Saved Queries

by Yajie Liu, Jiangchun Chen, Jian Bao, Longpeng Ding, Hongfei Yang, Yuyang Liu, Yufeng Li, Haiyang Lu and Guangshang Ge

Agriculture 2026, 16(11), 1142; https://doi.org/10.3390/agriculture16111142 - 22 May 2026

Abstract

The semi-structured vineyard environments contain numerous irregular obstacles, posing stringent requirements on the navigational safety and trajectory tracking accuracy of mobile robots. To address this challenge, this study first optimizes the A* algorithm at the global planning layer by incorporating a composite turning-cost evaluation model and a heuristic dynamic weighting strategy, thereby effectively enhancing search efficiency and path smoothness. Building upon this, a local planning method is further developed by integrating an adaptive sampling mechanism with high-order interpolation-based kinematic continuity constraints and a heading-rate-driven velocity smoothing strategy. This enables the robot to maintain a safe clearance from obstacles in dynamic environments, thereby significantly enhancing the smoothness of obstacle avoidance maneuvers. Both simulation and field experiment results demonstrate that the improved global planning algorithm reduces the number of critical turning points and the total turning angle by up to 18.0%. Across three typical path scenarios, the proposed fusion method reduces the robot’s positional deviation by up to 21.8% and the heading angle deviation by up to 29.6%, while concurrently increasing the safe clearance from obstacles by 42.0%. These findings suggest that the proposed framework establishes a viable algorithmic foundation for improving the navigation accuracy, obstacle avoidance stability, and operational safety. Full article

(This article belongs to the Section Agricultural Technology)

30 pages, 5901 KB

Open AccessArticle

Hybrid Analytical and Simulation-Based Approach for Workspace Verification of a Pneumatic Upper Limb Exoskeleton

by Nikita Mayorov, Daniil Teselkin, Denis Dedov and Artem Obukhov

Sensors 2026, 26(11), 3308; https://doi.org/10.3390/s26113308 - 22 May 2026

Abstract

The design of active pneumatic upper limb exoskeletons is complicated by the challenge of reliably determining a kinematically safe workspace. Existing analytical kinematic methods are not sufficient to predict geometric collisions between elements of closed kinematic chains, which poses risks of mechanical damage and threats to user safety during exoskeleton operation. This paper proposes a hybrid algorithm for verifying the workspace of a pneumatic exoskeleton, combining analytical modelling in MATLAB R2020b based on the Product of Exponentials (PoE) method with high-performance static simulation in the Unity environment. At the initial stage, a discrete set comprising 758 million positions of the upper exoskeleton manipulator was generated. Subsequently, a multithreaded two-stage filtering process was implemented: analytical verification of rod stroke limits and angular constraints, followed by the detection of physical intersections of solid-state meshes using the PhysX engine. The results indicate that while the analytical model filters out 99.6% of invalid configurations. Yet, among the remaining positions—formally correct from a mathematical standpoint—up to 50% lead to critical geometric collisions or breaks in the kinematic chain. The computational efficiency of the proposed architecture enabled full static workspace verification in under 20 min. A reachable zone topology was established, revealing pronounced asymmetry and the presence of a “manoeuvrability core” in the user’s anterior hemisphere. The developed algorithm generates a verified set of kinematically safe exoskeleton states, providing a foundation for the kinematic safety layer of a hierarchical control system. These findings demonstrate the necessity of complementing analytical kinematics with physical collision detection when designing hybrid kinematic mechanisms, and the approach can be applied to verify collision-free movement trajectories in various robotic systems. The approach can be applied to verify collision-free movement trajectories in simulation, with physical validation deferred to future work. Full article

(This article belongs to the Section Intelligent Sensors)

►▼ Show Figures

Figure 1

31 pages, 1354 KB

Open AccessSystematic Review

Planning for Experience: A Systematic Review of the Link Between the 15-Minute City and Neighbourhood Satisfaction

by Hilal Çepni and João de Abreu e Silva

Urban Sci. 2026, 10(6), 295; https://doi.org/10.3390/urbansci10060295 - 22 May 2026

Abstract

This systematic literature review comparatively examines two largely parallel research streams: the 15-minute city (15MC) and neighbourhood satisfaction (NS), identifying their overlaps, divergences, and unresolved tensions. It combines a bibliometric analysis of two thematic corpora with an in-depth full-text synthesis of empirical studies, following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) reporting practices. The bibliometric results show a rapidly expanding 15MC field since 2020, centered on proximity, accessibility, and sustainability, while NS research has a longer tradition focused on subjective well-being and perceived neighbourhood experiences, including environmental comfort, social cohesion, safety, and neighbourhood quality. Across the literature, the synthesis shows that spatial proximity and measured accessibility are important but insufficient to explain NS without also considering service quality, environmental comfort, perceived safety, and social relations. The review highlights persistent gaps in linking objective accessibility metrics with subjective outcomes, as well as mismatches in neighbourhood definitions and spatial scales. It also identifies limited evidence on temporal dynamics, population heterogeneity, and the social effects of proximity planning, including gentrification and displacement. Building on five conceptual bridges, the review proposes an integrated framework connecting objective proximity-based planning conditions with subjective, social, and contextual determinants of neighbourhood satisfaction. Full article

(This article belongs to the Section Urban Planning and Design)

33 pages, 2950 KB

Open AccessArticle

State-of-Health and Remaining-Useful-Life Estimation of Lithium-Ion Batteries Using Axial-Embedding Transformer–Bidirectional Long Short-Term Memory Optimized by an Improved Newton–Raphson-Based Optimizer

by Yonggang Wang, Kai Cui and Haoran Chen

Batteries 2026, 12(6), 187; https://doi.org/10.3390/batteries12060187 - 22 May 2026

Abstract

Accurate estimation of the state of health (SOH) and prediction of the remaining useful life (RUL) of lithium-ion batteries (LIBs) are critical for ensuring system reliability and safety across diverse energy storage applications. This paper proposes a hybrid deep learning framework that integrates an axial-embedding Transformer (AxEmbTrans) encoder and a bidirectional LSTM (BiLSTM) module for the joint estimation of SOH and RUL. The AxEmbTrans encoder employs axial attention with abstract embeddings to capture global dependencies among multidimensional health features at reduced computational complexity compared to standard self-attention, while the BiLSTM models local temporal dynamics and short-term degradation fluctuations across consecutive cycles, with its bidirectional structure enhancing robustness against transient noise. Informative health features are extracted from charge–discharge curves, grouped into temporal, energy, and thermal categories, and fused using local linear embedding (LLE) for nonlinear dimensionality reduction. An improved Newton–Raphson-based optimizer (INRBO) is introduced to automatically tune the framework’s key hyperparameters, including the hidden dimension, number of attention heads, number of BiLSTM units, and learning rate, incorporating directional similarity modulation and multi-elite guidance to overcome the convergence instability of the standard NRBO. Extensive experiments on NASA and Maryland datasets demonstrate that the proposed method consistently outperforms baselines in both SOH and RUL prediction, achieving higher accuracy, improved robustness, and better cross-condition generalization. Full article

(This article belongs to the Section Lithium-Ion and Solid-State Batteries)

21 pages, 754 KB

Open AccessReview

Essential Oils: Chemistry and Mechanisms of Anticonvulsant Action

by Lígia Salgueiro, Mónica Zuzarte, Jeremias Justo Emídio, Diogo Vilar da Fonsêca and Damião Pergentino de Sousa

Int. J. Mol. Sci. 2026, 27(11), 4691; https://doi.org/10.3390/ijms27114691 - 22 May 2026

Abstract

Essential oils have attracted increasing attention due to their bioactive properties. This review focuses on their anticonvulsant potential by exploring the relation between the chemical composition of essential oils and the mechanism of action underlying this effect. Evidence from in vivo and ex vivo studies is presented to identify structure–activity relations and to distinguish well-supported effects from preliminary findings. Moreover, as essential oil’s quality is vital to ensure safety and efficacy in pharmacotherapeutic approaches. For this reason, factors including extraction and analytical methods as well as authenticity assessment are discussed due to their impact on pharmacological consistency and reproducibility. Overall, this review highlights key compounds and mechanisms contributing to anticonvulsant activity, identifies current limitations in the literature, and outlines priorities for future research aimed at validating essential oils as potential complementary therapeutic agents in seizure management. Full article

(This article belongs to the Special Issue Neurological Mechanisms of Action of Natural Products)

10 pages, 341 KB

Open AccessArticle

Choline Alfoscerate in the Treatment of Subthreshold Depression in the Elderly: A Pilot Study (CARTESIO)

by Filippo Fleishhacker, Annamaria Bonfanti, Nicolò Granata, Claudio Mencacci, Mario Mangrella, Roberto Piazza, Ilaria Coco and Giancarlo Cerveri

J. Clin. Med. 2026, 15(11), 4037; https://doi.org/10.3390/jcm15114037 - 22 May 2026

Abstract

Background: Subthreshold depression is a prevalent condition among the elderly and often remains untreated due to the limited efficacy and poor tolerability of standard antidepressants. Choline alfoscerate, a cholinergic precursor, is indicated for the treatment of a condition, pseudodepression in the elderly, that is currently clinically classified as subthreshold depression in older adults. Also, choline alfoscerate has shown neuroprotective and antidepressant-like effects. Objective: This pilot study aims to evaluate the efficacy and safety of choline alfoscerate in elderly patients with subthreshold depressive symptoms, using contemporary diagnostic criteria and standardized outcome measures. Methods: Seventeen patients aged ≥65 years were enrolled in an open-label, single-arm study and received 1200 mg/day of choline alfoscerate for 8 weeks. Clinical and neuropsychological assessments were performed at baseline, after 4 weeks, and at the study’s end. Results: A statistically significant improvement was observed in depressive symptoms, as reflected by reductions in HAMD-17 (p < 0.001) and GDS-15 scores (p < 0.05), as well as in overall clinical severity assessed by the Clinical Global Impression–Severity scale (CGI-S, p < 0.05). No significant changes were noted in cognitive performance (MOCA) or apathy (AES-I). The treatment was well tolerated. Conclusions: Choline alfoscerate may represent a potentially safe and promising therapeutic option for subthreshold depression in older adults. However, given the exploratory nature of this open-label pilot study, these findings should be considered preliminary and hypothesis-generating and require confirmation in randomized controlled trials. Full article

(This article belongs to the Section Mental Health)

►▼ Show Figures

Figure 1

17 pages, 2359 KB

Open AccessArticle

Risk Evaluation for Wear of Deep Well Vertical Filling Pipeline Based on Cloud Model and Distance Discriminant Weighting Method

by Jiang Guo, Jing Wu, Jiachuang Wang and Mingjian Huang

Mathematics 2026, 14(11), 1799; https://doi.org/10.3390/math14111799 - 22 May 2026

Abstract

With the rapid development of the world economy in recent years, the mineral resources in the shallow part of the Earth can no longer meet the needs of mankind, and resource development is continually moving into the deep part of the Earth. The filling method, in particular, has gradually been employed for the treatment of mining goaves in response to the requirements of environmentally sustainable development. As an important part of the filling system, the wear and tear of the deep filling pipeline is of great significance to the normal operation of the system, the safe production of the mine and the reasonable protection of the environment. In this paper, the wear situation of the deep well vertical filling pipeline is selected as the analysis angle to carry out the research, and the risk assessment model is constructed by combining the distance discriminant weighting method and the cloud model for the uncertainty of the wear risk grading assessment. Firstly, 11 quantitative factors and three qualitative factors were selected as evaluation indicators and employed as cloud model variables. Appropriate cloud model digital features were picked based on cloud model theory, to construct the cloud model of each indicator. Secondly, the distance discriminant weighting method is introduced to obtain the weight of each indicator, and the risk level of the vertical filling pipeline in deep wells is obtained by calculating the comprehensive certainty of the risk evaluation object belonging to different levels. Finally, the model was applied to Dongguashan Copper Mine, and the model calculation results were analyzed and compared with the actual wear situation. The results show that the model transforms the ambiguity and randomness into a certain quantitative value of certainty, completing the map from qualitative to quantitative. This method introduces a new idea and method for dealing with similar problems of vertical filling pipes in deep wells. Full article

26 pages, 9441 KB

Open AccessArticle

Evaluation of Water Status and Thermal Characteristics of Dried Carrot Half-Slices in Correlation with Physicochemical and Sensory Properties

by Anna Ignaczak, Łukasz Woźniak, Mariola Kozłowska and Hanna Kowalska

Molecules 2026, 31(11), 1789; https://doi.org/10.3390/molecules31111789 - 22 May 2026

Abstract

The aim of the study was to investigate the effect of enriching carrot slices by NFC (not from concentrate) juices from chokeberry (CH), sea buckthorn (SB), cherry (CHE) and carrot (CA) before microwave-vacuum (MVD) and freeze-drying (FD) carrot on the physicochemical and thermal properties. While water activity (AW) was not dependent on enrichment treatment but only on drying method, NFC juices significantly enriched carrot slices with biocomponents. Freeze-dried samples, as a reference, had significantly lower AW than those dried by the MVD method. Both FD and MVD-dried samples had comparable polyphenol content and DPPH antioxidant activity (AA), but the MVD-dried samples exhibited higher ABTS antioxidant activity. Carrot enrichment in chokeberry and cherry juices resulted in up to six and 10 times higher TPC than in the raw material. In addition, samples enriched in these juices and dried with FD proved to be the most stable in terms of water state and glass transition temperature (61.4 and 69.6 °C) and water activity (approx. 0.10). In FTIR analysis, all samples exhibited similar spectral shapes, indicating similar chemical composition and functional group composition. Only in the spectral region below 900 cm⁻¹ were unique molecular vibrations induced by various organic compounds present. Enriching carrot in juices and MVD can lead to increased hardness (Fmax and breaking work), although this is associated with increased crispness, resulting from the microstructure with a large number of small pores, especially in MVD samples enriched with cherry, chokeberry, and carrot juices, with scores of 8.0–8.4 In this respect, the average crispness rating of the MVD samples (7.2) exceeded that of the FD samples (6.8). If there is a requirement for crunchiness in the future production of dried vegetables as snacks, changes in hardness should be prioritized, along with color and biocomponent content. Full article

(This article belongs to the Special Issue Advances in Physicochemical Properties of Innovative Food Products During Processing)

►▼ Show Figures

Figure 1

39 pages, 1158 KB

Open AccessArticle

Minification Integer-Valued Split-BREAK Process with Power Series Innovations and Application in Fire Safety Dynamics

by Vladica S. Stojanović, Nikola Mitrović, Kristina Tomović, Hassan S. Bakouch and Shuhrah Alghamdi

Axioms 2026, 15(6), 388; https://doi.org/10.3390/axioms15060388 - 22 May 2026

Abstract

This manuscript introduces a new class of count time series models, referred to as the minification integer-valued Split-BREAK (MIN–SB) process. The proposed framework extends the Split-BREAK modeling philosophy to the integer-valued setting and provides a flexible mechanism for capturing rare events, zero inflation, and structural regime changes frequently observed in safety-related data. The main stochastic properties of the MIN–SB process are derived, including stationarity conditions, explicit moment structure, and correlation dynamics. A key theoretical result reveals an implicit hidden Markov structure underlying the observable process, providing a structural explanation for zero clustering observed in rare-event count processes. Parameter estimation is developed using a simulated method of moments (SMM) approach based on zero-related statistics, and the asymptotic properties of the resulting estimators are established. A Monte Carlo simulation study demonstrates favorable finite-sample performance of the proposed estimation procedure. The practical usefulness of the model is illustrated through an empirical application to time series of injuries and fatalities caused by fire accidents in Serbia. The results show that the MIN–SB specification provides a flexible and accurate framework for modeling zero-inflated count processes arising in fire safety dynamics. Full article

(This article belongs to the Special Issue Mathematical and Statistical Methods and Their Applications, 3rd Edition)

36 pages, 34951 KB

Open AccessArticle

Evaluating the ESP32-S3 for Wi-Fi Penetration Testing Through the Development of Deauther32 and HackHeld32

by Stefan Kremser and Kalman Graffi

Sensors 2026, 26(11), 3287; https://doi.org/10.3390/s26113287 - 22 May 2026

Abstract

Wi-Fi security analysis and testing tools are vital to ensure the safety of wireless networks. Specialised hardware and software are needed to examine the underlying technology that connects our devices wirelessly. This article explores the feasibility of utilising the ESP32-S3 microcontroller as the basis for a low-cost, open-source, portable Wi-Fi penetration testing tool. By developing and evaluating the Deauther32 firmware, the project demonstrates key functionalities such as capturing and injecting frames to execute common Wi-Fi attacks, like beacon flooding and deauthentication. The developed HackHeld32 design complements the firmware by offering a compact and extendable handheld device, making the tool standalone and portable. These prototypes build upon previous work, the ESP8266 Deauther and the HackHeld Vega, by introducing significant improvements in functionality, usability, and hardware capabilities. This establishes a strong foundation for future development by demonstrating the potential of microcontroller-based solutions. These tools bridge the gap between accessibility for beginners and functionality for professionals by offering a cost-effective and portable solution for Wi-Fi security testing and beyond. Full article

(This article belongs to the Special Issue Security and Privacy Challenges in IoT-Driven Smart Environments)

►▼ Show Figures

Graphical abstract

38 pages, 2798 KB

Open AccessReview

Biochar Modulates the Dynamics of Legacy Nutrients in Enhancing Soil Health and Crop Productivity

by Manish Kumar, Shiv Bolan, Rakesh Kumar, Juhi Gupta, Dingjiang Chen, Hao Wu, Sarah Stackpoole, Nitika Chandel, Santanu Mukherjee, Manoj Chandra Garg, Srinithi Mayilswami, Kadambot H. M. Siddique and Nanthi Bolan

Land 2026, 15(6), 896; https://doi.org/10.3390/land15060896 (registering DOI) - 22 May 2026

Abstract

Most major crops in agricultural soils exhibit relatively low nutrient use efficiency for nitrogen (N), phosphorus (P), and potassium (K), often necessitating supplemental nutrient inputs to achieve sustainable yields. Furthermore, the increasing use of biowastes such as compost, manure, and biosolids, which frequently have nutrient ratios that do not match crop requirements, has contributed to excessive nutrient inputs and subsequent accumulation in soils. This situation has been further exacerbated by intensive farming practices involving multiple cropping cycles per season. Overuse of nutrients causes them to accumulate in the soil, creating a legacy nutrient pool. The application of biochar as soil amendment is considered a potential strategy to control legacy nutrients dynamics. The current review inspects the possible value of biochar in modulating legacy nutrient reserves in the soil, thereby increasing the bioavailability of nutrients and improving crop yield. This review discusses the search scope and synthesis approaches for the bibliometric methodological component through rigorous screening process (Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA)), focusing on journal articles published in last 20 years that specifically address legacy nutrient management. The significance of the economic and environmental effects of legacy nutrients and the insufficient knowledge of how biochar application influences nutrient dynamics in soil highlight the necessity for additional research to address current gaps. Full article

(This article belongs to the Section Land, Soil and Water)

►▼ Show Figures

Figure 1

25 pages, 1456 KB

Open AccessArticle

Thermodynamic Behavior of Onboard Hydrogen Storage Cylinders Under Real-Gas Conditions Using an Equivalent Thermal Conductivity Method for Multi-Layered Structures

by Heng Xu, Jia-Wen Liu, Xue-Li Li, Jia-Han Guo, Shu-Wei Chen, Yi-Ming Dai, Ji-Chao Li and Ji-Qiang Li

Fire 2026, 9(6), 214; https://doi.org/10.3390/fire9060214 - 22 May 2026

Abstract

The thermodynamic prediction of the fast refueling process for vehicular hydrogen storage cylinders faces the complex problem of modeling multi-layer composite walls. Drawing on the series thermal resistance principle, this paper introduces an equivalent thermal conductivity approach, simplifying the multi-layer structure into homogeneous material. Combined with the real-gas-state equation, a coupled thermodynamic framework combining zero-dimensional gas dynamics and one-dimensional cylinder wall heat transfer is developed. The comparison and verification with the 70 MPa fast charging experimental data have demonstrated that the proposed model exhibits sufficient accuracy and robustness for the problem. By comparing the temperature rise changes of different volume type-III gas cylinders, it was found that the surface area-to-volume ratio (A/V) was the primary geometric factor—the key geometric parameter that governs the temperature rise behavior. Larger volume gas cylinders exhibit more significant temperature rise due to their lower heat dissipation efficiency. A further comparison of the thermal response characteristics between Type-III and Type-IV cylinders demonstrates that the equivalent thermal conductivity is the dominant parameter determining the temperature rise behavior: The lower this coefficient, the stronger the limitation on the cylinder’s heat dissipation capacity, and the more pronounced the temperature rise. The proposed method not only ensures accuracy but also reduces the complexity of the modeling process, providing an efficient theoretical tool for optimizing the refueling strategy and conducting thermal safety assessment of vehicular hydrogen storage systems. Full article

(This article belongs to the Special Issue Clean Combustion and New Energy)

17 pages, 609 KB

Open AccessReview

Quorum Sensing Modulators as Antibiotic Alternatives in Animal Production: From Bacterial Signaling to Gut Health and Performance

by Chenxin Tang, Kehui Ouyang, Mingren Qu and Qinghua Qiu

Vet. Sci. 2026, 13(6), 507; https://doi.org/10.3390/vetsci13060507 - 22 May 2026

Abstract

In intensive animal production, the overuse of antibiotics has exacerbated bacterial antimicrobial resistance and environmental pollution. Together with gut microbiota dysbiosis and recurrent disease outbreaks, these challenges severely constrain the sector’s high-quality development. Quorum sensing (QS), a cell-density-dependent bacterial communication mechanism, can be modulated through agents that specifically inhibit or activate QS circuitry to regulate microbial community functions. Such QS modulators possess notable advantages, such as environmental benignity and high target specificity, and thus offer innovative strategies to decrease antibiotic reliance, enhance production efficiency, and reduce environmental emissions. This review examines QS modulators sourced from plants, microorganisms, animals, and synthetic processes, while highlighting key challenges such as environmental interference, resistance development, high costs, and the lack of standardized biosafety evaluations. Future research should focus on enhancing specificity, stability, affordability, and safety, with an emphasis on rational design, synergistic systems, improved manufacturing processes, and multi-target modulators. This review may provide a theoretical basis for translating QS-regulation technologies into farm-level applications, thereby advancing sustainable animal production and antibiotic-free husbandry. Full article

(This article belongs to the Section Veterinary Microbiology, Parasitology and Immunology)

63 pages, 885 KB

Open AccessReview

Large Language Model Benchmarks: A Taxonomy of Capabilities, Scientific Quality Assessment, and Saturation Analysis

by Rubén Gómez, Carlos E. Miranda, Julio-Alejandro Romero-González, Diana-Margarita Córdova-Esparza, Gendry Alfonso-Francia, Edgar-Arturo Chávez-Urbiola, Alfonso Ramirez-Pedraza and Juan Terven

Mach. Learn. Knowl. Extr. 2026, 8(6), 141; https://doi.org/10.3390/make8060141 - 22 May 2026

Abstract

The rapid evolution of Large Language Models (LLMs) has exposed limitations of static, accuracy-oriented benchmarks and increased the need for evaluation frameworks that distinguish among capabilities and benchmark quality. This survey analyzes 63 LLM benchmarks spanning 2012–2026 and organizes them into a taxonomy of six capability dimensions and 20 operational subcategories. We also propose the Benchmark Quality Assurance Index (BQAI), an AHP-weighted composite framework for assessing the scientific quality of benchmarks across seven dimensions related to annotation, clarity, standardization, reproducibility, robustness, coverage, and fairness. The BQAI is applied to 30 representative benchmarks, corresponding to 48% of the 63-benchmark corpus, with three-evaluator blinded scoring, formal inter-rater reliability validation

(ICC (2, k)

and quadratic-weighted Cohen’s

κ)

, and Monte Carlo sensitivity analysis

(n = 1000 trials, \pm 10 % to \pm 50 % weight perturbation)

. In addition, we synthesize public performance results for 16 models across 10 benchmarks to examine saturation trends and reporting gaps. The analysis indicates that benchmark usefulness varies substantially across evaluation settings, that several established benchmarks are becoming less discriminative for frontier models, and that important gaps remain in safety, agentic, and cross-cultural assessment. Together, the taxonomy, BQAI, and saturation analysis provide a structured perspective on the current LLM benchmark landscape and on priorities for more rigorous evaluation. Full article

(This article belongs to the Section Thematic Reviews)

38 pages, 1728 KB

Open AccessArticle

A Real-Time Sensor-Driven Multi-Agent Navigation System with Reinforcement Learning for Blind and Visually Impaired Users in Urban Environments

by Pilar Herrero-Martin and Álvaro García-Ballestero

Electronics 2026, 15(11), 2250; https://doi.org/10.3390/electronics15112250 - 22 May 2026

Abstract

Urban navigation in dynamic environments remains a challenging problem for blind and visually impaired users due to the presence of unpredictable obstacles and the limitations of conventional navigation systems, which rely primarily on static map-based information and lack real-time environmental awareness. This paper presents a real-time sensor-driven navigation system based on a multi-agent architecture incorporating a reinforcement-learning navigation policy for assistive mobility in urban environments. The proposed system integrates GPS-based global localization with vision-based perception to enable continuous fusion of global route planning and local obstacle detection. This integration allows the system to dynamically adjust navigation strategies in response to changing environmental conditions. The architecture is designed as a modular multi-agent system comprising agents for perception, navigation, sensor fusion, personalization, safety arbitration, interface management, and system monitoring. The reinforcement learning component formulates local navigation as a sequential decision-making problem, where the navigation policy is trained to balance path efficiency, obstacle avoidance, and safety constraints through interaction with simulated environments. Prototype implementation is developed and evaluated in both simulation and controlled real-world scenarios. Experimental results demonstrate that the proposed system shows improved obstacle avoidance performance and navigation stability under the evaluated conditions while maintaining low-latency responsiveness compared to baseline navigation approaches. The system also exhibits robust behaviour under varying environmental conditions, supporting its potential applicability to assistive navigation tasks in controlled urban environments. The proposed approach contributes to a scalable architecture that integrates a reinforcement-learning navigation policy within a multi-agent coordination framework and real-time sensor perception, providing a foundation for the development of intelligent and deployable assistive navigation systems. Full article

(This article belongs to the Special Issue Wearable and Intelligent (Bio)Electronics for Healthcare: From Sensors to AI)

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 2000.

Go to page 1 2 3 4 5

Search Results (109,321)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI