检索结果-内蒙古大学图书馆

Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Chenyang Chen, Keyan Zhao, Rui Zou, Zhengxia Shi, Zhenwei The Department of Aerospace Intelligent Science and Technology School of Astronautics The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China The Key Laboratory of Spacecraft Design Optimization and Dynamic Simulation Technologies Ministry of Education China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Shen Yuan Honors College of Beihang University Beijing100191 China The Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

Recently, generative foundation models have significantly advanced large-scale text-driven natural image generation and have become a prominent research trend across various vertical domains. However, in the remote sensing field, there is still a lack of research on large-scale text-to-image (text2image) generation technology. Existing remote sensing image-text datasets are small in scale and confined to specific geographic areas and scene types. Besides, existing text2image methods have struggled to achieve global-scale, multi-resolution controllable, and unbounded image generation. To address these challenges, this paper presents two key contributions: the Git-10M dataset and the Text2Earth foundation model. Git-10M is a global-scale image-text dataset comprising 10.5 million image-text pairs, 5 times larger than the previous largest one. The dataset contains essential resolution information and covers a wide range of geographic scenes and contains essential geospatial metadata, significantly surpassing existing datasets in both size and diversity. Building on Git-10M, we propose Text2Earth, a 1.3 billion parameter generative foundation model based on the diffusion framework to model global-scale remote sensing scenes. Text2Earth integrates a resolution guidance mechanism, enabling users to specify image resolutions. A dynamic condition adaptation strategy is proposed for training and inference to improve image generation quality. Text2Earth not only excels in zero-shot text2image generation but also demonstrates robust generalization and flexibility across multiple tasks, including unbounded scene construction, image editing, and cross-modal image generation. This robust capability surpasses previous models restricted to the basic fixed size and limited scene types. On the previous text2image benchmark dataset, Text2Earth outperfoms previous models with a significant improvement of +26.23 FID and +20.95% Zero-shot Cls-OA metric. Our project page is https://chen-y

关键词： Optical remote sensing

Block-Wise Index Modulation and Receiver Design for High-Mobility OTFS Communications

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qian, Mi Ji, Fei Ge, Yao Wen, Miaowen Cheng, Xiang Poor, H. Vincent The School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China The Continental-NTU Corporate Lab Nanyang Technological University Singapore The State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronics School of Electronics Engineering and Computer Science Peking University Beijing100871 China The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

As a promising technique for high-mobility wireless communications, orthogonal time frequency space (OTFS) has been proved to enjoy excellent advantages with respect to traditional orthogonal frequency division multiplexing (OFDM). Although multiple studies have considered index modulation (IM) based OTFS (IM-OTFS) schemes to further improve system performance, a challenging and open problem is the development of effective IM schemes and efficient receivers for practical OTFS systems that must operate in the presence of channel delays and Doppler shifts. In this paper, we propose two novel block-wise IM schemes for OTFS systems, named delay-IM with OTFS (DeIM-OTFS) and Doppler-IM with OTFS (DoIM-OTFS), where a block of delay/Doppler resource bins are activated simultaneously. Based on a maximum likelihood (ML) detector, we analyze upper bounds on the average bit error rates for the proposed DeIM-OTFS and DoIM-OTFS schemes, and verify their performance advantages over the existing IM-OTFS systems. We also develop a multi-layer joint symbol and activation pattern detection (MLJSAPD) algorithm and a customized message passing detection (CMPD) algorithm for our proposed DeIM-OTFS and DoIM-OTFS systems with low complexity. Simulation results demonstrate that our proposed MLJSAPD and CMPD algorithms can achieve desired performance with robustness to the imperfect channel state information (CSI). © 2023, CC BY.

关键词： Message passing

Real-Time Adaptive Safety-Critical Control with Gaussian Processes in High-Order Uncertain Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yu Wen, Long Yao, Xiangtong Bing, Zhenshan Kong, Linghuan He, Wei Knoll, Alois The Department of Informatics Technical University of Munich Germany The Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau China The School of Intelligence Science and Technology University of Science and Technology Beijing Beijing100083 China The Key Laboratory of Intelligent Bionic Unmanned Systems Ministry of Education University of Science and Technology Beijing Beijing100083 China

This paper presents an adaptive online learning framework for systems with uncertain parameters to ensure safety-critical control in non-stationary environments. Our approach consists of two phases. The initial phase is centered on a novel sparse Gaussian process (GP) framework. We first integrate a forgetting factor to refine a variational sparse GP algorithm, thus enhancing its adaptability. Subsequently, the hyperparameters of the Gaussian model are trained with a specially compound kernel, and the Gaussian model’s online inferential capability and computational efficiency are strengthened by updating a solitary inducing point derived from newly samples, in conjunction with the learned hyperparameters. In the second phase, we propose a safety filter based on high order control barrier functions (HOCBFs), synergized with the previously trained learning model. By leveraging the compound kernel from the first phase, we effectively address the inherent limitations of GPs in handling high-dimensional problems for real-time applications. The derived controller ensures a rigorous lower bound on the probability of satisfying the safety specification. Finally, the efficacy of our proposed algorithm is demonstrated through real-time obstacle avoidance experiments executed using both simulation platform and a real-world 7-DOF robot. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational efficiency

Study on an Adaptive Clamping Device for Passive Safety Delivery of Vascular Intervention Robot

学校读者我要写书评

暂无评论

Study on an Adaptive Clamping Device for Passive Safety Deli...

IEEE International Conference on Mechatronics and Automation

作者： Sheng Cao Shuxiang Guo Jian Guo Jian Wang Chunying Li Huiyin Xu Bin Wang Mingchao Ding Aerospace Center Hospital & the Key Laboratory of Convergence Medical Engineering System and Healthcare Technology School of Life Science & Ministry of Industry and Information Technology Beijing Institute of Technology Beijing China Shenzhen Institute of Advanced Biomedical Robot Company Limited Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China National Engineering Laboratory of Computer Technology for Big Data Systems Shenzhen University Shenzhen China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

In practical clinical applications, vascular intervention surgical robots have developed sophisticated human-machine interaction systems, enabling assistance to physicians in performing remote surgeries and providing intelligent visual feedback. However, regarding surgical safety, current research predominantly focuses on force feedback and robot control logic, with clamping mechanisms targeting the locking of catheters and guide wires. Excessive clamping force may lead to surface damage to intervention instruments, while insufficient force delivery may result from slippery surfaces. Therefore, addressing these issues, this study proposed a passive, compliant safety strategy for an adaptive clamping device based on a vascular intervention surgical robot platform. This device can accommodate different diameter catheters and maintain a constant delivery force during the intervention process. Finally, through experimentation, the effectiveness, safety, and stability of the device were demonstrated.

关键词： Visualization Medical robotics Force Wires Robot control Surgery Safety

On an Information and Control Architecture for Future Electric Energy systems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xie, Le Huang, Tong Kumar, P.R. Thatte, Anupam A. Mitter, Sanjoy K. Department of Electrical and Computer Engineering Texas A&M University College StationTX United States Department of Electrical and Computer Engineering San Diego State University San DiegoCA United States CarmelIN United States Laboratory for Information and Decision Systems Massachusetts Institute of Technology CambridgeMA United States

This paper presents considerations towards an information and control architecture for future electric energy systems driven by massive changes resulting from the societal goals of decarbonization and electrification. This paper describes the new requirements and challenges of an extended information and control architecture that need to be addressed for continued reliable delivery of electricity. It identifies several new actionable information and control loops, along with their spatial and temporal scales of operation, which can together meet the needs of future grids and enable deep decarbonization of the electricity sector. The present architecture of electric power grids designed in a different era is thereby extensible to allow the incorporation of increased renewables and other emerging electric loads. © 2022, CC BY.

关键词： Electric loads

Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cereda, Elia Crupi, Luca Risso, Matteo Burrello, Alessio Benini, Luca Giusti, Alessandro Pagliari, Daniele Jahier Palossi, Daniele The Dalle Molle Institute for Artificial Intelligence USI SUPSI Lugano6962 Switzerland The Department of Control and Computer Engineering Politecnico di Torino Turin10129 Italy The Department of Electrical Electronic and Information Engineering University of Bologna Bologna40136 Italy The Integrated Systems Laboratory ETH Zürich Zürich8092 Switzerland

Miniaturized autonomous unmanned aerial vehicles (UAVs) are an emerging and trending topic. With their form factor as big as the palm of one hand, they can reach spots otherwise inaccessible to bigger robots and safely operate in human surroundings. The simple electronics aboard such robots (sub-100 mW) make them particularly cheap and attractive but pose significant challenges in enabling onboard sophisticated intelligence. In this work, we leverage a novel neural architecture search (NAS) technique to automatically identify several Pareto-optimal convolutional neural networks (CNNs) for a visual pose estimation task. Our work demonstrates how real-life and field-tested robotics applications can concretely leverage NAS technologies to automatically and efficiently optimize CNNs for the specific hardware constraints of small UAVs. We deploy several NAS-optimized CNNs and run them in closed-loop aboard a 27-g Crazyflie nano-UAV equipped with a parallel ultra-low power System-on-Chip. Our results improve the State-of-the-Art by reducing the in-field control error of 32% while achieving a real-time onboard inference-rate of ∼10 Hz@10 mW and ∼50 Hz@90 mW. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

Six-Body and Eight-Body Exciton States in Monolayer WSe2

学校读者我要写书评

暂无评论

Physical Review Letters 2022年第7期129卷 076801-076801页

作者： Dinh Van Tuan Su-Fei Shi Xiaodong Xu Scott A. Crooker Hanan Dery Department of Electrical and Computer Engineering University of Rochester Rochester New York 14627 USA Department of Chemical and Biological Engineering Rensselaer Polytechnic Institute Troy New York 12180 USA Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy New York 12180 USA Department of Physics University of Washington Seattle Washington 98195 USA Department of Materials Science and Engineering University of Washington Seattle Washington 98195 USA National High Magnetic Field Laboratory Los Alamos New Mexico 87545 USA Department of Physics and Astronomy University of Rochester Rochester New York 14627 USA

In the archetypal monolayer semiconductor WSe2, the distinct ordering of spin-polarized valleys (low-energy pockets) in the conduction band allows for studies of not only simple neutral excitons and charged excitons (i.e., trions), but also more complex many-body states that are predicted at higher electron densities. We discuss magneto-optical measurements of electron-rich WSe2 monolayers and interpret the spectral lines that emerge at high electron doping as optical transitions of six-body exciton states (“hexcitons”) and eight-body exciton states (“oxcitons”). These many-body states emerge when a photoexcited electron-hole pair interacts simultaneously with multiple Fermi seas, each having distinguishable spin and valley quantum numbers. In addition, we explain the relations between dark trions and satellite optical transitions of hexcitons in the photoluminescence spectrum.

关键词： Excitons Magneto-optics Trions Transition metal dichalcogenides

Effective Two-Stage Double Auction for Dynamic Resource Trading in Edge Networks via Overbooking

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Sicheng Liwang, Minghui Wang, Deqing Wang, Xianbin Wu, Chao Tang, Junyi Li, Li Jiao, Zhenzhen The School of Informatics Xiamen University Fujian China The Department of Control Science and Engineering The National Key Laboratory of Autonomous Intelligent Unmanned Systems Tongji University Shanghai China Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Tongji University Shanghai China The Department of Electrical and Computer Engineering Western University ON Canada The School of Public Affairs Zhejiang University Hangzhou310027 China School of Information Science and Engineering Lanzhou University Lanzhou China The iF-Labs Beijing Teleinfo Technology Co. Ltd. CAICT China

To facilitate responsive and cost-effective computing resource scheduling and service delivery over edge-assisted mobile networks, this paper investigates a novel two-stage double auction methodology via utilizing an interesting idea of resource overbooking to overcome dynamic and uncertain nature from edge servers (sellers) and demand from mobile devices (as buyers). The proposed auction integrates multiple essential factors such as social welfare maximization and decision-making latency (e.g., the time for determining winning seller-buyer pairs) reduction, by introducing a stagewise strategy: an overbooking-driven pre-double auction (OPDAuction) for determining long-term cooperations between sellers and buyers before practical resource transactions as Stage I, and a real-time backup double auction (RBDAuction) for handling residual resource demands during actual transactions. In particular, by applying a proper overbooking rate, OPDAuction helps with facilitating trading contracts between appropriate sellers and buyers as guidance for future transactions, by allowing the booked resources to exceed supply. Then, since pre-auctions may cause risks, our RBDAuction adjusts to real-time market changes, further enhancing the overall social welfare. More importantly, we offer an interesting view to show that our proposed two-stage auction can support significant design properties such as truthfulness, individual rationality, and budget balance. Through extensive experiments, we demonstrate good performance in social welfare, time efficiency, and computational scalability, outstripping conventional methods in dynamic edge computing settings. Copyright © 2025, The Authors. All rights reserved.

关键词： Budget control

Reinforcement Learning with Large Language Model for Hybrid Disassembly Lines in Remanufacturing Contexts

学校读者我要写书评

暂无评论

Reinforcement Learning with Large Language Model for Hybrid ...

IEEE International Conference on Automation Science and engineering (CASE)

作者： Peng Ji Xi Wang Guo Jiacun Wang Weitian Wang Shu Jin Qin Ying Tang Qi Kang College of Information and Control Engineering Liaoning Petrochemical University Fushun China Dept of Comp. Sci. and Soft. Eng. Monmouth University W. Long Branch NJ USA Collaborative Robotics and Smart Systems Laboratory (CRoSS Lab) Montclair State University Montclair NJ USA College of Economics and Management Shangqiu Normal University Shangqiu China Electrical and Computer Engineering Rowan University Glassboro New Jersey USA Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Large language models (LLM), ChatGPT is making substantial impact across various fields. This study for the first time presents a novel approach to the hybrid disassembly line balancing problem using LLM and reinforcement learning algorithms in remanufacturing contexts. The problem is divided into two sub-stages. LLM is innovatively used to capture a disassembly sequence well in the first stage, while reinforcement learning is utilized to address the problem in the second stage. Upon comparing the performance with and without LLM, the proposed approach significantly reduces the trial-and-error space and achieves faster convergence to achieve the desired solution. Future work of this study is also discussed.

关键词： computer aided software engineering Automation Large language models Reinforcement learning Chatbots Convergence