Search Results (6,660)

Deep learning models are widely used in autonomous vehicle systems for perception, localization, and decision-making. However, their lack of transparency poses significant challenges in safety-critical environments. This systematic review presents a unified mathematical framework for explainable deep learning which integrates multimodal inputs, graph-theoretic road geometry, uncertainty modeling, and intrinsically interpretable representations. Road-structured priors that include lane topology and spatial constraints are incorporated into learning and optimization processes for ensuring model predictions and explanations to remain physically and semantically grounded. The review synthesizes methods across saliency-based, concept-based, causal, and intrinsic explainability, and extends them to vision-language models. This enables language-grounded, human-interpretable reasoning in autonomous vehicle systems. While vision-language models offer a new paradigm for semantic explainability, their limitations such as hallucinations, misgrounding, and reduced reliability under distribution shifts are also critically examined. Along with the role of road priors in improving alignment and robustness, another key contribution of this work is its quantitative evaluation metrics for road-aware explainability. These evaluation metrics link the explanations to spatial consistency, uncertainty alignment, and graph-structured reasoning. The overall framework connects latent representations, predictions, and explanations within a single formulation, enabling systematic comparison and analysis across models. Based on a PRISMA-guided review of 164 studies, this research identifies gaps in real-world reliability, temporal reasoning, and standardized evaluation, and outlines future directions including human-in-the-loop systems, regulatory readiness, and language-based auditing. Overall, this study advances a mathematically grounded and road-aware perspective on explainable vehicle AI which significantly bridges the gap between high-performance models and transparent, trustworthy autonomous systems. Full article

With the development of autonomous driving and intelligent connected vehicle technologies, the vehicle cabin is shifting from a simple transportation space to an intelligent mobile space integrating infotainment, interaction, and rest, and passenger comfort has gradually become an important factor affecting user experience, system trust, and perceived safety. Focusing on three categories of cabin environmental factors, namely the acoustic, optical, and thermal environments, this study develops an experimental design and comprehensive modeling method for passenger comfort evaluation. First, controlled single-factor experiments were conducted to establish quantitative mapping relationships between physical environmental parameters and subjective comfort ratings. The analytic hierarchy process (AHP) was then used to determine the weights of each indicator, and a penalty-based aggregation mechanism was introduced to construct a comprehensive comfort evaluation model. Finally, external validation was performed on an independent vehicle platform to examine the model’s applicability and consistency. The results show that acoustic comfort decreases as the sound pressure level increases, whereas optical and thermal comfort exhibit nonlinear behavior with optimal intervals. AHP weight results show that the thermal environment has the highest weight (0.4280), followed by the acoustic environment (0.3305) and the optical environment (0.2415). The external validation results indicate that the proposed model exhibits good predictive consistency across three steady-state operating conditions, with a mean absolute error of 0.122, a root-mean-square error of 0.150, and a Pearson correlation coefficient of 0.960. The findings show that the penalty-based aggregation model can effectively characterize the limiting-factor effect under the joint action of multiple environmental factors, providing a computable and interpretable evaluation framework for intelligent cockpit environmental control and automotive engineering experimental teaching. The conclusions of this study are mainly applicable to the current experimental platform and steady-state operating conditions, and further validation is still required with more vehicle models, dynamic road scenarios, and complex multi-environment factor disturbances. Full article

Prevention of crossing collisions between cyclists and vehicles at nonsignalized intersections on community roads where walls and hedges limit visibility is required in Japan. Because available observation information in real-time is limited on community roads, the use of statistical information that represents the typical movement characteristics of cyclists is effective to compensate for the lack of observation information. From such a background, in our previous study, we proposed a method to construct “location-dependent statistical information” (LDSI) and a method to utilize it as “virtual observation” (VO) and “virtual control input” (VCI) in stochastic position estimation. Here, although LDSI was constructed for multiple clusters of cyclists, the classification method of the cyclists observed in real-time was not considered. In the real world, the limitation of the observation information causes classification uncertainty. Thus, in this study, we propose a position estimation method that utilizes soft classification results and considers classification uncertainty by integrating VO and VCI derived from LDSI of each cluster. To evaluate the proposed method in this study, we conduct a simulation and an experiment in the real world. Through the comparison with conventional methods, we confirm that our proposed method in this study improves the performance of the position estimation. The proposed method will contribute to a cooperative safety system. Full article

Persistent traffic congestion and the need for efficient traffic monitoring have increased the demand for automated vehicle-analysis systems based on CCTV footage. This study presents a CCTV-based vehicle monitoring system that integrates vehicle detection, tracking, counting, public/private vehicle class prediction, seven-category vehicle-type prediction, vehicle-color recognition, and traffic-state estimation using YOLOv12 and DeepSORT. To reduce manual annotation effort during the initial training stage, a semi-automated method for generating synthetic composite road scenes was developed by combining cropped vehicle images and road-background images. The detector was first trained on 10,000 synthetic images and then sequentially fine-tuned on real CCTV data. Four real-world traffic video clips from Metro Manila were used in the study. Three 5 min clips were used within the staged refinement workflow: the first two for iterative refinement and the third for final post-refinement evaluation of the adapted model. A separate fourth CCTV clip was reserved exclusively for blind evaluation without on-the-fly retraining. The final system achieved average accuracies of 97% for public/private vehicle class prediction, 90% for seven-category vehicle-type prediction, 82% for vehicle-color recognition, and 96.67% for vehicle counting on the final evaluation video. The results show that synthetic pretraining combined with limited real-world fine-tuning can improve performance in CCTV-based vehicle monitoring while reducing the amount of manually labeled real-world data required. The study also discusses the limitations of the current evaluation protocol and the need for broader multi-location testing. Full article

Road freight transport (RFT) faces growing pressure from increasing freight demand, stricter environmental requirements, and persistent driver shortages. Automation technologies (ATes)—especially semi-autonomous driving—are increasingly viewed as a practical pathway toward improving the sustainability performance of freight operations; however, their effects depend strongly on infrastructure and operational conditions. This study evaluates the sustainability potential of autonomous and semi-autonomous trucks through an integrated framework combining (i) a structured review of technical and regulatory developments, (ii) surveys of transport enterprises (TEes) and road users (RUs), (iii) SWOT/TOWS analysis, and (iv) a cost minimization logistics model that links operational feasibility to infrastructure readiness (IR). The proposed model minimizes cost per tonne-kilometre and introduces an Infrastructure Readiness Score (IRS) to represent the share of a route that can be operated in automated mode; it also accounts for fuel savings from platooning and higher maintenance and capital costs of semi-autonomous vehicles (SAVs). Results indicate that, as IRS increases, semi-autonomous operations achieve higher daily mileage and lower unit costs, with a break-even point at approximately IRS ≈ 0.125. Beyond this threshold, unit costs decline from EUR 0.0433 to EUR 0.0348 per tonne-kilometre as IRS rises toward 0.6, after which further infrastructure improvements yield diminishing mileage gains. These cost and utilization improvements imply sustainability benefits via improved energy efficiency and reduced emissions intensity per tonne-kilometre. Nevertheless, survey evidence highlights major adoption barriers, including insufficient IR, regulatory uncertainty, technological reliability concerns, and limited public trust in fully autonomous systems. Overall, the findings support semi-autonomous trucking as the most feasible near-term stage of transition, while emphasizing that infrastructure upgrades and governance mechanisms are critical for scaling sustainability gains. Full article

This study estimates daily nitrogen dioxide (NO₂) concentrations at ground level across the Marmara Region of Türkiye at 0.01° resolution. The framework integrates Sentinel-5P (S5P) TROPOspheric Monitoring Instrument (TROPOMI) and GEOS Composition Forecast (GEOS-CF) tropospheric NO₂ vertical column density (VCD) data with meteorological, topographic, land-use, socioeconomic, and temporal features through four tree-based ensemble algorithms trained on 74 ground station observations. Under a temporal split (2019–2022 training, 2023 validation, 2024 testing), S5P-Categorical Boosting (CatBoost) achieved the best performance (Pearson correlation coefficient (R) = 0.706, R² = 0.498, root mean square error (RMSE) = 14.31 µg/m³). Random splitting inflated R by +0.168 due to temporal autocorrelation, while leave-one-station-out and leave-one-province-out cross-validation reduced R to ~0.50 by removing spatial dependence, together revealing the combined effect of temporal and spatial autocorrelation. SHapley Additive exPlanations (SHAP) analysis identified TROPOMI NO₂ VCD, population density, road length, and nighttime light as dominant predictors; population density was the top predictor in the GEOS-CF model, followed by VCD. Concentration maps for 2024 showed that 95.9% of the region’s 26.74 million inhabitants were exposed above the WHO annual air quality guideline of 10 µg/m³, with a population-weighted mean of 21.08 µg/m³. Full article

Linear assets (LAs), such as conveyor systems, road networks, pipelines, and power transmission lines, are typically maintained through localized, segment-based interventions. While such approaches effectively address spatially heterogeneous degradation, they often neglect the system-level consequences of repeated local actions. In particular, improvements in segment condition may be accompanied by increased structural complexity, leading to reduced reliability and higher lifecycle costs. This paper proposes a unified engineering framework that integrates segment-level condition assessment with system-level structural effects. The framework is based on a dual representation of asset condition, distinguishing between material state (MS) and structural state (SS), which correspond to material aging (MA) and structural aging (SA), respectively. A key contribution is the introduction of the fragmentation penalty (FP), capturing the negative impact of increasing segmentation and interface density on system performance. The framework incorporates multi-threshold decision logic, enabling differentiation between operational, refurbishment, and replacement regimes, and interprets maintenance actions as transformations affecting both condition and structure. A formal model is developed to represent the asset as a dynamic system of segments and interfaces. It provides a basis for future empirical calibration and structure-aware optimization. Although the model is developed using conveyor belt loops as a reference case, its broader relevance is discussed for other classes of linear assets with repeated local intervention and evolving structural heterogeneity. A simple worked example is included to demonstrate the operational meaning of the proposed fragmentation-aware perspective. The results show that maintenance decisions may change when structural side effects are considered together with local condition improvement, and they provide a basis for future empirical calibration and structure-aware optimization of maintenance strategies. Full article

The rapid electrification of road transport has increased interest in distributed energy strategies that reduce grid demand and support decarbonization. Vehicle-integrated photovoltaics (VIPV), including vehicle-applied photovoltaic configurations (VAPV), can generate electricity directly on the vehicle. This systematic review examines peer-reviewed VIPV literature published between 2015 and 2026, focusing on the distinction between theoretical photovoltaic generation and practically usable energy. A Scopus search conducted on 2 May 2026 identified 196 records, of which 88 studies were included after screening against predefined criteria. Due to heterogeneity in vehicle types, climates, technologies, modeling assumptions, and reported metrics, no meta-analysis was performed. Instead, the review applies a multi-layered framework covering climate, geometry, thermal effects, electrical mismatch, battery state-of-charge interactions, fleet-scale modeling, economics, and life-cycle implications. The evidence shows that VIPV is technically feasible and can deliver measurable energy yields, especially in high-irradiance regions and vehicles with favorable daytime parking exposure. However, useful contribution depends strongly on curvature losses, dynamic shading, electrical configuration, SOC limits, charging behavior, seasonality, and vehicle energy demand. Therefore, VIPV is best understood as a context-dependent supplementary energy strategy rather than a transformative standalone solution. Its strongest value lies in specific vehicle classes, climates, and usage patterns where on-board generation can reduce charging demand, support operational resilience, or improve distributed self-consumption. The review also proposes minimum reporting requirements for future studies, including annual energy yield, Wh/km contribution, PV area or capacity, mileage assumptions, SOC modeling, and curtailment treatment. The review was not formally registered, and no formal risk-of-bias or certainty assessment was applied. Full article

Street lighting systems are essential for ensuring nighttime road safety and visibility. The integration of solar photovoltaic (PV) systems into street lighting infrastructure improves energy efficiency and sustainability; however, the mismatch between daytime energy generation and nighttime lighting demand requires effective energy management solutions. In addition, long-distance electrical connections introduce voltage drop constraints, which are often overlooked in conventional design approaches. This study addresses the integration of lighting design, electrical constraints, and techno-economic performance in nanogrid-based LED street lighting systems for secondary roads. A unified framework is developed to evaluate lighting performance, PV–battery sizing, voltage drop behavior, and lifecycle cost under different system architectures. Optimal pole spacing and luminaire ratings are determined using DIALux, while PV–battery configurations are optimized using HOMER Pro based on site-specific solar irradiance. The analysis focuses on voltage drop as the key electrical constraint and examines its impact under decentralized and centralized nanogrid configurations (25%, 50%, and 100%) in both stand-alone and grid-connected modes. The results show that increasing centralization reduces component redundancy but significantly increases cable length, conductor sizing, and infrastructure cost. A techno-economic assessment with lifecycle cost and sensitivity analysis indicates that a 25% centralized configuration reduces total system cost by approximately 23% compared to fully decentralized systems while avoiding excessive cabling costs. These findings demonstrate that voltage drop and electrical infrastructure constraints play a decisive role in determining optimal system design, highlighting the importance of system-level integration rather than isolated optimization of lighting or energy components. Full article

The pursuit of sustainable winter road maintenance has intensified the need for deicers that balance functional effectiveness, economic viability, and minimal environmental impact. However, the absence of a systematic, multi-dimensional evaluation framework has hindered informed product selection and green procurement. This study develops and validates the Comprehensive Deicer Multi-criteria Evaluation System (CDMES)—a structured assessment framework that integrates economic, functional, environmental, and infrastructural sustainability dimensions. The evaluation index system was constructed for deicers, consisting of 18 indicators including preparation cost, engineering maintenance cost, operability of agent preparation, application difficulty, asphalt binder adhesion loss, minimum application concentration, proportion of active ingredients, effective time, ambient temperature, freezing point, solid dissolution rate, relative snow/ice-melting capacity, seed damage rate, chlorophyll attenuation, soil pH, aqueous solution pH, steel–carbon corrosion rate, and pavement friction attenuation rate. Subsequently, the analytic hierarchy process (AHP) was employed to determine the weight of each indicator, and evaluation criteria were established in accordance with relevant standards and literature. Finally, this weight determination method, combined with the simple additive weighting (SAW) method for index aggregation, forms a quantitative evaluation model. These elements together constitute a comprehensive deicer evaluation system, designated as the Comprehensive Deicer Multi-criteria Evaluation System (CDMES). Validation using three representative deicers—sodium chloride, a composite chloride-based formulation, and an organic acetate-based product—demonstrated that the CDMES can effectively discriminate product performance across multiple sustainability dimensions and identify critical weaknesses that may be obscured by purely compensatory scoring. The framework offers a transparent and reproducible decision-support tool for winter maintenance managers seeking to align deicer selection with sustainability objectives. Full article

Wildfire severity and frequency continue to increase worldwide, making effective aerial wildfire suppression a critical component of wildfire response. The COLOSSUS (Collaborative SoS) X-Challenge project established a system-of-systems (SoS) framework to design and evaluate next-generation firefighting capabilities and operational concepts. Building on this framework, this paper presents a simulation environment that jointly evaluates conventional fixed-wing and electric vertical takeoff and landing (eVTOL) firefighting aircraft concepts by integrating aircraft design, fleet-level coordination, and mission-level tactics into the unified SoS assessment, enabling performance-driven design exploration. The framework was expanded with new tactics, including a ridge-based drop method, and a flanking selection algorithm that leverages road networks to establish anchor points and construct fire lines. Simulations across three representative wildfire locations (Salamis, Pyrenees, and Palisades) demonstrate that combining purpose-built aircraft with adaptive tactics can significantly improve mission effectiveness. Full article

Remote sensing technologies provide valuable geospatial data for analyzing environmental conditions and for supporting spatial ecological modeling across large, heterogeneous landscapes. In this study, multi-source remote sensing–derived environmental variables were integrated with ensemble machine learning techniques to model the habitat suitability of the common leopard (Panthera pardus) in Azad Jammu and Kashmir (AJ&K), Pakistan. Environmental predictors derived from satellite observations included land cover, vegetation condition, terrain attributes, and climate-related indicators. To ensure model reliability, multicollinearity among predictors was evaluated, and spatial clustering patterns of leopard occurrence records were examined using global spatial autocorrelation analysis. Two complementary machine learning algorithms, Maximum Entropy (MaxEnt) and Random Forest (RF), were implemented and integrated through a weighted ensemble approach to improve predictive accuracy and robustness. The ensemble model achieved high predictive performance with an area under the curve (AUC) value of 0.942, outperforming individual algorithms. The resulting habitat suitability map indicates that approximately 30% of the study region is highly suitable habitat, primarily in the northern and central districts, including Muzaffarabad, Neelum, Hattian, Poonch, and Sudhnutti. Variable importance analysis identified remotely sensed land cover, elevation, vegetation cover, slope, and temperature seasonality as the dominant predictors of habitat suitability, whereas anthropogenic indicators such as proximity to roads and population density had secondary effects in fragmented areas. The results demonstrate the potential of integrating remote sensing data and ensemble machine learning for spatial habitat modeling and wildlife conservation planning in mountainous ecosystems. Full article

Surface modification processes significantly influence the aggregate characteristics of steel slag and the road performance of asphalt mixtures. Therefore, this study employs four different substances to conduct surface modification treatment on aged steel slag with particle size ranges of 4.75–9.5 mm and 9.5–13.2 mm to determine the optimal surface modification process through macroscopic and microscopic analytical methods. Ultimately, a comparative analysis is performed on the pavement performance of asphalt mixtures incorporating aged steel slag and modified aged steel slag at different volume replacement ratios. Experimental results demonstrate that Epoxy Acrylate-Modified Organosilicon Resin (EAOR) significantly improved the aggregate properties of Aged Steel Slag (ASS), making it a viable alternative to natural stone; under identical conditions, the volume stability of modified aged steel slag (EAOR-ASS) was slightly superior to that of ASS, while the differences in high-temperature stability and low-temperature cracking resistance of the corresponding asphalt mixtures were minimal. Surface modification of ASS with EAOR significantly enhanced the water damage resistance of the asphalt mixture under freeze–thaw cycle conditions, thereby improving the utilization rate of steel slag. Both an increased volume replacement ratio of steel slag and surface modification with EAOR contributed to improved resistance to elastic deformation of the asphalt mixture. Full article

Under the constraints of limited maintenance budgets, research on pavement performance prediction is of considerable practical significance for improving the efficiency of maintenance decision-making, optimizing fund allocation, and ensuring highway serviceability. This study was conducted in conjunction with pavement maintenance projects on ordinary national and provincial highways in Shanxi Province, China. Representative routes were selected based on the natural zoning and road network scale of Linfen City. A comprehensive factor system influencing pavement service performance was established, encompassing pavement characteristics, traffic attributes, climatic and environmental conditions, and maintenance management levels. By employing Particle Swarm Optimization (PSO) to tune the hyperparameters of a Long Short-Term Memory (LSTM) network, a PSO-LSTM prediction model incorporating a sliding window mechanism was constructed for the Pavement Condition Index (PCI) and Ride Quality Index (RQI). The model achieves coefficients of determination (R²) of 0.845 and 0.869 for PCI and RQI, respectively, enabling dynamic prediction of pavement service performance and thereby providing scientific support and a data-driven basis for the formulation of pavement maintenance strategies. Full article

As the most common safety hazard among road surface distresses, pavement cracks require fine-grained segmentation to support subsequent maintenance decision-making. However, existing methods find it difficult to cope with complex environmental interference and multi-morphology cracks while maintaining low computational cost. To address the above issues, this study proposes a lightweight crack segmentation model, DSMUNet. Based on the U-shaped encoder–decoder framework, depthwise separable convolution is adopted to replace traditional convolution to reduce computational cost, and the SGE spatial group enhancement mechanism is introduced at the encoder side to emphasize crack features and suppress interference from non-crack textures. In addition, a new multi-scale feature fusion module is proposed to improve the overall connectivity of cracks during the feature fusion stage, thereby further improving model performance on the basis of model lightweighting. The experimental results show that DSMUNet contains only 0.55 M parameters and requires 21.708 GFLOPs, with an average inference latency of 5.42 ms, while achieving Dice/mIoU scores of 78.10%/69.05% on the private dataset and 87.12%/79.57% on the Crack500 dataset, respectively. These results demonstrate the advantages of this study in terms of resource consumption as well as its excellent segmentation performance, providing a more efficient implementation scheme for pavement crack segmentation in resource-constrained environments. Full article