检索结果-内蒙古大学图书馆

DNN Task Assignment in UAV Networks: A Generative AI Enhanced Multi-Agent Reinforcement Learning Approach

IEEE Internet of Things Journal 2025年第10期12卷 13340-13352页

作者： Tang, Xin Chen, Qian Weng, Wenjie Liao, Binhan Wang, Jiacheng Cao, Xianbin Li, Xiaohuan Guilin University of Electronic Technology Guangxi University Key Laboratory of Intelligent Networking and Scenario System School of Information and Communication Guilin541004 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Guilin University of Electronic Technology School of Architecture and Transportation Engineering Guilin541004 China Nanning530001 China Beihang University School of Electronic and Information Engineering Key Laboratory of Advanced Technology of Near Space Information System Ministry of Industry and Information Technology of China Beijing100191 China

Unmanned Aerial Vehicles (UAVs) offer high mobility and flexible deployment capabilities, making them ideal for Internet of Things (IoT) applications. However, the substantial amount of data generated by various applications within the existing low-altitude network requires processing through Deep Neural Networks (DNN) on UAVs, which is challenging due to their limited computational resources. To address this issue, we propose a two-stage optimization method for flight path planning and task allocation based on a mother-child UAV swarm system. In the first stage, we employ a greedy algorithm to solve the path planning problem by considering the task size of the target area to be inspected and the shortest flight path as constraints. The goal is to minimize both the flight path of the UAV and the overall cost of the system. In the second stage, we introduce a novel DNN task assignment algorithm that combines Multi-Agent Deep Deterministic Policy Gradient (MADDPG) and Generative Diffusion Models (GDM), named GDM-MADDPG. This algorithm takes advantage of the reverse denoising process of GDM to replace the actor network in MADDPG. It enables UAVs to generate specific DNN task assignment actions based on agents' observations in a dynamic environment, thereby improving the efficiency of task assignment and overall system performance. The simulation results demonstrate that our algorithm outperforms the benchmarks in terms of path planning, Age of Information (AoI), task completion rate, and system utility, demonstrating its effectiveness. © 2014 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation-based Radio Frequency Fingerprint Identification for Industrial Cyber-Physical Systems

引用

IEEE Network 2025年

作者： Wang, Yatong Cao, Bin Wen, Zhongyi Yan, Mu Song, Changqing Beijing Institute of Technology School of Information and Electronics Beijing100081 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Laboratory of Electromagnetic Space Cognition and Intelligent Control Technology Beijing100191 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing100191 China

With the widespread adoption of cloud and fog platforms, security issues facing Industrial Cyber-Physical Systems (ICPSs) are increasingly prominent. Radio Frequency Fingerprinting (RFFI) emerges as a promising physical layer security technique for user authentication, effectively enhancing ICPS security over wireless networks by exploiting inherenthardware imperfections in transmitters. However, as technologies evolve and user environments become denser and more complex, existing RFFI techniques encounter significant domain shift challenges, leading to performance degradation. Therefore, developing domain-adaptive RFFI techniques is crucial for the effectiveness of ICPSs. In this article, we first provide a comprehensive review of the RFFI framework, emphasizing its applications in ICPSs and the key processes involved. Next, we focus on the domain shift issues faced by RFFI in ICPSs and present a comprehensive survey of domain adaptation methods. To tackle these challenges, we propose a novel feature-alignment based domain adaptation (FADA) framework for RFFI, which is designed to mitigate the performance degradation caused bycross-domain shifts by aligning the feature representations of the source and target domain. Finally, we discuss the inherent challenges and future directions for developing domain adaptation based RFFI to enhance the security of ICPSs. © 2025 IEEE. All rights reserved.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs

arXiv

引用

arXiv 2025年

作者： Lykov, Artem Serpiva, Valerii Khan, Muhammad Haris Sautenkov, Oleg Myshlyaev, Artyom Tadevosyan, Grik Yaqoot, Yasheerah Tsetserukou, Dzmitry The Intelligent Space Robotics Laboratory Center for Digital Engineering Skolkovo Institute of Science and Technology Russia

This paper introduces CognitiveDrone, a novel Vision-Language-Action (VLA) model tailored for complex Unmanned Aerial Vehicles (UAVs) tasks that demand advanced cognitive abilities. Trained on a dataset comprising over 8,000 simulated flight trajectories across three key categories—Human Recognition, Symbol Understanding, and Reasoning—the model generates real-time 4D action commands based on first-person visual inputs and textual instructions. To further enhance performance in intricate scenarios, we propose CognitiveDrone-R1, which integrates an additional Vision-Language Model (VLM) reasoning module to simplify task directives prior to high-frequency control. Experimental evaluations using our open-source benchmark, CognitiveDroneBench, reveal that while a racing-oriented model (RaceVLA) achieves an overall success rate of 31.3%, the base CognitiveDrone model reaches 59.6%, and CognitiveDrone-R1 attains a success rate of 77.2%. These results demonstrate improvements of up to 30% in critical cognitive tasks, underscoring the effectiveness of incorporating advanced reasoning capabilities into UAV control systems. Our contributions include the development of a state-of-the-art VLA model for UAV control and the introduction of the first dedicated benchmark for assessing cognitive tasks in drone operations. The complete repository is available at https://***. © 2025, CC BY-NC-ND.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

UAV-VLA: Vision-Language-Action System for Large Scale Aerial Mission Generation

arXiv

引用

arXiv 2025年

作者： Sautenkov, Oleg Yaqoot, Yasheerah Lykov, Artem Mustafa, Muhammad Ahsan Tadevosyan, Grik Akhmetkazy, Aibek Cabrera, Miguel Altamirano Martynov, Mikhail Karaf, Sausar Tsetserukou, Dzmitry Intelligent Space Robotics Laboratory Center for Digital Engineering Skolkovo Institute of Science and Technology Russia

The UAV-VLA (Visual-Language-Action) system is a tool designed to facilitate communication with aerial robots. By integrating satellite imagery processing with the Visual Language Model (VLM) and the powerful capabilities of GPT, UAV-VLA enables users to generate general flight paths-and-action plans through simple text requests. This system leverages the rich contextual information provided by satellite images, allowing for enhanced decision-making and mission planning. The combination of visual analysis by VLM and natural language processing by GPT can provide the user with the path-and-action set, making aerial operations more efficient and accessible. The newly developed method showed the difference in the length of the created trajectory in 22% and the mean error in finding the objects of interest on a map in 34.22 m by Euclidean distance in the K-Nearest Neighbors (KNN) approach. The code is available here: https://***/sautenich/uav-vla © 2025, CC BY-NC-ND.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

ImpedanceGPT: VLM-driven Impedance control of Swarm of Mini-drones for intelligent Navigation in Dynamic Environment

arXiv

引用

arXiv 2025年

作者： Batool, Faryal Zafar, Malaika Yaqoot, Yasheerah Khan, Roohan Ahmed Khan, Muhammad Haris Fedoseev, Aleksey Tsetserukou, Dzmitry Intelligent Space Robotics Laboratory Center for Digital Engineering Skolkovo Institute of Science and Technology Russia

Swarm robotics plays a crucial role in enabling autonomous operations in dynamic and unpredictable environments. However, a major challenge remains ensuring safe and efficient navigation in environments filled with both dynamic alive (e.g., humans) and dynamic inanimate (e.g., non-living objects) obstacles. In this paper, we propose ImpedanceGPT, a novel system that combines a Vision-Language Model (VLM) with retrieval-augmented generation (RAG) to enable real-time reasoning for adaptive navigation of mini-drone swarms in complex environments. The key innovation of ImpedanceGPT lies in the integration of VLM and RAG, which provides the drones with enhanced semantic understanding of their surroundings. This enables the system to dynamically adjust impedance control parameters in response to obstacle types and environmental conditions. Our approach not only ensures safe and precise navigation but also improves coordination between drones in the swarm. Experimental evaluations demonstrate the effectiveness of the system. The VLM-RAG framework achieved an obstacle detection and retrieval accuracy of 80% under optimal lighting. In static environments, drones navigated dynamic inanimate obstacles at 1.4 m/s but slowed to 0.7 m/s with increased separation around humans. In dynamic environments, speed adjusted to 1.0 m/s near hard obstacles, while reducing to 0.6 m/s with higher deflection to safely avoid moving humans. © 2025, CC BY-NC-SA.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Evolution 6.0: Evolving Robotic Capabilities Through Generative Design

arXiv

引用

arXiv 2025年

作者： Khan, Muhammad Haris Myshlyaev, Artyom Lykov, Artem Cabrera, Miguel Altamirano Tsetserukou, Dzmitry Intelligent Space Robotics Laboratory Center for Digital Engineering Skolkovo Institute of Science and Technology Russia

We propose a new concept, Evolution 6.0, which represents the evolution of robotics driven by Generative AI. When a robot lacks the necessary tools to accomplish a task requested by a human, it autonomously designs the required instruments and learns how to use them to achieve the goal. Evolution 6.0 is an autonomous robotic system powered by Vision-Language Models (VLMs), Vision-Language Action (VLA) models, and Text-to-3D generative models for tool design and task execution. The system comprises two key modules: the Tool Generation Module, which fabricates task-specific tools from visual and textual data, and the Action Generation Module, which converts natural language instructions into robotic actions. It integrates QwenVLM for environmental understanding, OpenVLA for task execution, and Llama-Mesh for 3D tool generation. Evaluation results demonstrate a 90% success rate for tool generation with a 10-second inference time and action generation achieving 83.5% in physical and visual generalization, 70% in motion generalization, and 37% in semantic generalization. Future improvements will focus on bimanual manipulation, expanded task capabilities, and enhanced environmental interpretation to improve real-world adaptability. © 2025, CC BY-NC-SA.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

LLM-Glasses: GenAI-driven Glasses with Haptic Feedback for Navigation of Visually Impaired People

arXiv

引用

arXiv 2025年

作者： Tokmurziyev, Issatay Cabrera, Miguel Altamirano Khan, Muhammad Haris Mahmoud, Yara Moreno, Luis Tsetserukou, Dzmitry Intelligent Space Robotics Laboratory Center for Digital Engineering Skolkovo Institute of Science and Technology Russia

We present LLM-Glasses, a wearable navigation system designed to assist visually impaired individuals by combining haptic feedback, YOLO-World object detection, and GPT-4o-driven reasoning. The system delivers real-time tactile guidance via temple-mounted actuators, enabling intuitive and independent navigation. Three user studies were conducted to evaluate its effectiveness: (1) a haptic pattern recognition study achieving an 81.3% average recognition rate across 13 distinct patterns, (2) a VICON-based navigation study in which participants successfully followed predefined paths in open spaces, and (3) an LLM-guided video evaluation demonstrating 91.8% accuracy in open scenarios, 84.6% with static obstacles, and 81.5% with dynamic obstacles. These results demonstrate the system’s reliability in controlled environments, with ongoing work focusing on refining its responsiveness and adaptability to diverse real-world scenarios. LLM-Glasses showcases the potential of combining generative AI with haptic interfaces to empower visually impaired individuals with intuitive and effective mobility solutions. © 2025, CC BY-NC-ND.

关键词： Haptic interfaces

来源：评论

学校读者我要写书评

暂无评论

Asynchronous PID control for T-S Fuzzy Systems Over Gilbert-Elliott Channels Utilizing Detected Channel Modes

引用

IEEE Transactions on Fuzzy Systems 2025年第5期33卷 1555-1567页

作者： Wang, Yezheng Wang, Zidong Zou, Lei Ge, Quanbo Dong, Hongli Nanjing University of Information Science and Technology School of Automation Nanjing210044 China Shandong University of Science and Technology College of Electrical Engineering and Automation Qingdao266590 China Brunel University London Department of Computer Science UxbridgeUB8 3PH United Kingdom Donghua University College of Information Science and Technology Shanghai201620 China Ministry of Education Engineering Research Center of Digitalized Textile and Fashion Technology Shanghai201620 China Nanjing University of Information Science and Technology Jiangsu Provincial University Key Laboratory of Big Data Analysis and Intelligent Systems Nanjing210044 China Nanjing210044 China Northeast Petroleum University State Key Laboratory of Continental Shale Oil Daqing163318 China Northeast Petroleum University Artificial Intelligence Energy Research Institute Daqing163318 China Northeast Petroleum University Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Daqing163318 China

This article is concerned with the H∞ proportional-integral-derivative (PID) control problem for Takagi-Sugeno fuzzy systems over lossy networks that are characterized by the Gilbert-Eillott model. The communication quality is reflected by the presence of two channel modes (i.e., "bad" mode and "good" mode), which switch randomly according to a Markov process. In the "bad" mode, packet dropouts are governed by a stochastic variable sequence. Considering the inaccessibility of channel modes, a mode detector is utilized to estimate the communication situation. The relationship between the actual channel mode and the estimated mode is depicted in terms of certain conditional probabilities. Moreover, a comprehensive model is constructed to represent the probability uncertainties arising from statistical errors in channel mode switching, packet dropouts, and mode detection processes. Subsequently, a robust asynchronous PID controller, based on the detected channel mode, is proposed. Sufficient conditions are then derived to ensure the mean-square stability of the closed-loop system while maintaining the desired H∞performance. Finally, the efficacy of the proposed design approach is demonstrated through a simulation example. © 1993-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Projection Neural Network With Finite-Time Convergence for Energy Management of Multi-Energy System

引用

IEEE Transactions on Smart Grid 2025年第3期16卷 2156-2168页

作者： Liu, Xueying He, Xing Li, Chaojie Huang, Tingwen Southwest University Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Chongqing400715 China North China Electric Power University State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources Beijing102206 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518055 China

In this paper, an approach based on projection neural network (PNN), sliding mode control technique, and deep learning is proposed to solve the energy management problem of multi-energy systems (MES) containing dynamic parameters. First, the sliding mode technique is introduced in the PNN to design a finite-time PNN (FTPNN). The stability and finite-time convergence of the proposed FTPNN are proved by the Lyapunov method and the setting time bound is given. Then, the deep FTPNN (DFTPNN) is designed by combining deep learning with the proposed FTPNN. The dynamic parameters in the MES that change over time are used as input variables for the DFTPNN, allowing the trained DFTPNN to respond immediately to changes in the dynamic parameters and to predict the solutions of the FTPNN with different parameters directly. Simulation experiments show that FTPNN has faster convergence compared to PNN. DFTPNN significantly reduces the computation time compared to FTPNN. DFTPNN provides predicted solutions to FTPNN. Since DFTPNN can respond immediately to changes in dynamic parameters and directly provide energy management strategies under different parameters, it can adapt to changing environments and promote the economic and stable operation of MES. © 2010-2012 IEEE.

关键词： Cogeneration Heuristic algorithms Convergence Deep learning Prediction algorithms Optimization Heating systems Energy management Approximation algorithms Power system stability

来源：评论

学校读者我要写书评

暂无评论

Impact of aerosol-radiation interaction and heterogeneous chemistry on the winter decreasing PM_(2.5)and increasing O_(3)in Eastern China 2014–2020

引用

Journal of Environmental sciences 2025年第5期151卷 469-483页

作者： Yasong Li Tijian Wang Qin’geng Wang Mengmeng Li Yawei Qu Hao Wu Min Xie School of the Environment Nanjing UniversityNanjing 210023China School of Atmospheric Sciences Nanjing UniversityNanjing 210023China College of Intelligent Science and Control Engineering Jinling Institute of TechnologyNanjing 211169China Key Laboratory of Transportation Meteorology of China Meteorological Administration Nanjing Joint Institute for Atmospheric SciencesNanjing 210041China School of Environment Nanjing Normal UniversityNanjing 210023China

In the context of the prevalent winter air quality issues in China marked by declining PM_(2.5)and rising O_(3),this study employed amodified WRF-Chem model to examine the aerosol radiation interaction(ARI),heterogeneous chemistry(AHC),and their combined impact(ALL)on the variations in O_(3)and PM_(2.5)during the 2014–2020 in eastern *** analysis confirmed that ARI curtailed O_(3)while elevating PM_(2.5).AHC reduced O_(3)through heterogeneous absorption of NOx and hydroxideswhile notably fostering fine-grained sulfate,resulting in a PM_(2.5)*** reductions mitigated the inhibitory impact of ARI on meteorological fields and photolysis *** reduction individually without aerosol feedback led to a 5.43 ppb O_(3)increase and a 22.89μg/m^(3)PM_(2.5)*** and AHC amplified the emission-reduction-induced(ERI)O_(3)rise by 1.83 and 0.31 ppb,*** response of ARI to emission diminution brought about a modest PM_(2.5)increase of 0.31μg/m^(3).Conversely,AHC,acting as the primary contributor,caused a noteworthy PM_(2.5)decrease of 4.60μg/m^(3).As efforts concentrate on reducing PM_(2.5),the promotion of ARI on PM_(2.5)counterbalanced the efficacy of emission reduction and the AHC-induced strengthening of PM_(2.5)*** ALL magnified the ERI O_(3)increase by 38.9%and PM_(2.5)decrease by 18.7%.Sensitivity experiments with different degrees of emission reduction demonstrated a consistent linear relationship between the ALL-induced enhancement of O_(3)increase and PM_(2.5)decrease to the ERI PM_(2.5)*** investigation revealed the complex connection between emissions and aerosol feedback in influencing air quality.

关键词： Aerosol-radiation interaction Heterogeneous chemistry O_(3)increase PM_(2.5)decrease Emission reduction

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：