, the design of these devices is based on intuition and experience. This leads to potentially sub-optimal or even harmful designs that could cause discomfort or injury to the wearer. This paper deals with automatically finding appropriate attachments and routing locations for exotendons. We propose to do that by accurate musculoskeletal modeling and design parameter optimization of soft exosuits. We focus here on a soft exosuit with a single passive exotendon to assist the shoulder. Using three arm raising-lowering and internal-external rotation motions as examples, we optimize the attachment point and rest-length of the exotendon to reduce overall muscle effort. We then fabricate the exosuit and validate the model predictions by testing with six participants. Supporting the predictions from simulations, measured muscle activity shows reductions in the deltoid and trapezius muscles. This work represents the first instance of explicitly optimizing functional and geometric parameters of exotendons in wearable assistive devices for minimizing human effort. © 2022 IEEE.

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

Applying CNN Models with Stereo Camera for Object Detection and Distance Estimation in Automatic Micro Electric Vehicle (MEVi) 1

Applying CNN Models with Stereo Camera for Object Detection ...

引用

1st International Conference on Smart mechatronics, ICSMech 2024

作者： Harimanto, Farrell Putra Hasanah, Nurul Pradana, Muhammad Khristamto Aditya Puji, Muhammad Nurul Binus Aso School of Engineering Bina Nusantara University Automotive & Robotics Program Computer Engineering Department Jakarta11480 Indonesia National Research and Innovation Agency Kst Samaun Samadikun Research Center for Smart Mechatronics Bandung40135 Indonesia

ISBN: (纸本)9798350368918

Technological advancements in the automotive industry are currently focused on autonomous driving systems or driver assistance systems. Depth estimation is also an important feature of the autonomous driving system as it can accurately estimate the distance to the detected objects. In current developments technologies such as stereo cameras are more popular for a more accurate depth estimation. The process for object detection consists of a combination of classification, localization, and segmentation. Deep convolutional neural networks are the basis of object detection. The methods for object detection are divided into two categories namely the Region Proposal-based method such as RCNN, and the Classification-based method which provides for methods such as YOLO and MobileNet. As a part of the research conducted by the National Research and Innovation Agency (BRIN) on Automatic Micro Electric Vehicles or MEVi, this paper analyzed and compared the performance of several CNN models for object detection as well as the performance of depth sensing using ZED stereo camera which was used for the autonomous system in MEVi. Among several models that had been compared, YOLO v8 model demonstrates high accuracy and moderate speed as indicated by its high mAP (0.50) and FPS (38.46). Based on depth sensing results, the accuracy of distance measurement also depended on brightness and environment with the average of accuracy achieved indoors was 98.2% and outdoors was 96.3%. © 2024 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Optimum Design of a Wire-Driven Redundant Spherical Parallel Manipulator for Foot Drop Rehabilitation System 48

Optimum Design of a Wire-Driven Redundant Spherical Parallel...

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Gamal, Ahmed Mohamed, Abdelfatah Iwata, Hiroyasu Assal, Samy F. M. Department of Mechatronics and Robotics Engineering Egypt Waseda University Japan Tanta University Faculty of Engineering Department of Production Engineering and Mechanical Design Egypt

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

Post stroke patients may suffer from a gait disorder which is called foot drop. They may experience a toedrag, slow walking speed and a high risk of tripping. Although physical therapy exercises can be a remedy to such cases, their high cost and the lack of professional caregivers arise the need for robotic rehabilitation systems. On the other hand, the existing robotic systems for foot-drop rehabilitation are heavy and bulky. Therefore, in this paper, a lightweight foot-drop rehabilitation system based on a wire-driven redundant spherical parallel manipulator (RSPM) is developed. The proposed RSPM can provide 3-DOF movements to exercise the dorsiflexion, plantarflexion, supination, lateral and medial rotations. Kinematic and static analyses are performed for the proposed rob RSPM. In order to guarantee permissible positive tensions for the wires of the RSPM, a new performance index is introduced, called permissible tension index. Optimum design based on optimizing certain performance indices is carried out to obtain the proper dimensions of the movable platform design parameters of the proposed RSPM. A new index called permissible tension index is introduced to guarantee permissible positive tensions for the wires of the RSPM. A weighted sum of the global kinematic dexterity, global minimized transmission and the global permissible tension indices is considered for the objective function of the optimization process. The RSPM performance is evaluated over its range of motion and the reaction forces exerted on the ankle are shown to be tolerable by an injured ankle. Additionally, the Jacobian-based kinematic controller is shown to be capable of tracking the normal gait trajectories with acceptable tracking errors. © 2022 IEEE.

关键词： Kinematics

来源：评论

学校读者我要写书评

暂无评论

Advances of triboelectric and piezoelectric nanogenerators toward continuous monitoring and multimodal applications in the new era

引用

International Journal of Extreme Manufacturing 2025年第1期7卷 174-205页

作者： Jianlong Hong Xiao Wei Huiyun Zhang Yukun Xiao Chongguang Meng Yuqi Chen Jiahui Li Ling Li Sanghoon Lee Qiongfeng Shi Jun Wu Interdisciplinary Research Center School of Electronic Science and EngineeringSoutheast UniversityNanjing 211189People’s Republic of China Department of Robotics&Mechatronics Engineering Daegu Gyeongbuk Institute of Science&TechnologyDaegu 42899Republic of Korea

Benefiting from the widespread potential applications in the era of the Internet of Thing and metaverse,triboelectric and piezoelectric nanogenerators(TENG&PENG)have attracted considerably increasing *** outstanding characteristics,such as self-powered ability,high output performance,integration compatibility,cost-effectiveness,simple configurations,and versatile operation modes,could effectively expand the lifetime of vastly distributed wearable,implantable,and environmental devices,eventually achieving self-sustainable,maintenance-free,and reliable ***,current triboelectric/piezoelectric based active(***-powered)sensors still encounter serious bottlenecks in continuous monitoring and multimodal applications due to their intrinsic limitations of monomodal kinetic response and discontinuous transient *** work systematically summarizes and evaluates the recent research endeavors to address the above challenges,with detailed discussions on the challenge origins,designing strategies,device performance,and corresponding diverse ***,conclusions and outlook regarding the research gap in self-powered continuous multimodal monitoring systems are provided,proposing the necessity of future research development in this field.

关键词： triboelectric piezoelectric continuous monitoring multimodal sensing internet of thing

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：