检索结果-内蒙古大学图书馆

Ultrafast Miniature Robotic Swimmers with Upstream Motility

Cyborg and Bionic Systems 2023年第1期4卷 452-459页

作者： Yibin Wang Hui Chen Junhui Law Xingzhou Du Jiangfan Yu School of Science and Engineering The Chinese University of Hong KongShenzhenChina ShenzhenInstitute of Artificial Intelligence and Robotics for Society ShenzhenChina Department of Mechanical and Industrial Engineering University of TorontoTorontoCanada

With the development of materials science and micro-nano fabrication techniques,miniature soft robots at millimeter or submillimeter size can be manufactured and actuated *** small-scaled robots have the unique capability to access hard-to-reach regions in the human body in a noninvasive *** date,it is still challenging for miniature robots to accurately move in the diverse and dynamic environments in the human body(e.g.,in blood flow).To effectively locomote in the vascular system,miniature swimmers with upstream swimming capability are ***,we design and fabricate a miniature robotic swimmer capable of performing ultrafast swimming in a fluidic *** maximum velocity of the swimmer in water is 30 cm/s,which is 60 body ***,in a tubular environment,the swimmer can still obtain a swimming velocity of 17 cm/*** swimmer can also perform upstream swimming in a tubular environment with a velocity of 5 cm/s when the flow speed is 10 cm/*** ultrasound-guided navigation of the swimmer in a phantom mimicking a blood vessel is also *** work gives insight into the design of agile undulatory milliswimmers for future biomedical applications.

关键词： millimeter upstream environments

来源：评论

学校读者我要写书评

暂无评论

Hand Gestures and Machine Learning: A Novel Path to Number Prediction

Hand Gestures and Machine Learning: A Novel Path to Number P...

引用

2023 International Conference on Recent Advances in Science and Engineering Technology, ICRASET 2023

作者： Karegoudra, Shilpa Veeresha, R.K. Department of Computer Science and Engineering Udupi574110 India Department of Robotics and Artificial Intelligence Udupi574110 India

ISBN: (纸本)9798350306927

The gesture-based communication system proves highly valuable for individuals who are almost deaf and discourse disabled. It allows them to convey messages effectively through gestures. The objective of this application is to provide a platform that accurately interprets these signs, enabling regular individuals to understand the gestures. The system detects and recognizes the gestures and displays the corresponding characters. This technology, which utilizes the PCA method, achieves comparable accuracy to other existing systems and methods. The system we have developed plays a crucial role in enabling individuals to understand and communicate like normal people using static gestures. While various proposals exist for gesture systems with specific languages like ASL, ISL, etc., we introduce a new set of static gestures using MATLAB, building upon existing systems. The system involves capturing input through a camera, after which the system applies preprocessing techniques to enhance the captured image. Next, a set of features is extracted from the preprocessed image using PCA (Principal Component Analysis). To identify the gestures, the system compares these features with those in the training sets, using the Euclidean Distance method. Our hand gesture system has been designed to recognize and interpret numbers from 0 to 5. Once a gesture is identified, the system can produce the output in the form of text ensuring effective communication for the users. © 2023 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Next View Planning Policy for Autonomous 3D Reconstruction of Unknown Environments 8

Next View Planning Policy for Autonomous 3D Reconstruction o...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Han, Haoyi Li, Shuai Chen, Jiemin Lin, Qing Chen, Quanjie Wang, Zhan Zhejiang Energy Digital Technology Co. Ltd Department of Artificial Intelligence and Robotics Hangzhou China

ISBN: (纸本)9798350302455

This paper mainly discusses the problem of next-scan view planning for autonomous scanning of 3D cameras in unknown environments. Based on the fact that the weight of adjacent voxel of boundary hole equals to zero in the truncated distance function (TSDF) model, a boundary extraction algorithm based on TSDF volume is firstly proposed. The boundary point cloud is then divided into multiple clusters by using the edge point elimination and DBSCAN clustering. The connection between boundary point cloud and camera frame is established by creating the centroid frames of point cloud clusters which points to current camera frame. The next scanning poses are finally proposed by using the Rodriguez formula to rotate the current camera frame around the centroid frame. The simulation experiment on the public dataset is conducted and the rendered image of current and final 3D model in transformed camera perspective is compared, verifying the point cloud completion on target object and proving the feasibility of the planning strategy proposed in this paper. © 2023 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Shaving Aided Interval Constraint Propagation for Guaranteed Landmark Estimation 8

Shaving Aided Interval Constraint Propagation for Guaranteed...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Wang, Zhan Lu, Ding Chen, Jiemin Zhang, Yingchi Yu, Rongdong Meng, Yuwei Zhejiang Energy Digital Technology Co. Ltd Department of Artificial Intelligence and Robotics Hangzhou China

ISBN: (纸本)9798350302455

Landmark depth estimation is a key step in simultaneous localization and mapping (SLAM) algorithm. Recently, interval analysis-based methods have aroused increasing interests from researchers due to its capability of providing guaranteed solution. However, they cannot contract the infinite depth uncertainty in some scenarios when applying local consistent interval constraint propagation (ICP) algorithm. To solve this problem, this paper proposes a shaving aided ICP (SICP) algorithm for guaranteed landmark depth uncertainty contraction. The principle of proposed SICP is to determine the upper and lower bounds of depth uncertainty by recursively calling a local consistent ICP algorithm on the sub-slices of the initial domain and removing those which are contradict to the constraints generated by the observation model. As a result, the landmark uncertainty is efficiently contracted without losing any feasible value. The numerical results show that the infinite depth uncertainty can be directly contracted by our proposed SICP algorithm and achieved better estimation (contraction) than normal ICP algorithm in 4 certain observation cases, showing the potential application of the proposed algorithm in SLAM algorithm. © 2023 IEEE.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

Research on Transformer Partial Discharge Localization Based on Residual Neural Network Model 43

Research on Transformer Partial Discharge Localization Based...

引用

43rd Chinese Control Conference, CCC 2024

作者： Li, Shilong Li, Ang Zhang, Jianlei Zhang, Chunyan Nankai University College of Artificial Intelligence Department of Automation Tianjin300071 China Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin300071 China Nankai University College of Artificial Intelligence Tianjin China

ISBN: (纸本)9789887581581

In the monitoring of electrical insulation, the detection of partial discharge (PD) activity is crucial to ensure the uninterrupted operation of power systems. The occurrence of PD is closely related to the weakening of insulation strength, and a failure to inspect PD occurrences may lead to unforeseen insulation breakdowns. A comprehensive PD diagnostic process involves the detection, localization, and classification of PD. Accurate localization of the source of partial discharge is essential for identifying weakened insulation segments. The conventional method for localization is based on the Time Difference of Arrival (TDOA), which is highly sensitive to delay estimation and often computationally intensive. Here we propose a data-driven approach based on a residual neural network model. It utilizes CST electromagnetic simulation software to simulate real-sized transformers and employs ultra-high-frequency sensors to measure field strength intensity as the network input. The output corresponds to the coordinates of the PD source and is used for network training. Simulation results demonstrate that this method exhibits high localization accuracy and efficiency. Moreover, different network models and datasets are considered for their influence on localization results, setting the groundwork for a more reliable PD source localization. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Partial discharges

来源：评论

学校读者我要写书评

暂无评论

Thin and Flexible Breeze-Sense Generators for Non-Contact Haptic Feedback in Virtual Reality

引用

Nano-Micro Letters 2025年第6期17卷 397-410页

作者： Kaijun Zhang Zhe Liu Yexi Zhou Zhaoyang Li Dazhe Zhao Xiao Guan Tianjun Lan Yanting Gong Bingpu Zhou Junwen Zhong Department of Electromechanical Engineering and Centre for Artificial Intelligence and Robotics University of MacaoMacao SAR 999078People’s Republic of China Joint Key Laboratory of the Ministry of Education Institute of Applied Physics and Materials EngineeringUniversity of MacaoMacao SAR 999078People’s Republic of China

In the realm of virtual reality(VR),haptic feedback is integral to enhance the immersive experience;yet,existing wearable devices predominantly rely on skin contact feedback,lacking options for compact and non-contact breeze-sense ***,we propose a compact and non-contact working model piezoelectret actuator for providing a gentle and safe breeze *** easy-fabricated and flexible breeze-sense generator with thickness around 1 mm generates air flow pressure up to~163 Pa,which is significantly sensed by human *** a typical demonstration,the breeze-sense generators array showcases its versatility by employing multiple coded modes for non-contact information *** thin thinness and good flexibility facilitate seamless integration with wearable VR setups,and the wearable arrays empower volunteers to precisely perceive the continuous and sudden breeze senses in the virtual *** work is expected to inspire developing new haptic feedback devices that play pivotal roles in human-machine interfaces for VR applications.

关键词： Virtual reality Wearable electronics Non-contact haptic feedback Breeze-sense Piezoelectret actuator

来源：评论

学校读者我要写书评

暂无评论

Kinematic Synthesis and Design of a Five Fingered Hand Exoskeleton 5th

Kinematic Synthesis and Design of a Five Fingered Hand Exosk...

引用

5th International and 20th National Conference on Machines and Mechanisms, iNaCoMM 2021

作者： Sarmah, Nilavjyoti Hazarika, Shyamanta M. Biomimetic Robotics and Artificial Intelligence Lab Department of Mechanical Engineering IIT Guwahati Guwahati781039 India

ISBN: (纸本)9789811937156

This paper outlines a method to design an underactuated, linkage-based hand exoskeleton.A planar 8-link mechanism with phalanges and articulations as part of the kinematic chain is used for each *** links are attached to the proximal and distal *** the thumb, a planar 6-link mechanism directly connected at the distal phalanx is *** kinematic synthesis of the mechanism based on Burmester Theory was performed with two principal considerations: *** obtain link lengths that ensured no mechanical interference between the mechanisms and the hand and *** mechanism ensured that each finger follows the natural *** mechanism is evaluated by comparing the workspace of the anatomical index finger with that of the hand exoskeleton assisted finger. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Design

来源：评论

学校读者我要写书评

暂无评论

Design and Fabrication of an Eco-Friendly Remote controlled Fish Catching Bot for Coastal Fishing

Design and Fabrication of an Eco-Friendly Remote controlled ...

引用

2024 IEEE International Conference on Recent Advances in Science and Engineering Technology, ICRASET 2024

作者： Dsouza, Vincent Linish Sherigar, Anurag R. Poojary, Avish N. Bangera, Dheeraj M. Harshith, Kumar S. Hemaraju Department of Robotics & Artificial Intelligence Nitte India Department of Mechanical Engineering Nitte India Adichunchangiri University Bgsit Department of Mechanical Engineering BG Nagara India

ISBN: (纸本)9798350388602

This research presents the design and fabrication of an eco-friendly, remote-controlled fish-catching bot for coastal fishing, aimed at minimizing ecological impacts while ensuring efficient operation. Conventional fishing techniques often harm non-target aquatic species and involve non-selective fishing practices. In contrast, the fish-catching bot developed in this study aims to minimize these issues by selectively capturing fish without causing physical harm, allowing them to be kept alive for extended periods. This feature makes the device suitable for research, recreational fishing, and bulk capture while ensuring the well-being of the fish. Additionally, the bot is designed to reduce the human risks associated with fishing in unpredictable and harsh weather conditions. A key challenge in the design process was mitigating the sensitivity of fish to external vibrations. To address this, the bot was engineered to operate with minimal noise and vibration, with motors selectively driven to reduce disturbance. The fish-catching bot has been successfully designed, fabricated, and tested in aquatic environments demonstrating its viability for sustainable fishing. © 2024 IEEE.

关键词： Fishing (oil wells)

来源：评论

学校读者我要写书评

暂无评论

A Novel Actuation Mechanism for High-Bandwidth Bidirectional Rotation of Cable-Driven Revolute Joints 16th

A Novel Actuation Mechanism for High-Bandwidth Bidirectiona...

引用

16th International Federation of Theory of Machines and Mechanisms World Congress, IFToMM WC 2023

作者： Zhou, Zhihao Zhao, Zihang Ruan, Lecheng Wang, Qining The Institute for Artificial Intelligence Peking University Beijing100871 China The National Key Laboratory of General Artificial Intelligence Beijing100080 China The Department of Advanced Manufacturing and Robotics College of Engineering Peking University Beijing100871 China

ISBN: (纸本)9783031457081

In recent years, cable-driven revolute joints have been successfully applied in various robotic fields. However, two major concerns remain unsolved. (i) The pull-only characteristic of cable requires additional actuators or a passive low-bandwidth resetting mechanism for bidirectional rotation. (ii) The actuation performance is constrained by the nonlinear relationship between the rotations of the revolute joint and the motor. This paper proposes a general actuation mechanism for a large group of cable-driven revolute joints of various shapes and sizes. A pulley with two separate non-circular tracks, which can retract and release two-side cables simultaneously and independently, is designed to achieve high-bandwidth bidirectional rotation with only one motor while creating a linear relationship between the joint and motor rotations. The profile of the pulley track is depicted with differential equations and the calculation process facilitates revolute joints of various symmetric or asymmetric configurations. The design is verified by the simulation with a numerical example of real-world parameters. Results show the advantages of the proposed mechanism in contrast with the conventional pulley with a circular track profile on both concerns. This mechanism can potentially enlarge the application of cable-driven revolute joints with space and payload limitations, in addition to the requirements of highly dynamic performance. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Rotation

来源：评论

学校读者我要写书评

暂无评论

Exploiting autoencoder’s weakness to generate pseudo anomalies

引用

Neural Computing and Applications 2024年第23期36卷 14075-14091页

作者： Astrid, Marcella Zaheer, Muhammad Zaigham Aouada, Djamila Lee, Seung-Ik Department of Artificial Intelligence University of Science and Technology Daejeon34113 Korea Republic of Field Robotics Research Section Electronics and Telecommunications Research Institute Daejeon34129 Korea Republic of Interdisciplinary Centre for Security Reliability and Trust University of Luxembourg Luxembourg1855 Luxembourg Department of Computer Vision Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

Due to the rare occurrence of anomalous events, a typical approach to anomaly detection is to train an autoencoder (AE) with normal data only so that it learns the patterns or representations of the normal training data. At test time, the trained AE is expected to well reconstruct normal but to poorly reconstruct anomalous data. However, contrary to the expectation, anomalous data are often well reconstructed as well. In order to further separate the reconstruction quality between normal and anomalous data, we propose creating pseudo anomalies from learned adaptive noise by exploiting the aforementioned weakness of AE, i.e., reconstructing anomalies too well. The generated noise is added to the normal data to create pseudo anomalies. Extensive experiments on Ped2, Avenue, ShanghaiTech, CIFAR-10, and KDDCUP datasets demonstrate the effectiveness and generic applicability of our approach in improving the discriminative capability of AEs for anomaly detection. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Anomaly detection

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：