Search Results (827)

Objectives: Heart failure (HF) arises from multiple interrelated pathological processes. Among these, lysosomal impairment and loss of autophagic homeostasis are increasingly recognized as important contributors to myocardial damage and ventricular remodeling. This study sought to identify lysophagy-associated signature genes in HF and to define their biological roles, cellular origins, and potential diagnostic relevance. Methods: Bulk myocardial transcriptome datasets, including GSE16499, GSE57338, and GSE76701, were integrated with the human cardiac single-cell dataset GSE145154. Differential expression analysis was first performed to identify lysophagy-related differentially expressed genes (DEGs). Candidate hub genes were then screened using support vector machine-recursive feature elimination (SVM-RFE) and least absolute shrinkage and selection operator (LASSO) regression. Functional enrichment analysis, Gene Set Enrichment Analysis (GSEA), immune infiltration assessment, single-cell transcriptomic mapping, and regulatory network analysis were subsequently conducted. The expression profiles of the selected genes were validated in a murine HF model, and VAMP8 overexpression assays were performed in H9c2 cells. Results: Five hub genes, namely VAMP8, STX2, MCOLN1, DERL1, and PTP4A2, were consistently and markedly decreased in failing myocardial tissue. These genes were mainly linked to SNARE-dependent vesicle trafficking and lysophagy regulation. A diagnostic model incorporating these hub genes demonstrated good discriminatory performance in both the training dataset and a small independent validation cohort, supporting further evaluation of their potential diagnostic value. Single-cell analysis further indicated that these genes were primarily enriched in cardiac FOLR2⁺ tissue-resident macrophages (TRMs). Pseudotime and cell–cell communication analyses associated this module with FOLR2⁺ TRM cell states and predicted interactions with cardiac stromal cells. In the HF mouse model, the mRNA levels of all five hub genes were decreased, with concurrent reductions in VAMP8, MCOLN1 and DERL1 protein expression. In Ang II/LLOMe-induced H9c2 cells, VAMP8 overexpression was associated with reduced cardiomyocyte injury, attenuation of changes in the abundance of lysosome- and autophagy-related proteins, and fewer ultrastructural abnormalities, suggesting a potential cardioprotective effect. Conclusions: VAMP8, STX2, MCOLN1, DERL1, and PTP4A2 were identified as candidate molecular markers of HF that reflect alterations in a lysophagy- and vesicular-transport-related program associated with FOLR2⁺ tissue-resident macrophages. These findings provide new insights into immune-microenvironment remodeling in HF and suggest potential directions for mechanistic and therapeutic investigations. Full article

The upcoming proliferation of Automated Vehicles (AVs) above Level 3 fundamentally disrupts established communicative conventions between road users and vehicles, and external Human–Machine Interface (eHMI) emerges as the primary channel for conveying vehicle intent to pedestrians, cyclists, and other drivers. Despite the standardisation of the marker lamp of AVs and the growing research activity since 2016, no internationally harmonized eHMI standard has been established as of early 2026. This Systematic Literature Review (SLR), following the PRISMA 2020 protocol, synthesizes empirical and technical findings from 149 peer-reviewed English journal articles spanning the decade from 2016 to 2026, from Web of Science, Scopus, IEEE Xplore, and Google Scholar. The review covers scenario design, test methodologies, participant demographics, eHMI modalities, and performance evaluation measures by mapping, coding, and presenting in a structured framework the reviewed papers. The key findings are as follows: (1) 13 use cases (50%, out of 26) still need to be further studied; (2) vehicle kinematics remain a primary determinant of crossing decisions, with eHMI signals serving as confirmatory rather than primary cues in many scenarios; and (3) cross-cultural and demographic diversity in empirical studies remains critically insufficient for global regulatory purposes. We synthesize these findings into a structured framework of evidence-based recommendations for international eHMI standardisation organizations and identify critical research gaps requiring resolution before comprehensive standards can be enacted. Full article

Advances in machine learning, predictive analytics, and clinical prediction modeling have accelerated the development of algorithmic tools for estimating reproductive outcomes after cancer treatment. In female oncofertility counseling, these models may support individualized assessment of treatment-related amenorrhea, premature ovarian insufficiency, and fertility risk, thereby improving risk communication and timely fertility-preservation referral. However, their use raises ethical concerns beyond predictive accuracy. This narrative review examines algorithmic prognostication in female oncofertility counseling, focusing on predictive uncertainty, surrogate reproductive endpoints, missing data, heterogeneous datasets, limited external validation, algorithmic bias, reproductive inequity, and the influence of algorithmic authority on patient autonomy and shared decision-making. We argue that predictive algorithms should be understood as decision-support tools rather than determinants of reproductive futures. Responsible implementation requires transparency, explainability, fairness assessment, ongoing validation, and meaningful human oversight. Algorithmic risk estimates should be communicated as conditional and contextual probabilities within patient-centered counseling, ensuring that predictive tools support informed, transparent, and value-concordant fertility-preservation decisions for women facing cancer treatment. Full article

Smart meters are the core terminals for distribution network data acquisition in smart cities, yet their collected data commonly suffer from quality issues caused by harsh operating environments, communication failures, hardware degradation, and human factors. This paper presents a systematic review of anomaly detection and data repair methods for smart meter data based on a critical analysis of many publications. First, we characterize five typical anomalies—sudden jumps, reading stagnation, reverse readings, pulse spikes, and gradual drifts—from physical root causes to data manifestations and provide unified mathematical definitions with explicit traceability to the existing literature. Additional anomaly types including meter replacement jumps, data duplication from retransmission, complete missing segments, and timestamp errors are also discussed to present a more complete picture of operational data quality challenges. Second, existing anomaly detection methods are systematically reviewed and classified into four categories—statistical, machine learning, deep learning, and dedicated time-series methods—with representative studies, quantitative performance metrics, and scenario-specific applicability examined for each. Third, data repair approaches are reviewed across four categories—traditional interpolation, matrix completion, generative models, and time-series prediction—with systematic comparison of their accuracy and limitations across different anomaly types and durations. Based on the synthesized evidence, we identify three cross-cutting structural limitations that persist across method categories: the performance ceiling of data-only detection without physical constraint embedding, the open-loop architecture that separates detection from repair and allows error propagation, and the exclusive reliance on statistical error metrics that fails to distinguish physically plausible repairs from those violating conservation laws. To address these gaps, we discuss a physics-guided integrated framework incorporating physical constraint embedding, joint anomaly diagnosis, scenario-adaptive repair, and posterior verification as a promising forward-looking direction. Finally, open challenges and future research directions are outlined, including parameter adaptation in unlabeled scenarios, multi-source data fusion for physical disambiguation, new power system extensions, explainable AI integration, edge-computing deployment, and standardized benchmark development. This review provides a comprehensive theoretical reference and technical roadmap for smart meter data quality research in the context of smart city energy systems. Full article

Industrial operations increasingly face high-stakes decisions that involve people, data streams, simulations, and control systems. Urgent sessions often require external expertise, retrieval of documents and live telemetry, running what-if simulations, and verifying safety constraints. These scenarios highlight the need for secure interoperability, explainable decision support, and human-in-the-loop control. This paper presents a proposal of a technology-agnostic reference architecture that builds on Industry 4.0 frameworks by incorporating the human-centric, resilient, and sustainable principles of Industry 5.0. Its intelligent layer enables the new approach to human involvement in the process, facilitating meaningful human–machine collaboration. The proposed research provides a practical and conceptual framework for systems engineers, industrial software architects, and operations managers seeking to transition legacy operational plants into human-aligned ecosystems. Its feasibility is evaluated through a simulation-based underground mining testbed, where heterogeneous data sources and communication protocols are integrated into a common operational environment. The proof of concept shows how telemetry, data storage, machine learning models, and operator feedback can be combined to support auditable, explainable, and human-contestable industrial decisions, demonstrating the classification accuracy, remaining useful life forecasting capabilities, and enhanced recommendation precision enabled by iterative operator feedback loops. Full article

To address the difficulty of directly incorporating crop growth-stage information into industrial control processes and the limited adaptability of control parameters to different developmental stages in conventional greenhouse fertigation management, this study developed a vision-based growth-stage determination and PLC-based fertigation parameter invocation system for greenhouse blueberry cultivation. The system integrated greenhouse blueberry image acquisition, edge-based visual recognition, STM32-based encoding conversion, PLC control, human–machine interaction, and actuator linkage. Image samples were collected from greenhouse blueberry plants, whereas system-level linkage verification was conducted on a small greenhouse prototype platform. The edge vision module was used to output preliminary blueberry growth-stage labels, while environmental and substrate sensor data were used for sensor status verification and control safety validation. The final growth-stage label was converted by the STM32 unit into a discrete coded signal and then transmitted to the PLC. Based on a predefined stage-strategy table, the PLC invoked the corresponding target parameters and drove the irrigation, fertilizer delivery, supplemental lighting, ventilation, and shading devices for coordinated control. The image-level stage classification evaluation based on an independent test set showed that different lightweight YOLO classification models exhibited different performance levels in identifying the major growth stages of blueberry. YOLO11n-cls achieved the highest Accuracy and Macro F1-score, reaching 85.71% and 84.81%, respectively. YOLOv8n-cls achieved an Accuracy, Macro F1-score, and Macro AP of 80.95%, 81.10%, and 91.25%, respectively, showing a favorable balance between model size and recognition performance. The confusion matrix indicated that misclassifications mainly occurred between the fruit expansion stage and the ripening stage, reflecting the morphological continuity of blueberry fruit development during the transitional period. The system linkage test results showed that blueberry growth-stage labels could be output by the edge vision terminal, converted by the STM32 unit, read by the PLC, and used for stage-specific target parameter invocation. Sensor acquisition, HMI display, and actuator response were completed cooperatively. The single determination and output time of the edge terminal was 500–1000 ms, and the remote-control response delay was 0.3–1.0 s. No obvious communication interruption, command loss, or abnormal shutdown occurred during system operation. These results indicate that blueberry growth-stage recognition results can serve as input conditions for PLC parameter invocation and device-control testing on a small greenhouse prototype platform. This study did not conduct a complete closed-loop cultivation experiment under real production greenhouse conditions or establish long-term blueberry cultivation control treatments. Therefore, no quantitative conclusions are drawn regarding water and fertilizer use efficiency, fertilizer application reduction, plant physiological responses, yield, or fruit quality improvement. Full article

Background/Objectives: Artificial intelligence (AI) is increasingly being evaluated for ophthalmic diagnosis, screening, and triage, yet its role in paediatric eye care remains less established than in adult ophthalmology. This systematic review aimed to synthesise evidence on AI-enabled tools for paediatric ophthalmic diagnosis, screening, triage, surveillance, and referral, with an emphasis on diagnostic performance, safety, workflow integration, equity, and implementation readiness in primary, community, and primary care-relevant settings. Methods: A PRISMA-guided systematic review was conducted using MEDLINE, Embase, Web of Science, Scopus, and IEEE Xplore from inception to 30 March 2026. Eligible studies evaluated AI or machine-learning tools for children and adolescents aged 0–18 years in relation to paediatric eye conditions. Study selection and data extraction were undertaken independently by reviewers, with disagreements resolved by consensus or third-reviewer adjudication. Methodological and reporting quality was evaluated using an author-adapted six-domain rubric informed by APPRAISE-AI. Diagnostic-accuracy studies were assessed using an author-adapted QUADAS-2 framework incorporating QUADAS-AI-informed AI-specific considerations, the prediction-model study was assessed using PROBAST+AI, and the non-randomised treatment-effect study was assessed using ROBINS-I. The public dataset descriptor was evaluated separately using an author-developed dataset-quality, representativeness, and applicability framework. Because of clinical and methodological heterogeneity, findings were synthesised thematically. Results: Twelve empirical studies and one public dataset descriptor were included, covering retinopathy of prematurity, retinoblastoma, amblyopia risk, myopia, congenital cataract, and visual-acuity assessment. AI systems frequently demonstrated promising diagnostic or screening performance, including sensitivity-first detection of treatment-requiring retinopathy of prematurity, high discrimination for retinoblastoma activity, and strong myopia prediction using fundus images. Several studies supported feasibility in neonatal, school, and community workflows using smartphone-based imaging, task-shifted operators, tele-referral, and human-in-the-loop review. However, external and temporal validation, calibration, patient-level reporting, subgroup and fairness assessment, and economic evaluation were limited. Conclusions: AI-enabled tools show promise for supporting selected paediatric ophthalmic screening, triage, and surveillance pathways, particularly when combined with image-quality control, explicit escalation, and human oversight. However, confidence in the reported performance is limited by single-centre studies and enriched samples, small numbers of clinically important cases, heterogeneous analytical units, potentially optimistic aggregation procedures, limited external or temporal validation, incomplete calibration, and absent fairness analyses. Routine autonomous implementation remains premature. Full article

The modern multi-domain battlespace increasingly demands cost-effective, persistent platforms for Forward Air Control (Airborne) (FAC(A)) and Close Air Support (CAS) missions. While utilizing Commercial Derivative Aircraft (CDA) presents a viable alternative to high-maintenance military assets, the specific aerodynamic, ergonomic, and cognitive workload limitations encountered during the transition across the civil–military “airworthiness seam” remain a significantly underexplored gap in contemporary aerospace literature. To address this gap, a comprehensive empirical flight test campaign was executed on the LX7-135 turboprop to evaluate its tactical mission suitability. Employing the Cooper–Harper Handling Qualities Rating and Bedford Workload scales, and guided by military specifications (MIL-HDBK-516C, MIL-F-8785C), the study systematically assessed the aircraft’s pure performance, unaugmented flight dynamics, and human–machine interface during simulated combat scenarios, including dynamic 9-Line briefings and kinetic “Box Pattern” delivery profiles. Flight test data indicated 12 “SATISFACTORY” parameters, highlighting climb rates, extended endurance, and heavily damped short-period and Dutch roll modes optimal for target tracking. Conversely, the evaluation identified 4 “UNSATISFACTORY” and 10 “TOLERABLE” deficiencies—chiefly a single-door egress bottleneck, restricted stick clearance, degraded longitudinal static stability, and the absence of secure tactical communications. Although these constraints elevated pilot cognitive workload during multi-axis tasks, the LX7-135 demonstrates potential suitability for further development for the FAC(A) role, subject to the successful implementation and subsequent flight-test verification of the identified critical engineering modifications and specialized training syllabi. Full article

Building materials and their spatial distribution play a significant role in determining the outcomes of human-caused and natural disasters in urban and peri-urban areas. However, building-level data on building and roofing materials are scarce. Here, we explore the feasibility and performance of a Convolutional Neural Network (CNN) model using spectrally transformed high-resolution multispectral imagery to map roofprints (i.e., classifying and delineating roofing materials at the building footprint-level) in Washington, District of Columbia (D.C.) and Denver, CO, United States. To generate consistent training data, we integrate geospatial vector data of individual building footprints with real estate industry-derived building-level roofing material data to create labeled image data from Planet SuperDove imagery. We compare the CNN classifier to a pixel-based machine learning (ML) model to demonstrate the capability of our roofprints mapping approach. With F1-scores ranging from 0.56 to 0.95 for the most common roof material classes, the CNN model outperformed the pixel-based ML classifier by 15% and 17% in Washington, D.C., and Denver, respectively. Results demonstrate within-domain robustness for the studied metropolitan areas, which are characterized by differing building densities, roof morphologies, and material patterns. While cross-region transferability was not evaluated, our findings provide a controlled comparison of pixel-based and context-aware approaches for rooftop material mapping and highlight the importance of hierarchical representations that integrate spectral information with roof texture, edge characteristics, spatial arrangement, and neighborhood context for improving classification performance. Accurately mapping building materials has the potential to advance urban planning and environmental policies, including assessments of heat exposure, energy demand, as well as hazard risk and community resilience. Full article

Traditional manual 10 kV live-line maintenance is accompanied by high personal risks and incomplete safety protection, while overall operational efficiency is limited. This paper develops an intelligent live-working robot based on a tracked insulated spider aerial vehicle. The system is equipped with vertical lifting modules and a pair of 6-DOF insulated manipulators to form a 13-DOF integrated motion platform. Binocular cameras, LiDAR, real-time insulation monitors, and electromagnetic interference detectors are integrated as multi-modal sensing hardware to achieve high-precision positioning of overhead lines and pole fittings. A master–slave collaborative control strategy combined with mixed reality (MR) and visual auxiliary force feedback is proposed to coordinate the tracked chassis, lifting structure, and dual manipulators. A four-dimensional full-cycle safety guarantee framework is further constructed, covering insulation protection, anti-interference communication, human–machine risk avoidance, and full-task supervision to support real-time early warning and motion interlock. Field tests on actual 10 kV distribution lines verify stable positioning performance under controlled test conditions, and no safety accidents occurred in all trials. The designed robotic system provides an optional technical scheme for intelligent unmanned live-line maintenance of distribution networks. Full article

The formation mechanisms of Urban Vitality have been constrained by the limitations of traditional linear driving hypotheses, and the fragmented analysis of subjective and objective factors. Integrating the explainable machine learning model XGBoost-SHAP with multi-source geospatial data, this study constructs a systematic analysis framework at the community scale, comprising 275 community units across five administrative districts in Changsha. It constructs a systematic analysis framework that unifies objective environmental conditions and subjective perceptions—a deliberate departure from the fragmented approaches dominant in previous vitality research. Through this objective-subjective integrated lens, it explores the spatial patterns, non-linear driving mechanisms, and variable interaction effects of Urban Vitality. The XGBoost model achieves a cross-validated R² of 0.794 and an RMSE of 0.031, ensuring interpretative reliability for exploring non-linear mechanisms. The results indicate that Urban Vitality exhibits a spatial pattern characterized by “high-value aggregation in the core, gradient decay in the periphery, and local fragmentation,” with a significant siphon effect observed in the core area. Partial Dependence Plot (PDP) analysis reveals that the impacts of variables on vitality can be categorized into four patterns: continuous upward, threshold leap, inverted U-shaped, and weak or sample-concentrated. Univariate dependence plots further delineates fine-grained threshold effects, including “threshold triggering, nterval suitability, high-value suppression, and co-occurrence signals.” Furthermore, bivariate interactions reveal four synergistic mechanisms: Building Density must match road network support; Functional Aggregation should synergize with locational value; transportation nodes must integrate with activity-support capacity; and Street View quality and human demand mutually regulate each other. The conclusion asserts that urban stock renewal must transcend the mindset of single-factor maximization and shift towards a precision governance approach of “threshold activation, synergistic matching, and zoning intervention,” thereby providing a quantitative decision-making basis for human-oriented, fine-grained urban regulation. Full article

Artificial intelligence (AI) is deeply integrated into daily life. Emerging evidence suggests AI may help change the dynamics of social relationships by influencing social interactions, connectivity, and interpersonal relationships, and by providing new avenues for communication and contributing to improved social well-being. Therefore, this review aims to explore the potential of artificial intelligence (AI) technologies as a tool to enhance social health, focusing on current applications, advantages, challenges, and ethical considerations associated with their implementation, as well as opportunities for future development. The literature on the relationship between the connectedness of social health dimensions and AI as a tool to better understand how interactions with AI technologies may influence social well-being. In this current review, key terms such as “Artificial Intelligence”, “Social Health”, “social inequalities”, “AI algorithm”, “AI technology”, “social connection”, “digital communication”, “social participation”, “social support”, “social isolation”, “loneliness”, “mental wellbeing”, were used to search relevant literature on Google Scholar, PubMed, Scopus and Web of Sciences. In addition, relevant aspects of the multidimensional impacts of AI on social health dimensions are also discussed. The use of AI technologies by individuals within societies was found to hold profound potential to reshape social health through enhancing social relationships, bridging communication gaps in diverse populations, stimulating social dynamics, and understanding human emotions. It may contribute to reducing social inequalities, promoting equity, accommodating individual differences, and enhancing the effectiveness of many tasks in the social and health care systems through deep learning, natural language processing, and machine learning techniques. This reduces social exclusion and increases accessibility and quality of health and social services. However, AI has also posed distinguishable challenges to its adoption, specifically in terms of data quality, privacy and security, algorithmic bias, ethical issues, public trust and acceptance, and regulatory and policy gaps. Evidence suggests that building public trust in the future of AI in social health requires interdisciplinary collaboration among health providers and professionals, social scientists, community members, and policymakers. Such collaboration is crucial to ensure that AI platforms do not perpetuate social inequalities or biases by maintaining transparency, explainability, and demonstrated effectiveness. In conclusion, the integration of AI into social health dimensions holds promise for social health transformation. As we move forward, several key areas need to be addressed to develop a robust governance and regulatory framework, along with ethical guidelines to ensure privacy protection, respect for human rights, transparency, and the promotion of the common good. Full article

Long-term wildfire susceptibility mapping represents a significant component of disaster prevention and the protection of human communities, public health, and local ecosystems. In this study, a wildfire inventory was developed through multi-sensor fusion of satellite data (MODIS and VIIRS), comprising 153,305 fire events across China for the period 2001–2024. In addition to historical incidents, 14 predictive variables were processed, representing geomorphological, climatological, hydrological, vegetative, and anthropogenic conditions. This study evaluates long-term spatial wildfire susceptibility based on long-term mean environmental and climatic conditions. Methodologically, the research applies six models from machine learning (ML), deep learning (DL), and transformer-based approaches: Random Forest (RF), Extreme Gradient Boosting (XGBoost), Deep Neural Network (DNN), Fourier Multi-Layer Perceptron (F-MLP), Kolmogorov–Arnold Network (KAN), and Feature Tokenizer (FT) Transformer. The results were integrated into an ensemble susceptibility map with a spatial resolution of 500 m using Geographic Information Systems (GIS), indicating that 7.4% of China’s territory is classified as having a very high wildfire susceptibility. In addition to the national-scale assessment, a local differentiation was conducted across 34 province-level divisions, revealing that Fujian Province (86.8%) and the Guangxi Zhuang Autonomous Region (82.9%) had the largest shares of areas classified as high and very high wildfire susceptibility. Performance evaluation under spatial block-based validation demonstrated that the Random Forest model achieved the highest predictive power, with an area under the curve (AUC) of 87.8%, followed by XGBoost (87.3%) and Fourier MLP (86.6%). Based on the combined SHAP (Shapley additive explanations) analysis of all applied models, soil moisture, elevation, and terrain slope were identified as the most influential factors affecting wildfire occurrence in China. Overall, the findings contribute to more effective wildfire prevention and risk management strategies at both the local and national levels. Full article

Inertial motion sensing plays an important role in real-time human–machine interaction applications, including interactive systems, virtual environments, and motion-controlled interfaces, where low latency and accurate motion tracking are important. This paper presents the design and implementation of an embedded inertial sensing system that acquires, processes, and transmits motion data from consumer-grade inertial measurement units (IMUs) under real-time constraints. Rather than introducing a new sensor fusion algorithm, the contribution lies in a systems-oriented methodology comprising a predictive clock-advancement mechanism that prevents cumulative timing drift, an automated matrix-based calibration procedure for hardware-agnostic deployment, and a benchmarking framework for end-to-end real-time system evaluation. Implemented on a resource-constrained embedded platform, the framework integrates sensor acquisition, lightweight filtering, sensor fusion, and real-time orientation estimation within a single processing pipeline. Motion data are transmitted using the CemuHook UDP (User Datagram Protocol) motion protocol (DSU) to demonstrate interoperability with existing motion-control software while maintaining low end-to-end latency and stable throughput. Experimental results show stable sampling frequency, low communication latency, accurate orientation estimation, and low computational overhead. The presented system provides an embedded inertial sensing framework that can be adapted to a range of real-time motion-sensing applications beyond the communication protocol used for demonstration. Full article

Agriculture 5.0 represents a breakthrough transformation from Agriculture 4.0, addressing the needs for safety, sustainability, and resilience in human–robot collaboration in agriculture. By integrating technologies such as artificial intelligence, digital twins, and big data, it achieves breakthroughs in three areas: perception, cognition, and execution. As carriers of agricultural technology, agricultural automated guided vehicles (AGVs) are an indispensable part of agricultural activities and play a crucial role in agricultural production. In the actual operation of AGVs, intelligent perception is a core technological prerequisite for enabling the communication and interaction among machines, humans, and the environment. However, due to the complexity and variability of agricultural environments, intelligent perception technology remains a highly challenging task. While existing reviews have focused on isolated aspects of agricultural automation, a comprehensive synthesis of intelligent perception technologies for agricultural AGVs within the holistic, human-centric framework of Agriculture 5.0 is notably lacking. This review bridges this gap by systematically analyzing and comprehensively reviewing recent advances in intelligent perception for agricultural AGVs, covering multi-sensor technologies, visual perception and target recognition, positioning and navigation algorithms, as well as applications such as path planning, multi-robot coordination, and human–robot collaboration. Furthermore, this paper delves into the potential challenges and future development trends of intelligent perception technology in the context of Agriculture 5.0, highlighting the transformative potential of these technologies in promoting multimodal fusion and addressing safety issues in human–robot collaboration. In the context of Agriculture 5.0, with the continuous advancement of intelligent perception technologies and the ongoing improvement of agricultural intelligent equipment, a human-centered, highly sustainable, resilient, data-driven agricultural production system will ultimately be formed in the future. Full article