信息工程最新文献

{"title":"Nonlinear optimal control of the planar inverted pendulum","authors":"G. Rigatos,&nbsp;G. Cuccurullo,&nbsp;P. Siano,&nbsp;M. Abbaszadeh,&nbsp;Z. Gao,&nbsp;F. Zouari","doi":"10.1007/s43684-026-00133-4","DOIUrl":"10.1007/s43684-026-00133-4","url":null,"abstract":"<div><p>The control and stabilization problem of the 4-DOF planar inverted pendulum is nontrivial due to the complex nonlinear dynamics and the underactuation of this dynamical system. In this article, a new nonlinear optimal control method is proposed for solving the problem of control and stabilization of the 4-DOF planar (XY) inverted pendulum. To apply the proposed nonlinear optimal control method, the dynamic model of the planar inverted pendulum undergoes first approximate linearization around a temporary operating point that is updated at each iteration of the control algorithm. The linearization takes place through first-order Taylor series expansion and through the computation of the Jacobian matrices of the pendulum’s state-space description. For the approximately linearized model of the planar inverted pendulum an H-infinity feedback controller is designed. Actually, the H-infinity controller stands for the solution of the optimal control problem for the planar inverted pendulum under uncertainty and external perturbations. For the computation of the feedback gains of the H-infinity controller an algebraic Riccati equation is solved at each time-step of the control method. The stability properties of the control algorithm are proven through Lyapunov analysis. The proposed control method achieves fast and accurate tracking of setpoints under moderate variations of the control inputs.</p></div>","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s43684-026-00133-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147938470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-UAV cooperative MUSIC localization and PLW power allocation for radar jamming","authors":"Jiafeng Zhou,&nbsp;Wen Fang,&nbsp;Te Ma,&nbsp;Peng Yi,&nbsp;Wei Gong,&nbsp;Qingwen Liu","doi":"10.1007/s43684-026-00134-3","DOIUrl":"10.1007/s43684-026-00134-3","url":null,"abstract":"<div><p>In modern communication and electronic systems, unmanned aerial vehicle (UAV) swarm networks have emerged as a critical component due to their distributed collaboration capabilities, yet dynamic network characteristics pose significant challenges in real-time resource allocation and spatial perception. Traditional methods for collaborative positioning and jamming power distribution often suffer from discrete execution modes, high computational complexity, limiting the effectiveness in complex electromagnetic environments. To address these limitations, this paper proposes a collaborative optimization framework that integrates multiple signal classification (MUSIC) localization with a path loss-aware weighted (PLW) allocation algorithm, aiming to enhance radar jamming effectiveness in contested electromagnetic environments. By leveraging MUSIC-based azimuth angle estimation and triangular geometric relationships, the system dynamically computes jammer-radar distances and azimuth angles, which are fed into the PLW algorithm that enforces minimum power constraints. Simulation results demonstrate that the proposed method achieves 3-5 dB gains in the interference suppression coefficient (J/S) and significant enhancements in suppression probability. These advancements provide a scalable solution for multi-UAV adversarial missions by offering novel technical pathways for real-time target protection in contested spectral environments, and enhancing the generalization ability of multi-UAV strategies.</p></div>","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s43684-026-00134-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147938322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"UAV swarm communication networking and routing optimization for high-demand users: a graph attention multi-agent reinforcement learning approach","authors":"Zhaopeng Ning,&nbsp;Gang Li,&nbsp;Wei Li","doi":"10.1007/s43684-026-00131-6","DOIUrl":"10.1007/s43684-026-00131-6","url":null,"abstract":"<div><p>Unmanned aerial vehicle swarms serving ground high-demand communication users in dynamic environments must simultaneously optimize three-dimensional trajectories, communication network topology, and routing strategies while considering limited energy, link quality fluctuations, and collision avoidance constraints. This problem faces three core challenges: routing decisions under dynamic topology require real-time adaptation to vehicle position changes and channel variations; end-to-end delay and throughput optimization in multi-hop communication demands coordinated forwarding strategies across all vehicles; high-dimensional continuous action spaces and partial observability make traditional optimization methods difficult to solve. This paper models the problem as a multi-agent partially observable Markov decision process and proposes a graph attention-based multi-agent deep deterministic policy gradient algorithm to jointly optimize velocity vectors, communication power, and routing decisions for each vehicle. The reward function comprehensively considers user quality of service, system throughput, end-to-end delay, and energy consumption while ensuring safety distance and energy margins through constraint penalties. Simulation results demonstrate that compared to single-agent deep deterministic policy gradient and independent Q-learning baseline methods, the proposed method achieves approximately 50% improvement in convergence speed, 12% to 18% increase in user service satisfaction, 25% to 40% improvement in system throughput, 30% to 45% reduction in end-to-end delay, and 39% to 102% improvement in energy efficiency. The framework dynamically adjusts network topology and routing strategies according to user demands, providing a deployable solution for large-scale vehicle swarm communication networks.</p></div>","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s43684-026-00131-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147738140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Strategies for computational efficiency in small language models","authors":"Jonathan Taylar","doi":"10.1007/s43684-026-00130-7","DOIUrl":"10.1007/s43684-026-00130-7","url":null,"abstract":"<div><p>The proliferation of Large Language Models (LLMs) is often constrained by their significant computational and memory requirements, limiting their deployment to large data centers. Small Language Models (SLMs) offer a feasible solution for on-device applications; yet their efficiency requires optimization to operate well on resource-constrained hardware. This study looks at ways to make SLMs more efficient at using computers. The effects of two primary methods were compared: post-training optimization and architectural innovation through quantitative and observational study. Using a standardized suite of benchmarks measuring accuracy, reasoning, and inference performance, a baseline is established with state-of-the-art SLMs like Phi-3 and Llama 3. Post-training techniques were evaluated, including 4-bit quantization (GPTQ) and knowledge distillation from a superior teacher model. Finally, these optimized Transformers were compared against a custom-trained, non-Transformer model based on the Mamba (State-Space Model) architecture. Results show that 4-bit quantization is the most effective compression strategy among those evaluated. It reduces peak inference memory footprint by 71%, increases throughput by 83%, and does so with minimal accuracy degradation. Within the controlled experimental space evaluated in this study, the 4-bit quantized Phi-3-mini model occupies a Pareto-optimal position in memory-normalized accuracy. Focused skill growth works best with knowledge distillation. However, new designs like Mamba offer a different trade-off by being the best at streaming jobs’ raw output. It was found that improving current Transformer-based SLMs through quantization is the best way to use them for general purposes. However, customized designs and distillation work better for specific, high-performance uses. This research offers a definitive framework and pragmatic recommendations for advancing the next generation of robust, efficient, and accessible language models.</p></div>","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s43684-026-00130-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147642347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AHAT: adaptive hybrid association strategy for multi-object tracking in complex motion scenes","authors":"Keyu Wang,&nbsp;Yajie Yang,&nbsp;Xiuxian Li","doi":"10.1007/s43684-026-00129-0","DOIUrl":"10.1007/s43684-026-00129-0","url":null,"abstract":"<div><p>Multi-object tracking (MOT) has long been a challenging task in computer vision, particularly in complex scenes with intricate motion patterns and frequent occlusions. Existing approaches often face significant hurdles in maintaining consistent and accurate trajectories under such demanding conditions. The integration of motion and appearance cues has proven beneficial, yet most methods rely on static fusion strategies that fail to adapt to dynamic scene variations. In this paper, we propose Adaptive Hybrid Association Tracking (AHAT), a novel framework designed to address the limitations of traditional MOT methods. AHAT employs a two-stage dynamic feature selection mechanism. The first stage combines motion and appearance features to achieve high-precision matching for high-scoring detection boxes, while the second stage utilizes a dynamic threshold for simple matching against low-scoring detection boxes. This approach effectively reduces trajectory fragmentation and ID switches, improving tracking robustness in crowded and dynamic environments. Notably, AHAT achieves a 5% improvement in HOTA in scenarios with low detection confidence or high motion complexity and reduces identity switches by over 10%. These results highlight AHAT’s effectiveness in practical applications, especially in video surveillance and robotics where high accuracy and real-time performance are crucial. The modular design of AHAT allows for seamless integration into existing tracking frameworks, offering a simple yet effective solution.</p></div>","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s43684-026-00129-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147642655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive regional segmentation and fitting-based building LOD reconstruction method","authors":"Bowen LI,&nbsp;Xukun SHEN,&nbsp;Yong HU","doi":"10.1016/j.vrih.2026.01.004","DOIUrl":"10.1016/j.vrih.2026.01.004","url":null,"abstract":"<div><div>Reconstructing accurate urban building models remains challenging because of large-scale variability and complex topologies. We introduce a practical multi-step framework that reconstructs a single building from a dense triangular mesh by explicitly exploiting its block-wise composition. The pipeline first partitioned the mesh into spatially coherent regions, then extracted height-aware contours, and classified the geometry into facades, roofs, and appurtenances. For each part, we performed contour-guided vectorized modeling with profile fitting and consistency constraints, producing watertight, semantically structured models at the level of detail (LOD) 2.3. The interactive refinement module further supported user adjustments to resolve rare failures and enforced design regularity. The proposed decomposition and layered fitting yielded compact outputs while preserving the salient geometry and made the reconstruction robust across scales and moderate noise. We also analyzed the modeling assumptions and implementation details to ensure reproducibility. Overall, this study offers a component-aware, engineering-ready solution for converting unstructured meshes into structured building models that are amenable to downstream urban modeling and visualization.</div></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"8 2","pages":"Pages 202-218"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147865369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detecting rug pulls in decentralized exchanges: The rise of meme coins","authors":"Alisa Kalacheva ,&nbsp;Pavel Kuznetsov ,&nbsp;Igor Vodolazov ,&nbsp;Yury Yanovich","doi":"10.1016/j.bcra.2025.100336","DOIUrl":"10.1016/j.bcra.2025.100336","url":null,"abstract":"<div><div>The rise in cryptoasset valuations and the ease of creating new tokens have spurred an increase in illicit activities within the market. Decentralized exchanges (DEX) facilitate the trading of a vast array of tokens, including those with minimal liquidity, amplifying the risk of fraudulent schemes. Fraudulent practices take various forms, including counterfeit tokens, rug pulls, and pump-and-dump schemes, all lacking functional innovation and relying heavily on aggressive social media marketing. This study contributes to the identification and profiling of deceitful tokens on DEX platforms. Our approach involved compiling new tokens with an active trading start and attracted competition to buy them in the first blocks spanning multiple years from the Ethereum blockchain, tracking all associated purchase and sale transactions. Our analysis revealed that Uniswap V2 predominantly hosts the trading of new tokens, with an alarming discovery that over 98% of tokens minted daily exhibit fraudulent characteristics. Subsequently, a machine learning model was developed to predict the likelihood of a rug pull occurring shortly after trading commencement. Although the dataset labeling methodology and detection problem statement are exploratory, we demonstrate the economic significance of the proposed approach within a trading pipeline. The findings highlight the importance of identifying fraudulent activities and emphasize the need for collaboration between DEX and regulatory bodies to mitigate financial losses for investors.</div></div>","PeriodicalId":53141,"journal":{"name":"Blockchain-Research and Applications","volume":"7 2","pages":"Article 100336"},"PeriodicalIF":5.6,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147750763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From embodied AI to cobodied AI: Foundations and frontiers","authors":"Feng LU,&nbsp;Ruijia PANG,&nbsp;Bosong QI,&nbsp;Qinping ZHAO","doi":"10.1016/j.vrih.2026.03.001","DOIUrl":"10.1016/j.vrih.2026.03.001","url":null,"abstract":"<div><div>This paper presents a systematic review and technical revisit of recent developments in embodied AI. We comprehensively synthesize current dominant paradigms, representative architectures, and pivotal advancements around five core modules: (1) perception and understanding, (2) reasoning and decision making, (3) control and action, (4) modeling and learning (e.g., VLA (vision-language-action) and WM (world models)), and (5) data and simulation. This analysis establishes a structured and cutting-edge panoramic view of embodied AI technology. Building on this foundation, we explore the transition from embodied AI to a new paradigm of deep human-AI collaboration. Anchored in the original concept of cobodied AI, we adopt a human-centered technical perspective to systematically investigate this paradigm shift. Specifically, we discuss breakthroughs in critical dimensions such as perceptual alignment, collaborative decision-making, action guidance, and bidirectional mutual learning. These efforts aim to realize three core characteristics: human-centered egocentric grounding, dual-mode cognitive integration, and physical co-embodiment. To our knowledge, this work constitutes the first systematic construction of a technical framework and implementation roadmap for realizing cobodied AI, building upon advances in embodied AI but fundamentally reorienting intelligence around the human body and intent, providing a foundational reference for future research in this domain.</div></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"8 2","pages":"Pages 131-171"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147865322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synchronizing virtual backgrounds with monocular camera motion: A novel panoramic framework for video conferencing","authors":"Senzhe XU ,&nbsp;Zian ZHOU ,&nbsp;Fanglue ZHANG ,&nbsp;Songhai ZHANG","doi":"10.1016/j.vrih.2026.01.003","DOIUrl":"10.1016/j.vrih.2026.01.003","url":null,"abstract":"<div><div>We present a novel 360° panoramic video conferencing system that dynamically synchronizes virtual backgrounds with real-time camera motion, addressing the limitations of static backgrounds in conventional systems. By integrating robust human segmentation, monocular visual odometry (VO), and virtual environment rendering, our method achieves seamless alignment between foreground participants and immersive 3D virtual scenes. Unlike prior approaches that suffer from foreground-background desynchronization during camera rotations or user movements, our framework estimates camera rotation in 3-DoF using a hybrid pipeline combining feature-based patch tracking and pose smoothing, while ignoring translation artifacts to maintain stability. This work bridges the gap between computational efficiency and MR-driven telepresence, offering a practical solution for next-generation virtual collaboration.</div></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"8 2","pages":"Pages 219-234"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147865324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Resolving the token loss vulnerability in the Ethereum ERC-20 standard","authors":"Nattawat Songsom,&nbsp;Jakapan Suaboot,&nbsp;Warodom Werapun","doi":"10.1016/j.bcra.2025.100329","DOIUrl":"10.1016/j.bcra.2025.100329","url":null,"abstract":"<div><div>Custom tokens are fundamental in decentralized Applications (dApps) operating on Ethereum and other Blockchain platforms. Ethereum, in particular, relies on the ERC-20 standard as a widely accepted token interface, facilitating seamless integration with numerous pre-existing dApps, user interface platforms, and popular web applications like exchange services. A notable security challenge within the ERC-20 framework is the “lost token problem”. This problem arises because users occasionally send tokens to the wrong addresses, and it has caused more than $27 million in damage. In this paper, we evaluate three existing solutions to this issue. Through the utilization of formal modeling, property specification, and the Temporal Logic of Actions (TLA). Most importantly, we propose a novel double-layer solution to remedy the ERC-20 vulnerability. Our formal verification and experimental results indicate our approach encompasses the protection of the already deployed smart contracts, which is a critical aspect that has never been addressed in the existing mitigation techniques.</div></div>","PeriodicalId":53141,"journal":{"name":"Blockchain-Research and Applications","volume":"7 2","pages":"Article 100329"},"PeriodicalIF":5.6,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147658148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}