检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Sautenkov, Oleg Asfaw, Selamawit Yaqoot, Yasheerah Mustafa, Muhammad Ahsan Fedoseev, Aleksey Trinitatova, Daria Tsetserukou, Dzmitry Intelligent Space Robotics Laboratory Center for Digital Engineering Skolkovo Institute of Science and Technology Russia

The swift advancement of unmanned aerial vehicle (UAV) technologies necessitates new standards for developing human-drone interaction (HDI) interfaces. Most interfaces for HDI, especially first-person view (FPV) goggles, limit the operator’s ability to obtain information from the environment. This paper presents a novel interface, FlightAR, that integrates augmented reality (AR) overlays of UAV first-person view (FPV) and bottom camera feeds with head-mounted display (HMD) to enhance the pilot’s situational awareness. Using FlightAR, the system provides pilots not only with a video stream from several UAV cameras simultaneously, but also the ability to observe their surroundings in real time. User evaluation with NASA-TLX and UEQ surveys showed low physical demand (µ = 1.8, SD = 0.8) and good performance (µ = 3.4, SD = 0.8), proving better user assessments in comparison with baseline FPV goggles. Participants also rated the system highly for stimulation (µ = 2.35, SD = 0.9), novelty (µ = 2.1, SD = 0.9) and attractiveness (µ = 1.97, SD = 1), indicating positive user experiences. These results demonstrate the potential of the system to improve UAV piloting experience through enhanced situational awareness and intuitive control. The code is available here: https://***/Sautenich/FlightAR © 2024, CC BY-NC-ND.

关键词： Helmet mounted displays

来源：评论

学校读者我要写书评

暂无评论

Design and Cold Test of a Mode-Suppression Circuit for the G-Band Gyro-TWT

Design and Cold Test of a Mode-Suppression Circuit for the G...

引用

International Conference on Vacuum Electronics

作者： Yingjian Cao Guo Liu Yuan Ma Yu Wang Weijie Wang Wei Jiang Yelei Yau Jianxun Wang Yong Luo University of Electronic Science and Technology of China Chengdu China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing China

In this paper, the design and measurement of a mode-suppression circuit used in the nonlinear interaction region for a G-band gyrotron travelling wave tube (gyro-TWT) are presented. By achieving sufficient coupling losses, this circuit can effectively suppress the parasitic oscillations without affecting the operating mode, thus improving the tube stability during high power operation. The measured results agree well with the simulated results, which can provide a loss of 5.6 dB/cm to suppress the backward-wave oscillation (BWO) of the TE21 mode. This proves that the circuit can be used as a new scheme for gyro- TWTs to achieve high stability and high power.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Signal Detector for OFDM Systems

引用

China Communications 2023年第12期20卷 66-77页

作者： Guangliang Pan Wei Wang Minglei Li Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information TechnologyCollege of Electronic and Information EngineeringNanjing University of Aeronautics and AstronauticsNanjing 211106China College of Control Science and Engineering China University of Petroleum(East China)Qingdao 266580China

In this paper,we propose a novel deep learning(DL)-based receiver design for orthogonal frequency division multiplexing(OFDM)*** entire process of channel estimation,equalization,and signal detection is replaced by a neural network(NN),and hence,the detector is called a NN detector(N^(2)D).First,an OFDM signal model is *** analyze both temporal and spectral characteristics of OFDM signals,which are the motivation for ***,the generated data based on the simulation of channel statistics is used for offline training of bi-directional long short-term memory(Bi-LSTM)***,a discriminator(F)is added to the input of Bi-LSTM NN to look for subcarrier transmission data with optimal channel gain(OCG),which can greatly improve the performance of the ***,the trained N^(2)D is used for online recovery of OFDM *** performance of the proposed N^(2)D is analyzed theoretically in terms of bit error rate(BER)by Monte Carlo simulation under different parameter *** simulation results demonstrate that the BER of N^(2)D is obviously lower than other algorithms,especially at high signal-to-noise ratios(SNRs).Meanwhile,the proposed N^(2)D is robust to the fluctuation of parameter values.

关键词： channel estimation deep learning OFDM optimal channel gain signal detection

来源：评论

学校读者我要写书评

暂无评论

Predefined-time prescribed performance guidance law design against maneuvering target under input saturation 2

Predefined-time prescribed performance guidance law design a...

引用

2023 2nd International Conference on Aerospace and control Engineering, ICoACE 2023

作者： Wei, Zhenyan Li, Jianfeng You, Weishuai Song, Shenmin Shi, Xiaoping Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Institute of Mechanical and Electrical Engineering Beijing100072 China School of Astronautics Harbin Institute of Technology No. 92 West Dazhi Street Nangang District Harbin150001 China

A novel SMC-based prescribed performance guidance law combined with a base generator (TBG) is proposed. A TBG-based modified Lyapunov function is first proposed, which ensures that the LOS tracking error converges into zero within a predefined time. A novel sliding manifold with adjusting convergent time property is proposed, which brings about a smaller control magnitude and predefined time convergent rate. To ensure a satisfied transit and steady performance, some converted variables are defined based on which a novel prescribed performance guidance law is constructed. The input saturation problem is properly solved by designing a novel TBG-based one-order auxiliary system. Extensive simulation results have verified the effectiveness of the proposed method. © Published under licence by IOP Publishing Ltd.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Secure Beamforming Design for IRS-ISAC Systems with a Hardware-Efficient Hybrid Beamforming Architecture

引用

IEEE Transactions on Vehicular technology 2025年

作者： Xiong, Weijie Zhao, Zhenglan Lin, Jingran Xiao, Zhiling Li, Qiang University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing100083 China Tianfu Jiangxi Laboratory Sichuan Chengdu641419 China

In this paper, we employ a hardware-efficient hybrid beamforming (HB) architecture to achieve balanced performance in an intelligent reflecting surface (IRS)-assisted integrated sensing and communication (ISAC) system. We consider a scenario where a multi-antenna, dual-function base station (BS) performs secure beamforming for a multi-antenna legitimate receiver while simultaneously detecting potential targets. Our objective is to maximize the communication secrecy gap by jointly optimizing the analog and digital beamformers, IRS reflection coefficients, and radar scaling factor, subject to constraints on beampattern similarity, total transmit power budget, and the constant modulus of both the analog beamformer and IRS reflection coefficients. This secrecy gap maximization problem is generally non-convex. To address this, we incorporate the exterior penalty method by adding the radar constraint as a penalty term in the objective function. We then propose an efficient approach based on the penalty dual decomposition (PDD) framework to solve the reformulated problem, featuring closed-form solutions at each step and guaranteeing convergence to a stationary point. Simulation results validate the effectiveness of the proposed algorithm and demonstrate the superiority of the IRS-ISAC system with HB architecture in balancing performance and hardware costs. © 1967-2012 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Combined active and passive adaptive variable admittance compliant control for space robotic manipulators

Combined active and passive adaptive variable admittance com...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Gao, Hang Zhang, Xiaodong Ma, Chao Zhou, Cheng University of Science and Technology Beijing School of Mechanical Engineering Beijing100083 China Beijing Institute of Spacecraft System Engineering Cast Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Application China

ISBN: (纸本)9798350325706

This paper develops a combined active and passive adaptive variable admittance compliant control algorithm for space robotic manipulators. In fact, the assembly task for space robots requires compliance and precision while ensuring avoidance of any occurrences of rigid collision throughout the process. Therefore, we design a new combined active and passive variable admittance control structure combined with the following three parts to meet these acquirements. Firstly, we develop an active variable admittance algorithm to facilitate the space robot rapid movement, enabling it to achieve higher speeds while maintaining compliance. Then, to mitigate the occurrence of unforeseen rigid collisions during the robot motion, we devise a passive variable admittance control algorithm, which aims to minimize the impact of collision events and ensure the robot safe operation. Furthermore, by employing the Lyapunov theory, a new active adaptive variable admittance control algorithm is presented for robot constant force output. Consequently, through contrast experiments, we demonstrate the effectiveness and enhanced performance of the proposed algorithm. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unifying Visual and Vision-Language Tracking via Contrastive Learning

arXiv

引用

arXiv 2024年

作者： Ma, Yinchao Tang, Yuyang Yang, Wenfei Zhang, Tianzhu Zhang, Jinpeng Kang, Mengxue Deep Space Exploration Laboratory School of Information Science and Technology University of Science and Technology of China China Intelligent Science Technology Academy of CASIC China

Single object tracking aims to locate the target object in a video sequence according to the state specified by different modal references, including the initial bounding box (BBOX), natural language (NL), or both (NL+BBOX). Due to the gap between different modalities, most existing trackers are designed for single or partial of these reference settings and overspecialize on the specific modality. Differently, we present a unified tracker called UVLTrack, which can simultaneously handle all three reference settings (BBOX, NL, NL+BBOX) with the same parameters. The proposed UVLTrack enjoys several merits. First, we design a modality-unified feature extractor for joint visual and language feature learning and propose a multi-modal contrastive loss to align the visual and language features into a unified semantic space. Second, a modality-adaptive box head is proposed, which makes full use of the target reference to mine ever-changing scenario features dynamically from video contexts and distinguish the target in a contrastive way, enabling robust performance in different reference settings. Extensive experimental results demonstrate that UVLTrack achieves promising performance on seven visual tracking datasets, three vision-language tracking datasets, and three visual grounding datasets. Codes and models will be open-sourced at https://***/OpenspaceAI/UVLTrack. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Design of Multi-target Tracking Algorithm Based on Multi-sensor Fusion 3rd

Design of Multi-target Tracking Algorithm Based on Multi-sen...

引用

3rd International Conference on Artificial Intelligence, 2022

作者： Song, Zhangchi Qiang, Xiaomin Sun, Peng Cao, Laitian Zhang, Lijia Yang, Baisheng Beijing Aerospace Automatic Control Institute Beijing100854 China National Key Laboratory of Science and Technology on Aerospace Intelligent Control Beijing100854 China

ISBN: (纸本)9789811694226

In the modern battlefield environment, the traditional single sensor often cannot give full play to its optimal performance. The advantages of different sensors are used for combined detection and tracking to obtain all-round multi-dimensional information of the target. Through multi-sensor fusion processing, interference is eliminated, and the target state estimation is obtained to achieve precise positioning of the target. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Feature Selection with self-Weighted and 2,0-Norm Constraint 48

Unsupervised Feature Selection with self-Weighted and 2,0-No...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Yuan, Yongjin Wang, Zheng Nie, Feiping Li, Xuelong Northwestern Polytechnical University School of Computer Science Xi'an710072 China Xi'an710072 China Science and Technology on Electromechanical Dynamic Control Laboratory China Ministry of Industry and Information Technology Key Laboratory of Intelligent Interaction and Applications Northwestern Polytechnical University Xi'an710072 China

ISBN: (纸本)9781728163277

At data mining field, it is a fundamental problem to dispose of high-dimensional data. Many existing unsupervised methods select features by manifold learning or exploring spectral analysis, thus preserving the intrinsic structure of raw data. But most of them follow an assumption that all features are equally importance. To settle this problem, we draw a novel feature selection module that simultaneously performs learning of feature weights matrix, similarity graph structure and projection matrix, so that the local structure after feature weighting and subspace sparse projection is received. Finally, we solve the model based on 2,0-norm directly by an iterative optimization algorithm and demonstrate the feasibility and effectiveness of our approach via extensive experiments. © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

A piezoresistive-based 3-axial MEMS tactile sensor and integrated surgical forceps for gastrointestinal endoscopic minimally invasive surgery

引用

Microsystems & Nanoengineering 2024年第5期10卷 71-83页

作者： Cheng Hou Huxin Gao Xiaoxiao Yang Guangming Xue Xiuli Zuo Yanqing Li Dongsheng Li Bo Lu Hongliang Ren Huicong Liu Lining Sun School of Mechanical and Electrical Engineering Jiangsu Provincial Key Laboratory of Advanced RoboticsSoochow UniversitySuzhouChina Faculty of Mechanical and Electrical Engineering Kunming University of Science and TechnologyJingming South RoadKunmingChina Yunnan Key Laboratory of Intelligent Control and Application KunmingChina Department of Electronic Engineering The Chinese University of Hong Kong(CUHK)Hong KongChina. Department of Gastroenterology Qilu HospitalShandong UniversityJinanShandongChina

In robotic-assisted surgery(RAS),traditional surgical instruments without sensing capability cannot perceive accurate operational forces during the task,and such drawbacks can be largely intensified when sophisticated tasks involving flexible and slender arms with small end-effectors,such as in gastrointestinal endoscopic surgery(GES).In this study,we propose a microelectromechanical system(MEMS)piezoresistive 3-axial tactile sensor for GES forceps,which can intuitively provide surgeons with online force feedback during robotic *** MEMS fabrication process facilitates sensor chips with miniaturized *** fully encapsulated tactile sensors can be effortlessly integrated into miniature GES forceps,which feature a slender diameter of just 3.5 mm and undergo meticulous calibration procedures via the least squares *** experiments,the sensor's ability to accurately measure directional forces up to 1.2 N in the Z axis was validated,demonstrating an average relative error of only 1.18%compared with the full-scale *** results indicate that this tactile sensor can provide effective 3-axial force sensing during surgical operations,such as grasping and pulling,and in ex vivo testing with a porcine *** compact size,high precision,and integrability of the sensor establish solid foundations for clinical application in the operating theater.

关键词： axial surgery intensified

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：