Search Results (22,987)

Vehicle repositioning is essential for improving efficiency and service quality in ride-sharing platforms, yet existing approaches typically optimize proxy rewards that fail to reflect human-centered preferences such as wait time, service coverage, and unnecessary empty travel. We propose the first two-stage Bilevel Reinforcement Learning (RL) from Human Feedback (RLHF) framework for preference-aligned vehicle repositioning. In Stage 1, a value-based Deep Q-Network (DQN)-RLHF warm start learns an initial preference-aligned reward model and stable reference policy, mitigating the reward-model drift and cold-start instability that arise when applying on-policy RLHF directly. In Stage 2, a Kullback–Leibler (KL)-regularized Proximal Policy Optimization (PPO)-RLHF algorithm, equipped with action masking, behavioral-cloning anchoring, and alternating forward–reverse KL, fine-tunes the repositioning policy using either Large Language Model (LLM)-generated or rubric-based preference labels. We develop and compare two coordination schemes, pure alternating (PPO-Alternating) and k-step alternating (PPO-k-step), demonstrating that both yield consistent improvements across all tested arrival scales. Empirically, our framework reduces wait time and empty-mile ratio while improving served rate, without inducing trade-offs or reducing platform profit. These results show that human preference alignment can be stably and effectively incorporated into large-scale ride-sharing repositioning. Full article

Accurate braking-distance prediction for heavy-duty multi-axle trucks remains challenging due to the large gross vehicle weight, tandem-axle interactions, and strong transient load transfer during emergency braking. Recent studies on tire–road friction estimation, commercial-vehicle braking control (EBS/AEBS), and weigh-in-motion (WIM) sensing have highlighted that unmeasured vertical-load dynamics and time-varying friction are key sources of prediction uncertainty. To address these limitations, this study proposes an integrated sensing–simulation–AI framework that combines real-time axle-load estimation, full-scale robotic braking tests, fused road-friction sensing, and physics-consistent machine-learning modeling. A micro-electro-mechanical systems (MEMS)-based load-angle sensor was installed on the leaf-spring panel linking tandem axles, enabling the continuous estimation of dynamic vertical loads via a polynomial calibration model. Full-scale on-road braking tests were conducted at 40–60 km/h under systematically varied payloads (0–15.5 t) using an actuator-based braking robot to eliminate driver variability. A forward-looking optical friction module was synchronized with dynamic axle-load estimates and deceleration signals, and additional scenarios generated in a commercial ASM environment expanded the operational domain across a broader range of friction, grade, and loading conditions. A gradient-boosting regression model trained on the hybrid dataset reproduced measured stopping distances with a mean absolute error (MAE) of 1.58 m and a mean absolute percentage error (MAPE) of 2.46%, with most predictions falling within ±5 m across all test conditions. The results indicate that incorporating real-time dynamic axle-load sensing together with fused friction estimation improves braking-distance prediction compared with static-load assumptions and purely kinematic formulations. The proposed load-aware framework provides a scalable basis for advanced driver-assistance functions, autonomous emergency braking for heavy trucks, and infrastructure-integrated freight safety management. All full-scale braking tests were carried out at approximately 60% of the nominal service-brake pressure, representing non-panic but moderately severe braking conditions, and the proposed model is designed to accurately predict the resulting stopping distance under this prescribed braking regime rather than to minimize the absolute stopping distance itself. Full article

Community energy systems are expected to play an increasingly important role in the decarbonization of the residential sector, but their operation depends on how different electricity and heat storage technologies are configured and used. Existing studies typically examine storage options in isolation, limiting the comparability of their operational roles. This study addresses this gap by developing a decision-support framework that enables a consistent, operation-focused comparison of battery energy storage, hydrogen storage, and electric-vehicle-based storage within a unified community-scale hybrid energy system. The model represents electricity and heat balances in a hub formulation that couples photovoltaic and wind generation, a gas engine, an electric boiler, thermal and electrical storage units, hydrogen conversion and storage, and an aggregated fleet of electric vehicles. It is applied to a stylized Polish residential community using local demand, generation potential, and electricity price data. A set of single-technology and multi-technology scenarios is analyzed to compare how storage portfolios affect self-sufficiency, self-consumption, grid exchanges, and operating costs under current electricity market conditions. The results show that battery and electric vehicle storage primarily provide short-term flexibility and enable price-driven arbitrage, as reflected in the highest contribution of battery discharge to the electricity supply structure (5.6%) and systematic charging of BES and EVs during low-price hours, while hydrogen storage supports intertemporal shifting by charging in multi-hour surplus periods, reaching a supply share of 1.4% at the expense of substantial conversion losses. Moreover, the findings highlight fundamental trade-offs between cost-optimal, price-responsive operation and autonomy-oriented indicators such as self-sufficiency and self-consumption, showing how these depend on the composition of storage portfolios. The proposed framework, therefore, provides decision support for both technology selection and the planning and regulatory assessment of community energy systems under contemporary electricity market conditions. Full article

Heavy-duty vehicles dominate global freight movement and primarily rely on fossil-derived diesel fuel. However, fluctuations in crude oil prices and evolving emissions regulations have prompted interest in alternative powertrains to enhance fleet energy resiliency. This study paired real-world operational data from a large commercial fleet with high-fidelity vehicle models to evaluate the potential for replacing diesel internal combustion engine (ICE) trucks with alternative powertrain architectures. The baseline vehicle for this analysis is a diesel-powered ICE truck. Alternatives include ICE trucks fueled by bio- and renewable diesel, compressed natural gas (CNG) or hydrogen (H₂), as well as plug-in hybrid (PHEV), fuel cell electric (FCEV), and battery electric vehicles (BEV). While most alternative powertrains resulted in some payload capacity loss, the overall fleetwide impact was negligible due to underutilized payload capacity for the specific fleet considered in this study. For sleeper cab trucks, CNG-powered trucks achieved the highest replacement potential, covering 85% of the fleet. In contrast, H₂ and BEV architectures could replace fewer than 10% and 1% of trucks, respectively. Day cab trucks, with shorter daily routes, showed higher replacement potential: 98% for CNG, 78% for H₂, and 34% for BEVs. However, achieving full fleet replacement would still require significant operational changes such as route reassignment and enroute refueling, along with considerable improvements to onboard energy storage capacity. Additionally, the higher total cost of ownership (TCO) for alternative powertrains remains a key challenge. This study also evaluated lifecycle impacts across various fuel sources, both fossil and bio-derived. Bio-derived synthetic diesel fuels emerged as a practical option for diesel displacement without disrupting operations. Conversely, H₂ and electrified powertrains provide limited lifecycle impacts under the current energy scenario. This analysis highlights the complexity of replacing diesel ICE trucks with admissible alternatives while balancing fleet resiliency, operational demands, and emissions goals. These results reflect a US-based fleet’s duty cycles, payloads, GVWR allowances, and an assumption of depot-only refueling/recharging. Applicability to other fleets and regions may differ based on differing routing practices or technical features such as battery swapping. Full article

Accurate identification of road roughness is pivotal for optimizing vehicle suspension control and enhancing passenger comfort. However, existing data-driven methods often struggle to balance classification accuracy with the strict computational constraints of real-time onboard monitoring. To address this challenge, this paper proposes a lightweight and robust road roughness classification framework utilizing a single sprung mass accelerometer. First, to overcome the scarcity of labeled real-world data and the limitations of linear models, a high-fidelity co-simulation platform combining CarSim and Simulink is established. This platform generates physically consistent vibration datasets covering ISO A–F roughness levels, effectively capturing nonlinear suspension dynamics. Second, we introduce DB-MLP, a novel Dual-Branch Multi-Layer Perceptron architecture. In contrast to computationally intensive Transformer or RNN-based models, DB-MLP employs a dual-branch strategy with multi-resolution temporal projection to efficiently capture multi-scale dependencies, and integrates dual-domain (time and position-wise) feature transformation blocks for robust feature extraction. Experimental results demonstrate that DB-MLP achieves a superior accuracy of 98.5% with only 0.58 million parameters. Compared to leading baselines such as TimeMixer and InceptionTime, our model reduces inference latency by approximately 20 times (0.007 ms/sample) while maintaining competitive performance on the specific road classification task. This study provides a cost-effective, high-precision solution suitable for real-time deployment on embedded vehicle systems. Full article

Autonomous driving systems rely on vast and diverse datasets for robust object recognition. However, acquiring real-world data, especially for rare and hazardous scenarios, is prohibitively expensive and risky. While purely synthetic data offers flexibility, it often suffers from a significant reality gap due to discrepancies in visual fidelity and physics. To address these challenges, this paper proposes a novel real–virtual fusion framework for efficiently generating highly realistic augmented image datasets for autonomous driving. Our methodology leverages real-world driving data from South Korea’s K-City, synchronizing it with a digital twin environment in Morai Sim (v24.R2) through a robust look-up table and fine-tuned localization approach. We then seamlessly inject diverse virtual objects (e.g., pedestrians, vehicles, traffic lights) into real image backgrounds. A critical contribution is our focus on inconsistency mitigation, employing advanced techniques such as illumination matching during virtual object injection to minimize visual discrepancies. We evaluate the proposed approach through experiments. Our results show that this real–virtual fusion strategy significantly bridges the reality gap, providing a cost-effective and safe solution for enriching autonomous driving datasets and improving the generalization capabilities of perception models. Full article

Under China’s dual-carbon policy, medium-duty commercial vehicles (MDCVs)—widely used in urban distribution with high load fluctuation and long operating hours—are key to transportation energy conservation and emission reduction. Optimizing powertrain parameters and energy management is essential for fuel-cell MDCVs. However, traditional powertrain parameter selection relies on fixed thresholds and lacks optimization, while the equivalent consumption minimization strategy (ECMS) suffers from poor driving cycle adaptability despite addressing hydrogen consumption and online application challenges. To overcome these issues, this study proposes an innovative approach for fuel cell-powered MDCVs: a driving cycle model was constructed based on hydrogen consumption and fuel cell degradation rates. Subsequently, the powertrain system parameters were optimized, culminating in the development of an adaptive ECMS (A-ECMS). Specifically, the method includes: (1) a driving cycle construction approach analyzing driving cycle clustering’s impact on adaptive control parameters; (2) a powertrain parameter optimization method considering vehicle performance under synthetic driving cycles; and (3) an A-ECMS enhanced by a crayfish optimization algorithm (COA) to improve driving cycle adaptability. Simulations show that A-ECMS achieves hydrogen consumption close to the dynamic programming algorithm (DP) optimum, reducing consumption by 2.12% and 1.45% compared to traditional ECMS under synthetic and World Transient Vehicle Cycle (WTVC) cycles, significantly improving MDCV economy. Full article

This study investigates left-turn safety at urban intersections using surrogate safety measures derived from field video observations. Time-to-Collision (TTC) among motorized traffic and Post-Encroachment Time (PET) among pedestrian and motorized traffic were extracted for left-turn conflicts across five intersection types in Thessaloniki, Greece, and linked to geometric attributes, signal operations, and traffic conditions. Count-based models (Poisson, Negative Binomial) were estimated alongside machine-learning approaches (Random Forest, Gradient Boosting with Poisson loss). For PET events, the Poisson model had the best balance of parsimony and predictive accuracy, whereas the Negative Binomial model provided a superior fit for TTC events. Results indicate that PET-defined conflicts increased with pedestrian volume and the presence of shared and protected left-turn lanes, and decreased with higher opposing flow, greater average acceleration, and wider end-approach lanes. By contrast, TTC events were associated with lower average speeds, the presence of protected signal phasing for left turns, and the number of passenger cars. Machine-learning models underperformed relative to classical count models, reflecting limited sample size and the discrete event structure. The analysis indicates that the determinants of TTC and PET differ, with certain variables such as pedestrian activity and lane configuration having contrasting effects on the two surrogate safety measures. The analysis reveals that pedestrian demand and shared lane configurations significantly increase PET occurrences, whereas TTC events are more strongly associated with vehicle volumes, speeds, and signal phasing. This distinction underscores the importance of tailoring safety assessment and intervention strategies to the type of interaction being evaluated. Full article

Urban sustainability heavily relies on efficient transportation systems, with dynamic bus lanes (DBL) being crucial components. However, traditional DBLs often face underutilization, leading to inefficient road usage. To this end, a novel IoT-Enabled Dynamic Bus Lane System (IoT-DBL) has been proposed, aimed at improving road utilization and reducing vehicle energy consumption. To assess the effectiveness of IoT-DBL, we developed a Markov chain-based queuing model and established a comprehensive evaluation framework through various performance metrics. Theoretical analysis reveals that the IoT-DBL system significantly improves intersection efficiency and reduces vehicle fuel consumption. Further optimization using a genetic algorithm (GA) identifies the optimal deployment length of IoT-DBLs to minimize fuel consumption. Numerical experiments demonstrate that the IoT-DBL strategy significantly outperforms traditional DBL methods, reducing queue lengths by 71.15%, vehicle delays by 69.48%, and fuel consumption by 70.42%, while increasing intersection efficiency by 100.11%. These results highlight that the IoT-DBL system can substantially improve traffic conditions, alleviate congestion, decrease fuel consumption, and enhance overall intersection efficiency, thereby providing a promising solution for sustainable urban transportation. Full article

Accurate and timely crop yield estimation remains a major challenge in agriculture due to the limitations of traditional field-based methods, which are labor-intensive, destructive, and unsuitable for large-scale applications. While recent advances in Unmanned Aerial Vehicles (UAVs) and Deep Learning (DL) have enabled non-destructive and scalable alternatives, melons (Cucumis melo L.) remain relatively understudied, and datasets for yield estimation are scarce. This study presents a computer vision pipeline for UAV-based fruit detection and yield estimation in melon crops. High-resolution UAV RGB imagery was processed using YOLOv12 (You Only Look Once, version 12) for fruit detection, followed by a volume-based regression model for weight estimation. The experiment was conducted during the May–August 2025 growing season in Apulia, southern Italy. The detection model achieved high accuracy, with strong agreement between estimated and actual fruit counts (R² = 0.99, MAPE = 5%). The regression model achieved an R² of 0.79 for individual weight estimation and a total yield error of 2.9%. By addressing the scarcity of melon-specific data, this work demonstrates that integrating UAV imagery with deep learning provides an effective and scalable approach for accurate yield estimation in melons. Full article

In the field of logistics distribution, the two-echelon vehicle routing problem has long been a critical focus. Against the backdrop of global warming, enterprises conducting logistics operations must now prioritize not only delivery costs but also the environmental impact of carbon emissions. To address these challenges, this study integrates occasional drivers into the two-echelon vehicle routing framework, centering on carbon emission reduction. First, Affinity Propagation (AP) clustering is applied to assign customer points to transfer centers. Subsequently, an optimization model is formulated to minimize both vehicle routing costs and carbon emission costs through a collaborative delivery system involving specialized and crowdsourced vehicles. An enhanced Sparrow–Whale Optimization Algorithm (S-WOA) is proposed to solve the model. The algorithm is tested against traditional heuristic methods on three datasets of different scales. Experimental results demonstrate that the two-echelon logistics and distribution model combining specialized vehicles and occasional drivers achieves a significant reduction in total delivery costs compared to models relying solely on specialized vehicles. Further analysis reveals that, with a fixed crowdsourced compensation coefficient, increasing the crowdsourced detour coefficient leads to a decline in total delivery costs. Conversely, when the detour coefficient remains constant, raising the compensation coefficient results in an upward trend in total costs. These insights provide actionable strategies for optimizing cost-efficiency and sustainability in logistics operations. Full article

To address the increasing vulnerability of unmanned aerial vehicle (UAV) lightweight airframe structures to high-velocity fragment impacts in complex operational environments, this study combines high-velocity impact penetration tests, quasi-static strength tests, fracture-surface microanalysis, and finite-element simulation to systematically reveal the formation mechanism of typical penetration damage and its influence on residual strength. Results show that such penetration induces damage such as adiabatic-shear local melting zones, spall cracks, and grain-boundary separation, significantly weakening static strength and shifting the fracture mode from ductility- to brittleness-dominated. A modified fracture-mechanics criterion with higher prediction accuracy than the traditional net-section criterion is proposed, and a high-precision simulation model based on explicit–quasi-static coupling is established, which well reproduces damage morphology and tensile-failure processes. Compared with conventional manned aircraft structures, UAV airframes characterized by thinner skins and higher lightweighting ratios exhibit more pronounced sensitivity to penetration-induced micro-defects, making rapid residual-strength assessment essential for operational recovery and field-level repair decision-making. The research reveals the damage mechanism and provides an engineering-applicable residual-strength assessment method, offering a reliable theoretical basis and simulation tool for rapid UAV damage evaluation and fast-turnaround repair planning for civil and industrial UAV platforms. Full article

The growing presence of autonomous AI systems, such as self-driving cars and humanoid robots, raises critical ethical questions about how these technologies should make moral decisions. Most existing moral machine (MM) models rely on secular, utilitarian principles, which prioritize the greatest good for the greatest number but often overlook the religious and cultural values that shape moral reasoning across different traditions. This paper explores how theological perspectives, particularly those from Christian, Islamic, and East Asian ethical frameworks, can inform and enrich algorithmic ethics in autonomous systems. By integrating these religious values, the study proposes a more inclusive approach to AI decision making that respects diverse beliefs. A key innovation of this research is the use of large language models (LLMs), such as ChatGPT (GPT-5.2), to design with human guidance MM architectures that incorporate these ethical systems. Through Python 3 scripts, the paper demonstrates how autonomous machines, e.g., vehicles and humanoid robots, can make ethically informed decisions based on different religious principles. The aim is to contribute to the development of AI systems that are not only technologically advanced but also culturally sensitive and ethically responsible, ensuring that they align with a wide range of theological values in morally complex situations. Full article

For the purpose of fulfilling the dual requirements of persistent cellular network connectivity and flight safety for cellular-connected Unmanned Aerial Vehicles (UAVs) operating in dense urban airspace, this paper presents an A*-oriented comprehensive path-planning scheme for multiple connected UAVs that integrates a radio map and complex network. Existing research often lacks rigorous processing of environmental map data, while the traditional A* algorithm struggles to simultaneously handle constraints such as obstacle avoidance, flight maneuverability, and multi-UAV path conflicts. To overcome these limitations, this study first constructs a path-planning model based on complex-network theory using environmental data and the radio map, clarifying the separation of responsibilities between environment representation and algorithmic search. On this basis, we proposed an improved A* algorithm for multi-UAV scenarios termed MURM-A*. Simulation results demonstrate that the proposed algorithm effectively avoids collisions with obstacles, adheres to UAV flight dynamics, and prevents spatial conflicts between multi-UAV paths, while achieving a joint optimization between path efficiency and radio quality. In terms of performance comparison, the proposed algorithm shows a marginal difference but ensures operational validity compared to traditional A*, exhibits a slightly increase in flight time but achieves a substantial reduction in radio-outage time compared to the Deep Reinforcement Learning (DRL) method. Furthermore, employing the path-planning model enables the algorithm to more accurately identify environmental information compared to directly using raw environmental maps. The modeling time is also notably shorter than the training time required for DRL methods. This study provides a well-structured and extensible systematic framework for reliable path planning of multiple cellular-connected UAVs in complex radio environments. Full article

With the rapid development of the automotive industry, autonomous driving has attracted growing research interest, among which path planning and trajectory tracking play a central role. To better understand the evolution, current status, and future directions of this field, this study conducts a comprehensive bibliometric analysis combined with latent Dirichlet allocation (LDA) topic modeling on publications related to autonomous vehicle path planning and trajectory tracking indexed in the Web of Science database. Multiple dimensions are examined, including publication trends, highly cited authors, leading institutions, research domains, and keyword co-occurrence patterns. The results reveal a sustained growth in research output, with trajectory planning, path optimization, trajectory tracking, and model predictive control (MPC) emerging as dominant topics, alongside a notable rise in learning-based approaches. In particular, reinforcement learning (RL) and deep reinforcement learning (DRL) have become increasingly prominent in complex decision-making and tracking control scenarios. The analysis further identifies core contributors and institutions, highlighting the leading roles of China and the United States in this research area. Overall, the findings provide a systematic overview of the knowledge structure and evolving research trends, offering valuable insights into key opportunities and challenges and supporting future research toward safer and more intelligent autonomous driving systems. Full article