Search Results (1,529)

Driven by the global energy transition and carbon neutrality goals, hybrid power systems have become a core technical path for energy conservation and carbon reduction in the transportation and power sectors, and the performance of energy management strategies directly determines the system’s overall energy efficiency. Traditional energy management methods have inherent bottlenecks of high model dependence and poor adaptability, making it difficult to satisfy real-time decision-making requirements under complex operating conditions. Deep Reinforcement Learning (DRL) provides an innovative solution to this technical bottleneck, and has become a cutting-edge research direction in this field. However, existing reviews have not yet constructed a full-chain analysis framework covering its algorithms, applications, verification, challenges and prospects. Focusing on the engineering application of DRL in the real-time energy management of hybrid power systems, this paper systematically sorts out domestic and international research results up to the first quarter of 2026. The core quantitative findings of this review are as follows: (1) DRL-based strategies can achieve 93–99.5% of the Dynamic Programming (DP) theoretical global optimum in fuel economy, which is 5–25% higher than rule-based methods; (2) DRL strategies only have 3.1–4.8% performance degradation under unseen operating conditions, which is significantly better than the 10.3–14.7% degradation of the Equivalent Consumption Minimization Strategy (ECMS); (3) Actor–Critic (AC) algorithms (Twin Delayed Deep Deterministic Policy Gradient (TD3)/Soft Actor–Critic (SAC)) have become the mainstream in this field, with a 3–5 times higher sample efficiency than value function-based algorithms; and (4) offline DRL and transfer learning can reduce the training time of DRL strategies by more than 80% while maintaining equivalent optimization performance. This paper first analyzes the essential attributes and core technical challenges of hybrid power system energy management; second, classifies DRL algorithms from the perspective of control engineering and analyzes their technical characteristics; third, disassembles the application design logic of DRL around four major scenarios: land vehicles, water vessels, aerial vehicles and fixed microgrids; fourth, summarizes the mainstream verification platforms and evaluation systems; fifth, analyzes core bottlenecks and cutting-edge solutions; and finally, prospects the development trends of next-generation intelligent energy management systems combined with cross-fusion technologies. This paper aims to build a complete technical system map for this field and promote the engineering deployment and practical application of intelligent energy management technologies integrating data and knowledge. Full article

Autonomous tracked amphibious robotic systems operating across water and land environments are essential for coastal inspection, disaster response, environmental monitoring, and complex terrain exploration. However, discontinuous water–land dynamics, unstable medium switching, and safety-critical control under environmental uncertainty pose significant challenges to existing amphibious navigation and path planning methods, where global reachability and adaptive decision-making are difficult to unify. Motivated by these challenges, this paper proposes CD-HSSRL, a Cross-Domain Hierarchical Safe-Switching Reinforcement Learning framework for autonomous tracked amphibious navigation. Specifically, a Cross-Domain Global Reachability Planner is developed to construct unified cost representations across heterogeneous water–land environments, a Hierarchical Safe Switching Policy enables stable medium-transition decision-making through option-based policy decomposition with switching regularization, and a Safety-Constrained Continuous Controller integrates action safety projection and risk-sensitive reward shaping to ensure collision-free control during complex shoreline interactions. These components are jointly optimized to achieve robust cross-domain navigation. The experimental results in the Gazebo + UUV simulation environment show that the proposed method demonstrates competitive performance compared with baseline approaches, achieving higher success rates and lower collision rates across water, land, and transition environments. In particular, in cross-domain scenarios, the proposed method improves success rates by approximately 20% compared to conventional RL methods while maintaining stable performance under environmental disturbances. Robustness and ablation studies further verify the effectiveness of hierarchical switching and safety-constrained control mechanisms. Overall, this work establishes an integrated framework for safe and robust cross-domain navigation of tracked amphibious robotic systems, providing new insights into hierarchical safe-switching architectures for multi-medium autonomous robots. Full article

Deploying highly generalizable deepfake detection systems on resource-constrained edge devices poses a significant technical challenge for conventional end-to-end large models that rely heavily on computational resources. Extracting multi-source physical prior features is a viable approach under limited computational power; however, in few-shot scenarios, the dimensional mismatch of heterogeneous features is prone to causing downstream classifiers to overfit. To mitigate this bottleneck, this paper proposes a “static feature extraction–central normalization alignment–independent downstream decision” decoupled detection system for few-shot cross-domain tasks on edge devices. The front end of the system constructs an 856-dimensional comprehensive feature reservoir, and a lightweight residual normalization adapter $g_{\varphi }$ is introduced as the central support module. This module explicitly compresses the intra-class variance of heterogeneous features, providing a smoothly aligned manifold base for downstream classifiers. Experimental results indicate that this decoupled architecture demonstrates consistent stability in few-shot ($K=10$) cross-domain evaluations. When encountering intra-family cross-domain shifts and cross-mechanism distribution shifts from diffusion models, the accuracy reaches 84.9% and 76.1%, respectively. Compared to representative end-to-end meta-learning baselines (e.g., MAML), the relative error rate is reduced by over 30%. Furthermore, after completing the asynchronous offline pre-processing (approximately 897 ms) at the front end, a single-image online classification query requires only 7.7 ms under a simulated single-core CPU constraint, satisfying the low-latency requirements for lightweight deployment on edge devices. Finally, combined with empirical observations, this paper discusses the performance boundaries of the architecture in cross-mechanism metric mismatch scenarios, providing a low-barrier, robust engineering defense scheme for resource-constrained environments. Full article

The continuous advancement of autonomy and intelligence in marine shipping has made the safe and efficient navigation of unmanned surface vehicles in complex waters a major research focus. As a key link of the autonomous decision-making system for unmanned surface vehicles (USVs), local path planning needs to achieve real-time collision avoidance and motion optimization under dynamic obstacles, multiple rule constraints, and strong environmental uncertainty. In recent years, reinforcement learning has gradually become an important technical route for local path planning of USVs by virtue of its autonomous decision-making ability in high-dimensional continuous state space and adaptability to complex nonlinear problems. Combined with the evolution of the algorithm paradigm and its functional positioning in different water scenarios, this paper systematically reviews the relevant literature by examining the evolution of algorithmic paradigms; focuses on summarizing deep Q-network (DQN), Proximal Policy Optimization (PPO), Soft Actor-Critic (SAC), and Twin Delayed Deep Deterministic Policy Gradient (TD3), along with the collaborative architectures integrated with traditional planning methods such as A* and Rapidly-exploring Random Tree (RRT); and summarizes the performance characteristics, advantages, and limitations of various methods in typical scenarios. The review shows that the main bottlenecks of current research include insufficient reward mechanism design, low sample utilization efficiency, difficulty in transferring from simulation to real ships, and insufficient safety and trustworthiness verification. This paper looks forward to the future development trends from the two directions of data fusion and security enhancement in order to provide reference for related research. Full article

In the context of evasive maneuvering for exo-atmospheric vehicles, reinforcement learning and other data-driven decision-making techniques have been explored extensively. However, most existing studies focus on scenarios where interceptors use a single guidance strategy, leading to significant performance degradation when the vehicle faces interceptors with different strategies. To address this, we introduce a novel Deep Policy Inference Twin Delayed Deep Deterministic Policy Gradient (DPI-TD3) algorithm that enhances evasive capabilities against interceptors employing a variety of guidance laws. We present a interception simulation framework that includes multiple types of interceptors. The deep policy inference model identifies the guidance law of the interceptor using the relative motion vector between the interceptor and the vehicle. Depending on the identified interceptor type, the algorithm either reuses an existing experience buffer or creates new ones through deep Bayesian inference and an experience mixing network. The updated TD3 algorithm then uses the selected buffer to train against the current interceptor, generating acceleration commands for the vehicle. Experimental results show that, compared to baseline methods, the proposed algorithm converges faster and produces more effective evasive maneuvers in response to various guidance laws. Under baseline conditions, DPI-TD3 achieves a penetration success rate of 96.4% and a miss distance of 15.58 m, outperforming TD3, Deep Deterministic Policy Gradient (DDPG), and the differential game method. In more complex scenarios with sensor noise and reduced interceptor maneuverability, DPI-TD3 still maintains success rates of 92.5% and 92.3%, showing less performance degradation than baseline methods. Full article

The long-term coexistence of human-driven vehicles (HVs) and autonomous vehicles (AVs) in mixed traffic presents significant challenges for lane-change interactions on freeways. To address this, we propose a closed-loop decision-making framework, centered on Social Value Orientation (SVO), that covers the entire process from recognition to fallback execution. First, we use maximum-entropy inverse reinforcement learning (MaxEnt-IRL) to infer driver SVO parameters (${\theta }_{SVO}$) from the NGSIM dataset, quantifying the trade-off between selfish and cooperative behaviors as learnable weights. These parameters are then incorporated into a Transformer-based predictor via conditional embeddings, enabling the model to generate personalized trajectories from identical historical data. Furthermore, within a receding-horizon, game-theoretic framework, we combine preference-weighted payoffs with this conditional predictor and introduce a dynamic lane-change abort mechanism. This mechanism triggers a fallback maneuver, generated by an APF + MPC controller, if the expected return of continuing the lane change drops below that of aborting. Simulations across 1000 adversarial scenarios show that our method markedly improves the lane-change success rate and cruising efficiency compared to the IDM + MOBIL baseline. It also significantly reduces forced merges and hazardous events when encountering aggressive or selfish blocking vehicles, demonstrating the safety and robustness benefits of our preference-aware model and abort mechanism. Full article

With the continuous advancement of intelligence in power systems, traditional unimodal fault diagnosis methods can no longer satisfy the demand for precise monitoring of complex power equipment. To address the challenges of multimodal data fusion and fault diagnosis in intelligent sensing scenarios, this paper proposes a multimodal intelligent diagnosis model for power transformers based on causal dynamic fusion reasoning. By introducing a causal reasoning mechanism, the proposed model overcomes the limitations of conventional multimodal fusion approaches that rely solely on statistical correlations. A four-layer architecture is constructed, consisting of a Causal Dynamic Fusion layer, a Graph Reasoning layer, a State Prediction layer, and a Meta-Reinforcement Learning Optimizer, thereby forming a complete closed-loop framework from multimodal feature extraction to intelligent diagnostic decision-making. This study focuses on key issues including causal discovery and dynamic fusion in multimodal data, cross-sample contextual enhancement, equipment state prediction, and early warning. Performance evaluation experiments are conducted on a large-scale synchronized dataset containing image, audio, and time-series modalities. Experimental results demonstrate that the proposed CDFMD model outperforms conventional methods in diagnostic accuracy and real-time performance, providing a novel technical pathway for intelligent operation and maintenance of power equipment. Full article

Background: Green logistics requires decision-support approaches that jointly address cost efficiency, emissions reduction, service reliability, and reporting transparency under dynamic operating conditions. Existing studies often treat optimization, predictive updating, stakeholder coordination, and emissions traceability separately, limiting integration. Methods: This study develops a simulation-based integrated decision-support framework that combines multi-objective mixed-integer linear programming (MILP), machine learning-based travel-time prediction in a rolling-horizon setting, cooperative allocation using a Shapley value mechanism, and ISO 14083:2023-aligned emissions accounting. A permissioned blockchain layer is included as a post-decision governance mechanism to support traceability. The framework is evaluated using industry-calibrated synthetic scenarios over a 30-day planning horizon with 50 independent simulation runs. Results: Under the tested scenarios, the integrated configuration reduced average CO₂ emissions per route by 27.6% (±2.4%), improved the cost index by 17.3% relative to the baseline, and increased on-time delivery to 96.8%. Robustness analyses showed average key performance indicator (KPI) deviations below 5%. Component-level analysis suggests that the main operational gains arise from the interaction between predictive updating and prescriptive optimization, while the blockchain layer mainly improves auditability. Conclusions: The framework improves environmental and operational performance under the tested simulation scenarios, although real-world validation remains necessary before deployment-level conclusions can be drawn. Full article

Pinyon–juniper (PJ) woodlands, one of the most extensive mature and old-growth woodland types in the Western United States, provide critical ecological, cultural, and economic benefits but face increasing threats from climate change, altered disturbance regimes, invasive species, and pests. We developed the PJ Woodland Climate Adaptation Management Menu, a decision support tool designed to guide adaptive, climate-informed management of PJ ecosystems, particularly within the Colorado Plateau ecoregion. The menu was created through an iterative, collaborative process involving literature review, integration of strategies from existing adaptation frameworks, and extensive input from scientists, land managers, and community partners during workshops and focus groups. The menu links specific, evidence-based approaches to each of six broad strategies, including soliciting community input, mitigating disturbance, enhancing and maintaining biodiversity, conserving ecotones, timing actions for optimal outcomes, and accepting climate-driven changes when appropriate. It is intended for use with the Adaptation Workbook to help managers connect local goals and climate vulnerabilities to tailored management tactics. Hypothetical scenarios demonstrate the menu’s application to contrasting PJ woodland conditions, from die-off events to old-growth maintenance. Lessons learned during development underscore the value of early stakeholder engagement, cross-sector collaboration, and balancing diverse ecological objectives. This menu offers a flexible, transferable framework to strengthen climate resilience in PJ woodlands and serves as a model that could improve adaptation planning in other dryland forest ecosystems. Full article

Multi-objective flexible job shop scheduling requires balancing conflicting objectives while supporting real-time decision-making in industrial environments. However, although traditional metaheuristics are effective for global search, their high computational cost limits their applicability in time-sensitive scenarios. To address this issue, this paper proposes dual-pool guided preference-conditioned graph reinforcement learning (DPG-GRL), an encoder–decoder framework for the multi-objective flexible job shop scheduling problem. In DPG-GRL, a graph attention network encoder extracts operation and machine-level representations from a heterogeneous graph, while the decoder is conditioned on a preference vector to generate scheduling solutions with different trade-offs using a single trained policy. To improve sample efficiency and training stability, a dual-pool guidance mechanism is introduced, in which an offline expert pool provides a stable behavioral prior for policy initialization and an online elite pool continuously replays high-quality trajectories to refine the policy. Experimental results show that DPG-GRL outperforms representative multi-objective evolutionary algorithms, including the non-dominated sorting genetic algorithm II (NSGA-II) and the multi-objective evolutionary algorithm based on decomposition (MOEA/D), on synthetic instances, with more pronounced advantages in solution quality and inference efficiency as the problem scale grows. In addition, evaluations on public benchmark instances using a model trained only on the small synthetic setting demonstrate rapid Pareto-front approximation, high-quality solution sets, and promising generalization to unseen instances. These results indicate the potential of DPG-GRL for real-time production scheduling and energy-aware manufacturing. Full article

Simulation is increasingly recognised as a strategic approach in nursing education for developing clinical competencies within safe learning environments. However, there is limited understanding of how virtual patient simulation supports the early development of clinical reasoning from the perspective of nursing students. Aim: To explore the perceptions of first-year undergraduate nursing students regarding the development of clinical reasoning and collaborative decision-making through virtual patient simulation. Methods: A qualitative, descriptive, and exploratory design was adopted. Semi-structured focus groups were conducted with 73 first-year undergraduate nursing students. Data were analysed using thematic content analysis following Bardin’s approach. Results: Students perceived virtual patient simulation as a meaningful and high-impact learning strategy. Realism, interactivity, and group collaboration emerged as key strengths. Engagement with dynamic clinical scenarios supported the integration of theoretical knowledge into practice, enhanced prioritisation skills, and promoted structured clinical reasoning. Collaborative learning facilitated shared reflection and collective problem-solving, while immediate feedback enabled learning through error within a psychologically safe environment. Participants also reported increased confidence and autonomy in decision-making. At the same time, students identified limitations related to software constraints and the alignment between automated assessment and their reasoning processes. Conclusions: Group-based virtual simulation appears to support the early structuring of clinical reasoning, extending beyond technical skill acquisition to foster reflective and collaborative practice. Its educational value, however, depends on intentional curricular integration and strong pedagogical alignment including structured facilitation, alignment between assessment and learning objectives, and opportunities for guided reflection. These findings contribute to a process-oriented understanding of how novice learners make sense of clinical reasoning in simulated contexts. Full article

Post-war reconstruction requires effective decision-support tools capable of integrating technical, economic, and organizational criteria under conditions of high uncertainty. The evaluation and prioritization of damaged buildings for recovery interventions are critical challenges for reconstruction project management. This study proposes a hybrid decision-support framework for assessing the strategic feasibility of building recovery using a novel Strategic Revitalization Index (SRI). The proposed methodology integrates a hierarchical fuzzy inference system, simulation techniques, and an artificial neural network surrogate model. The fuzzy model aggregates four key evaluation dimensions: technical condition of the building, economic feasibility of recovery actions, project implementation capability, and environmental and social impact. To analyze the model’s behavior and generate training data, a synthetic dataset was created using Latin Hypercube Sampling, covering a wide range of possible reconstruction conditions. The generated dataset was subsequently used to train an artificial neural network capable of approximating the nonlinear mapping implemented by the fuzzy decision model. The obtained results demonstrate high predictive performance of the surrogate model, with R² = 0.976, RMSE = 0.0266, MAE = 0.0133, and MAPE = 4.95%. Scenario analysis further illustrates how different recovery strategies influence SRI values and enables comparison of alternative reconstruction approaches. The proposed framework provides a flexible analytical tool for supporting strategic decision-making in post-war reconstruction projects. By combining fuzzy logic, simulation techniques, and machine learning, the model enables systematic prioritization of recovery strategies and may support large-scale reconstruction planning in post-conflict environments. Full article

Next-generation heterogeneous wireless networks (HetNets) comprising LTE macro-cells, 5G New Radio (NR) small cells, and WiFi 6 access points aim to provide seamless connectivity under diverse mobility scenarios. However, vertical handover (VHO) remains a performance bottleneck because of the highly variable radio environments, dynamic user mobility, stringent quality of service (QoS) requirements, and the coexistence of multi-tier access technologies. Existing handover approaches based on deep learning and deep reinforcement learning (DRL) suffer from limitations: deep learning models lack decision-making capabilities, whereas DRL models, particularly deep Q-network (DQN)-based policies, face Q-value overestimation and unstable convergence. To overcome these limitations, this paper introduces a Hybrid deep double-Q networks (DDQN)–bidirectional long short-term memory (Bi-LSTM) Framework that integrates bi-directional mobility prediction and DRL-based adaptive decision-making. The Bi-LSTM module captures forward and backward temporal dependencies and predicts future Received Signal Strength (RSS) trajectories, mobility dynamics, and cell-edge transitions. The DDQN module stabilizes the action value estimation, mitigates overestimation bias, and enables context-aware handover decisions. A multi-tier simulation environment consisting of LTE, 5G NR, and WiFi 6 networks was developed using realistic path loss, shadowing, interference, and mobility models. Extensive evaluations demonstrated substantial improvements in mobility prediction accuracy, handover stability, radio link reliability, throughput efficiency, and latency reduction compared to conventional RSS-based and DQN-based schemes. The findings highlight the effectiveness of integrating predictive intelligence with reinforcement learning for reliable mobility management in 5G-Advanced and emerging 6G networks. Full article

Unmanned aerial vehicles (UAVs) for urban and clinical–logistics missions operate under severe constraints in onboard energy, computation, and payload integrity. Addressing these challenges requires not only advanced algorithms but also a tight integration between embedded hardware, energy management, perception, and decision-making. This paper presents a unified UAV platform based on a system-level hardware–software co-design. First, a compact six-layer PCB (85 mm × 55 mm) integrates an NVIDIA Jetson Orin for on-edge artificial intelligence and a dedicated microcontroller for real-time flight control, with explicit power-domain separation, thermal management via arrays, and physical isolation of sensitive sensors. Second, a hybrid energy system combines LiPo batteries with perovskite photovoltaic cells and an MPPT stage with experimentally measured efficiency (94.5%), enabling stable operation under variable irradiance conditions. Third, an autonomous navigation strategy based on a Dueling Double Deep Q Network with Prioritized Experience Replay learns energy-efficient trajectories while explicitly incorporating payload thermal deviation (ΔT) and mechanical jerk into the reward function, thereby supporting clinically safe transport. Experimental validation on the physical platform includes onboard power and latency measurements, statistical evaluation across training and deterministic execution, and mission-level key performance indicators. Results show an average reduction of 18.4% in total energy consumption and a 12.1% increase in operational coverage under representative urban scenarios, with end-to-end decision latency below 50 ms. These findings demonstrate that a tightly integrated design of embedded hardware, hybrid energy management, and clinical-aware reinforcement learning enables robust, efficient, and application-ready UAV systems for urban and healthcare missions. Full article

This paper presents a novel system-oriented counterfactual deep learning framework, termed Hybrid Prediction–Intervention Neural Architecture (HPINA) for intelligent traffic accident risk prediction and proactive safety intervention in smart transportation systems. Unlike conventional data-driven models that rely solely on observational correlations, the proposed system integrates multi-domain data fusion, temporal deep representation learning, a continuous spatio-temporal risk field, and a latent-space counterfactual reasoning module within a unified decision-support architecture. The framework enables accurate prediction of traffic accident risk and simulation of “what-if” intervention scenarios to support real-time safety optimization in intelligent transportation environments. By leveraging heterogeneous inputs, including traffic dynamics, environmental conditions, road attributes, and temporal patterns, the system constructs a high-dimensional representation that captures complex nonlinear dependencies and evolving risk propagation across the network. A key innovation lies in the integration of a causal intervention mechanism and policy-guided decision layer, which jointly quantify intervention impact and identify optimal strategies for minimizing risk. The experimental results demonstrate that HPINA achieves a Test F1-score of 0.958 and an AUC of 0.989, outperforming strong baselines by up to 5.0% and 3.4%, while achieving a relative risk reduction of 0.091 and improved convergence stability with a validation loss of 0.042. These findings highlight the effectiveness of the proposed framework as an intelligent, scalable, and deployable system for real-world traffic safety management and smart city applications. Full article