Search Results (229)

Reviews of artificial intelligence (AI) for mobile robots usually cover one competence—perception, SLAM, path planning, control, or reinforcement learning—and rarely show how these combine into a working system. We take the opposite view and treat autonomy as one pipeline: sensing, perception, localization and mapping, prediction, planning, visual servoing and control, high-level decision-making, and continual learning. We survey how AI has reshaped each stage for industrial and service robots across Industry 4.0, 5.0, and the emerging Industry 6.0. Using a structured, PRISMA-informed protocol with explicit search strings, inclusion criteria, and cross-embodiment transfer rules, we screen the literature, analyze a corpus drawn mainly from the last five years, and position it against prior surveys with a coverage matrix that exposes their single-block focus. Four findings stand out. Perception and localization approach engineering maturity through multimodal fusion and foundation vision models. Planning and control stay effective but computationally demanding. Decision-making, now driven by large language and vision–language–action models, is powerful yet unverifiable and fails under safety constraints. Lifelong learning is almost absent from deployed systems. The decisive weaknesses sit at the interfaces: at the perception–planning, planning–control, and control–decision handoffs the sim-to-real gap, limited on-robot compute, and scarce industrial data compound. We compare AI families by technology readiness, catalog datasets and benchmarks, examine the safety-certification barrier, and consolidate cross-cutting gaps. We close with a staged roadmap toward Industry 6.0 and a next-generation architecture coupling a foundation perception backbone, a world model and digital twin, a continual-learning memory, and a reasoning core wrapped by a safety monitor. The aim is to move from cataloging algorithms to engineering integrated autonomy. Full article

The paper addresses the issue of quality management in large-scale infrastructure projects, with a specific focus on tunnel construction, where technical complexity and geotechnical risks represent critical factors. The primary objective of this work is to analyze modern approaches to quality management and to propose an effective control process, which is subsequently validated through a case study of the Norwegian highway tunnel. The study examines the development and application of an Inspection and Test Plan in compliance with strict Norwegian legislation and standards, particularly N500 and R761. Within the context of the Drill and Blast technological method, three standardized production cycles are defined—standard, water-control, and post-injection—enabling systematic and repeatable inspections. Special emphasis is placed on the digitalization of processes through a Common Data Environment and the Novade software application, which facilitates real-time data collection, transparent protocol approval, and the effective mitigation of human-error risks. The case study defines a process model for quality management in a CDE environment and, based on workflow mapping, demonstrates the potential of digitalization to accelerate approval processes, improve data traceability, and eliminate human errors during cyclic tunnel construction. The insights gained from Norwegian practice, which emphasizes detailed process specifications, can serve as significant inspiration for the modernization of quality management systems. Full article

Accurate and up-to-date knowledge of land use and land cover represents one of the central challenges in spatial planning and landscape sciences. In this context, the present work introduces GANCIU (Geospatial Analysis with Neural Classification and Image Understanding), an original hybrid pipeline for the automatic extraction of man-made infrastructure from high-resolution satellite imagery. The primary methodological contribution lies in the sequential integration of four technologically heterogeneous components: a per-pixel Random Forest classifier, a guided image modulation step, edge detection via the Mumford–Shah variational functional solved through the Ambrosio–Tortorelli approximation, and final object delineation via the Segment Anything Model (SAM). Each component does not operate independently but conditions and informs the next: The RF probability map guides the modulation, which in turn directs the sensitivity of the variational step exclusively towards regions of interest; the AT edges provide spatial prompts to SAM, for which its masks are finally filtered by the RF probability in an adaptive manner through a Gaussian Mixture Model. This progressive conditioning scheme constitutes the architectural core of GANCIU and distinguishes it from approaches that combine classification and segmentation in parallel or in purely sequential fashion with each stage conditioning the next but without any reverse correction between them. The Random Forest classifier was trained on 44 manually annotated scenes, geographically disjoint from the twelve independent scenes used for quantitative validation. This validation, based on an instance matching protocol (precision, recall, F1 score, and IoU), confirms the contribution of the full pipeline over a Random-Forest-only baseline: Pooled false positives fall by close to two orders of magnitude (from 8320 to 209), while true positives rise nearly twentyfold (from 5 to 95), with a mean IoU of 0.742 ± 0.060 on correctly matched objects. Notably, the entire pipeline—including SAM-based segmentation—runs end-to-end on a modest, GPU-free consumer laptop (four logical CPU cores, under 16 GB RAM), demonstrating that competitive infrastructure-extraction performance does not require specialised computing hardware. Full article

In 2024, the annual global surface temperature rose more than 1.5 °C above pre-industrial levels for the first time. This single-year figure is not the same as the long-term warming limit set by the Paris Agreement, but it signals a rising heat-related risk. Extreme heat is already the deadliest weather hazard in the United States, yet most outpatient clinics have no structured protocol for vulnerable patients. This narrative review does three things: it explains how heat stress injures compromised cardiovascular and renal systems, catalogs the primary care medications that impair thermoregulation, and offers a Heat Action Plan (HAP) toolkit for family medicine clinics. We searched PubMed, EMBASE, Google Scholar, and Web of Science for work published from 2000 to May 2026, supplemented by WHO, CDC, and national heat-health guidelines. Patients with cardiovascular disease, chronic kidney disease, diabetes, obesity, and serious mental illness face disproportionate risk during heat events. More than 20 drug classes, among them diuretics, beta-blockers, anticholinergics, and renin–angiotensin–aldosterone system inhibitors, weaken heat defense by blunting sweating, reducing cardiac output, or suppressing thirst. We present a three-tier risk classification and a four-stage toolkit that, when built into routine chronic disease care, may help reduce preventable heat-related illness and death. Full article

Autonomous parking is one of the most demanding manoeuvres a vehicle can be asked to perform. The available space is small, the margins for error are narrow, and the vehicle must achieve an exact final pose while respecting non-holonomic constraints. A persistent gap between detection and execution yields infeasible trajectories or terminal positioning errors. This systematic review examines how bird’s-eye view (BEV) reconstruction supports each link in the perception–planning–control chain, from slot detection through trajectory generation and manoeuvre execution, and identifies where those links remain weakest. No registered review protocol was used. Between 7 January and 10 February 2026, we retrieved 338 records through a single automated engine (OpenAlex) reaching multiple indexed venues, complemented by manual citation chasing; collection was semi-automated and screening was manual. Seventy-two studies passed eligibility screening, of which 45 provide primary, parking-specific evidence; the remaining 27 are prior surveys or generic methodological contributions retained as background rather than as primary evidence. We included studies addressing BEV reconstruction, slot detection, manoeuvre planning, or control with simulated or experimental validation, and excluded duplicates and works reporting no performance evaluation. The synthesis follows five axes: multi-camera homography-based BEV reconstruction, automatic parking-slot detection, geometric and kinematic modelling, planning in confined spaces, and nonlinear control with explicit constraint handling. Across the 45 primary studies, BEV-based methods are reported to improve geometric consistency and support reliable slot detection, and Hybrid A* combined with NMPC recurs as the most frequently reported route to dynamically feasible trajectories, although no study compares these approaches under identical conditions and no quantitative comparison across studies was performed here. The weakest point of the field is integration: perception and control are rarely coupled in a closed loop, and no standardised evaluation framework has yet gained wide acceptance. Heterogeneity in scenarios, metrics, and sensing configurations limits the strength of the evidence, and modular architectures show gaps in perception–planning–control coupling and reproducible transfer to platforms such as Gazebo. No formal risk-of-bias assessment was performed. Full article

Ferrofluid seals provide non-contact operation, low friction, and strong sealing performance in high-speed rotating equipment and liquid-sealing systems. However, high speed, liquid contact, thermal loading, vibration, and eccentricity can cause ferrofluid loss, performance degradation, leakage, and premature failure. Here, intelligent reliability denotes a reliability-centered framework that integrates condition monitoring, physically interpretable health assessment, fault diagnosis, uncertainty-aware prognosis, condition-based maintenance, and feedback-driven active control. This structured review synthesizes centrifugal, thermal, liquid-medium, eccentricity-related, and material-degradation mechanisms and evaluates pressure, leakage, temperature, torque, vibration, and acoustic-emission signals. It also assesses health indicators, diagnostic methods, remaining useful life (RUL) prediction, maintenance decisions, and health-management strategies. Its principal contribution is a framework linking degradation physics with observable evidence, health assessment, diagnosis, prognosis, and maintenance and design feedback. The framework also distinguishes direct ferrofluid-seal evidence from transferable methods and supports sensor selection, indicator design, validation planning, and intervention development. Key limitations include scarce public degradation datasets, inconsistent evaluation protocols, weak physical consistency of health indicators, and limited closed-loop implementation. Future work should prioritize public run-to-failure data, physics-informed multisource assessment, uncertainty-aware RUL prediction, and experimentally validated condition-based interventions and active-control strategies. Full article

Accurate 24 h photovoltaic (PV) power forecasting is essential for day-ahead scheduling, storage operation, reserve planning, and market participation. However, published deep learning comparisons are often difficult to reproduce and interpret because they use inconsistent datasets, forecasting horizons, baselines, evaluation metrics, and leakage-control procedures. From a software engineering perspective, this limits the trustworthiness, comparability, and practical adoption of AI-based forecasting systems. This paper presents a controlled and reproducible benchmarking framework for evaluating AI-driven forecasting software. The framework is applied to nine deep learning architectures, three non-deep learning reference models, and two persistence baselines for hourly PV-power forecasting at a 350 kWp rooftop installation near Edinburgh, Scotland. All models were evaluated under a consistent experimental protocol, including the same chronological train–validation–test split, a 32-feature meteorological and solar-geometry input set, a 24-step forecasting horizon, capacity-normalised mean absolute error (NMAE), and Bayesian hyperparameter optimisation. The results show that TCN-LSTM achieved the best aggregate H24 performance with 7.22% NMAE, narrowly outperforming CPWformer-DEC at 7.28% and CT-PatchTST at 7.31%. LightGBM ranked fourth at 7.35% with fixed hyperparameters, outperforming six of the nine deep learning models. The top three models differed by only 0.09 percentage points, indicating that architectural superiority cannot be established reliably without significance testing and operational diagnostics. Per-horizon analysis showed that CT-PatchTST and S-Mamba performed best at the nearest forecast steps, whereas TCN-LSTM provided the most stable far-horizon profile. Peak-power diagnostics further revealed that aggregate NMAE can mask operational shortcomings, as Naive Persistence outperformed all deep learning models in high-output peak detection. The findings highlight the importance of reproducible benchmarking, leakage safeguards, horizon-aware evaluation, and operationally meaningful diagnostics in trustworthy AI software evaluation. The novelty of this work lies not in proposing a new architecture but in a controlled, reproducible framework that benchmarks fourteen forecasters under identical conditions, with explicit leakage safeguards, per-horizon reporting, and operationally meaningful peak diagnostics, enabling claims of architectural superiority to be made trustworthy rather than merely favourable. Architecture selection for PV forecasting should therefore consider not only aggregate accuracy but also reliability, interpretability of evaluation outcomes, and deployment-relevant performance behaviour. Full article

Building facades are highly exposed envelope components whose degradation affects durability, habitability, urban image, and maintenance planning. Several studies address facade anomalies and service-life prediction. However, a need remains for integrated, reproducible procedures that combine visual inspection, taxonomic classification, and statistical analysis within a single framework. This research develops and validates a standardized methodology for the assessment of facade pathologies in urban buildings. The proposed framework is structured into sequential phases: documentary research, systematic visual inspection, photographic recording, damage classification, facade mapping, standardized inspection sheets, database generation, statistical analysis, and cluster-based interpretation of damage patterns. The methodology was validated through an urban case study in Valencia, Spain, where 168 building facades were inspected and 1600 damage were identified, classified, mapped, and digitized. The collected data were analysed according to building age, environmental exposure, and affected facade units. Soiling due to differential washing was the most frequent damage type, with 295 cases. Buildings constructed between 1930 and 1960 concentrated the highest number of recorded cases (639), while the wall area near ground level was the most affected facade unit (499 cases). K-means analysis retained a three-cluster solution, with a Silhouette Score of 0.65 and a BSS/TSS ratio of 86.13%. In addition, K-means cluster analysis was applied to classify damage types according to their frequency after Z-score standardization and validation through Silhouette Score and BSS/TSS metrics. The results demonstrate that the proposed framework enables homogeneous data collection, reproducible classification, and diagnostic interpretation of recurrent facade damage. Beyond the specific findings of the Valencia case study, the main contribution of this work is the development of a transferable assessment framework that can support preventive maintenance protocols, inspection planning, and evidence-based conservation strategies in other urban contexts. Full article

Three-dimensional scanning, additive manufacturing, and extended reality are now widely used in digital heritage, but they are often discussed as separate technical tools rather than as parts of a user-facing workflow. This review approaches them from the standpoint of user experience, asking how digital capture, model preparation, physical replication, immersive interpretation, and hybrid access affect the way heritage content is understood, used, and trusted. The paper develops a critical narrative discussion of recent work and design practices, without adopting a systematic review protocol. Particular attention is given to educational use, museum interpretation, accessibility, tactile interaction, XR navigation, perceived authenticity, and the evaluation of user experience. The discussion indicates that UX is shaped before the final interface appears: incomplete capture, opaque model editing, poorly readable replicas, or confusing XR layers can all weaken the cultural value of an otherwise advanced system. Recurring barriers include technical complexity, interoperability problems, limited staff training, institutional constraints, accessibility gaps, and uncertainty around automated reconstruction. The review argues that automated digital heritage workflows should be planned as human-centered systems, where efficiency is balanced with usability, inclusion, transparent interpretation, and user-based evaluation. Full article

The complete community paradigm, emphasising walkable, self-sufficient neighbourhoods, has gained significant global traction, yet the role of sports and physical activity spaces within such frameworks remains undertheorised, particularly in dense Chinese urban environments. This paper introduces the Chrono-Adaptive Sports Space Index (CASI), a preliminary evaluative framework whose diagnostic utility is demonstrated through three contrasting case studies. CASI integrates temporal usage dynamics, demographic composition, smart-city sensor data, and multi-generational programming flexibility to assess sports environments within China’s 15-Minute Complete Community (完整社区, Wánzhěng Shèqū) policy framework. Unlike existing frameworks that assess sports spaces through static metrics, CASI proposes that sports environments must be evaluated across four temporal dimensions: diurnal rhythms, weekly cycles, seasonal transitions, and demographic lifecycle shifts. The four sub-indices are weighted equally (25 points each) as a deliberate first-generation design choice reflecting the absence of pre-existing empirical benchmarks; this assumption requires empirical validation in future research. Through exploratory multi-case analysis of communities in Shanghai (Jing’an District), Chengdu (Tianfu New Area), and Beijing (Chaoyang District), this study provides preliminary evidence suggesting that temporally inert sports spaces may be associated with utilisation losses of 38–52% during off-peak periods and the systematic exclusion of elderly and child populations; these figures should be treated as indicative estimates pending broader empirical validation. A Chrono-Adaptive Design Protocol (CADP) is proposed as a conceptual, practice-informed protocol awaiting prospective empirical evaluation. This research is better characterised as a framework development and initial exploratory application study rather than a validation of a mature instrument. Its primary contribution is a new theoretical and diagnostic lens for complete community planning, together with an agenda for the empirical work needed to develop CASI into a broadly applicable assessment tool. The study’s limitations and a structured five-priority future research agenda are presented in a dedicated section following the Conclusions. Full article

Proactive disease transmission pathway analyses break complex transmission routes into simpler steps, making risks and uncertainties easier to identify. This approach is especially valuable for African Swine Fever (ASF), a difficult-to-control disease in low-biosecurity settings or when biosecurity practices are inconsistently applied. To support targeted biosecurity planning, a pathway analysis was conducted that is specific to pork harvest facilities in the United States. The analysis focused on two federally inspected plants that slaughter market hogs and produce primal cuts. Inputs, outputs, and potential transmission pathways were identified through a literature review, site visits, and facility personnel interviews. Because ASF virus remains stable at low temperatures and in many pork products, particular attention was given to pathways involving storage conditions, waste materials, and processing steps such as heating or pH modification. Processing steps were evaluated against existing process control plans and ASF inactivation thresholds to determine mitigation status. Of 42 identified pathways, 39 were classified as unmitigated or of unknown mitigation status. These unmitigated or unknown pathways—broadly involving pigs, people, vehicles, and waste—represent the highest priorities for further risk assessment work and for exploring ways to develop or strengthen biosecurity protocols that reduce ASF transmission. Full article

Accurate weather-regime classification is increasingly important for climate-sensitive decision-making in agriculture, aviation, disaster preparedness, and territorial planning, particularly in regions where strong climatic heterogeneity complicates conventional operational workflows. This study proposes a machine learning-based framework for broad-regime weather classification over Morocco using hourly METAR observations collected from 22 meteorological stations between July 2022 and February 2024. The proposed workflow integrates data cleaning, missing-value imputation, feature transformation, categorical encoding, class-imbalance handling, and model optimization under a leakage-safe experimental protocol. To preserve temporal integrity, observations were chronologically split into training, validation, and independent test subsets; SMOTE and random undersampling were applied exclusively to the training subset, whereas the validation and test subsets retained their original class distributions. Seven classifiers were evaluated, including XGBoost, LightGBM, CatBoost, Random Forest, Gradient Boosting, Support Vector Machine, and Logistic Regression, with hyperparameters optimized using Optuna. The results show that optimized boosting models are particularly effective for Moroccan station-based weather classification. XGBoost achieved the highest test-set accuracy of 95.1%, followed by LightGBM at 94.7% and CatBoost at 93.8%, with optimization improving accuracy by approximately 8–12 percentage points compared with baseline configurations. Because the dataset exhibits class imbalance, macro-averaged precision, recall, and F1-score were emphasized alongside accuracy to provide a more reliable assessment across weather classes. Confusion-matrix analysis indicates improved recognition of underrepresented regimes, especially Dust/Sand events, while residual confusion between Fog/Haze and Rain/Storm reflects both physical overlap and the limits of a four-class METAR taxonomy. Overall, the findings demonstrate that optimized ensemble learning can provide a robust, computationally efficient, and operationally relevant classification layer for regional meteorological decision support in Morocco, while future work should extend the framework to longer time series, finer weather taxonomies, and external regional validation. Full article

This paper presents the design and development of an adaptive augmented reality (AR) assistance system for complex mechanical assembly tasks. Integrating a wrist-worn optical heart rate sensor to evaluate the user’s cognitive state, the system is intended to run as a standalone application on the Meta Quest 3 headset. The system displays instructions and visual cues directly overlaid on the user’s physical workspace and constantly monitors their heart rate variability through the sensor as an estimate of their cognitive load. When the system detects an overload, it dynamically adjusts the presentation of information—for example, it slows down pacing, simplifies instructions, or switches to a different interaction modality (audio)—as an attempt to reduce the overload. The paper makes three contributions: first, it provides a documented standalone integration of physiological sensing with adaptive interface logic on a mixed reality headset without external compute infrastructure; second, it provides a systematic characterization of platform-specific tracking incompatibilities on the Meta Quest 3, documenting the progression through four spatial registration strategies and the specific failure condition that triggered each transition; third, it reports spatial interface design observations from iterative developer testing in the current prototype configuration, including panel height ranges not previously reported in the AR interface literature at this level of specificity. The paper also discusses the within-subjects evaluation protocol that is planned for final system testing with actual users. The work is intended as an engineering and design contribution that establishes the foundation for subsequent empirical evaluation of adaptive AR guidance in industrial assembly contexts. Full article

Rising ambient temperatures and the increasing frequency of training and competition in hot climates have made heat stress a major challenge in football. Under such conditions, players experience greater cardiovascular and thermoregulatory strain, faster glycogen use, higher perceived exertion, and progressive impairment in repeated high-intensity actions and decision-making. These responses have intensified interest in nutritional strategies that might complement heat acclimation, hydration/electrolyte planning, cooling practices, and recovery management. This narrative review critically synthesizes current evidence on nutritional interventions that may be relevant to football performed in the heat, with emphasis on hydration and electrolyte replacement, carbohydrate–protein strategies, taurine, branched-chain amino acids (BCAAs), creatine, menthol, antioxidant- and nitrate-related approaches, and selected multi-ingredient products. Across the available literature, hydration/electrolyte planning and carbohydrate–protein feeding remain the practical foundation, menthol appears most consistently useful for perceptual cooling, creatine seems safe and potentially helpful for repeated-sprint support, and taurine is promising but still supported by relatively few trials. By contrast, evidence for BCAAs, antioxidants, nitrates, and caffeine as stand-alone heat strategies, as well as for many compound supplements, remains inconsistent, context-specific, or too indirect for strong football-specific endorsement. Overall, the evidence base remains heterogeneous in study quality, protocol design, exercise mode, and sport specificity. A substantial proportion of the available data is derived from cycling, endurance, or laboratory heat-exercise models rather than football-specific trials. Accordingly, any practical recommendation should be interpreted cautiously and embedded within broader heat-management strategies. Future work should prioritize ecologically valid randomized controlled trials in football or football-like intermittent protocols, with transparent reporting of dose, timing, perceptual outcomes, and match-relevant performance measures. Full article

Autonomous driving in complex urban environments remains challenging due to perception uncertainty, dynamic multi-agent interactions, and control instability under adverse conditions. Despite advances in individual components, systematic evaluations of fully integrated modular pipelines under compounded urban disturbances remain scarce. This work presents a modular autonomous driving framework in CARLA Town10HD, integrating Convolutional Neural Network (CNN)-based perception using ResNet-18, global path planning via A* algorithm, and two control strategies: a classical Proportional–Integral–Derivative (PID) controller and a Deep Q-Network (DQN) agent with adaptive geometric steering assistance. A structured protocol assessed robustness across five scenarios: Heavy Rain, Dense Fog, Nighttime Driving, Dense Traffic, and Combined Extreme Conditions. The perception module achieved F1-scores close to 0.99 for traffic-sign, pedestrian, and lane classification; results reflect synthetic CARLA data and should not be interpreted as real-world generalization. The PID controller produced smoother trajectories with lower steering oscillations, while the DQN agent achieved faster traversal times at the cost of higher control variability. Route efficiency remained around 0.96 under isolated disturbances and decreased to 0.52 under compounded conditions, confirming sensitivity to multi-factor complexity. This study contributes a reproducible multi-scenario benchmark quantifying stability–adaptability trade-offs between classical and learning-based control, identifying scenario generalization and simulation-to-reality transfer as key future directions. Full article