Search Results (1,095)

Autonomous vehicles operating at signalized intersections face fundamental challenges arising from queue dynamics, signal-phase transitions, and tightly coupled multi-vehicle interactions. Conventional motion-planning methods, which rely primarily on instantaneous perception, are inherently reactive and struggle to reason about short-term traffic evolution. This paper presents a Transformer-based predictive motion-planning framework that embeds short-term traffic state prediction directly into the structure of the planning problem. A lightweight spatial–temporal Transformer model is designed to forecast traffic occupancy, queue evolution, and interaction patterns using historical trajectories, signal-phase information, and road topology. By converting predicted traffic dynamics into explicit spatial–temporal constraints, a hierarchical motion planner jointly optimizes path geometry and speed profiles through dynamically constructed feasible corridors. The proposed framework is evaluated using a joint SUMO–CARLA simulation platform under realistic traffic conditions derived from real-world datasets, including pNEUMA and CitySim. The experimental results across straight-through, queueing, and turning scenarios show that prediction-aware planning significantly reduces high-risk driving time and intersection travel time while maintaining stable real-time computational performance. Beyond scenario-level improvements, the results indicate that transforming traffic prediction into planning constraints provides a generalizable paradigm for proactive, feasibility-aware autonomous driving at signalized intersections. From a methodological perspective, the proposed framework can be interpreted through the lens of symmetry and asymmetry in intelligent transportation systems: the conventional symmetric decoupling between prediction and planning modules is deliberately broken by embedding predicted traffic states as time-varying, directionally asymmetric constraints, while the permutation symmetry of the multi-head attention mechanism is preserved over lane-segment tokens to provide a structured inductive bias for traffic state forecasting. This symmetry-aware design highlights how controlled symmetry breaking in modeling and optimization can yield safer, more efficient, and more adaptive autonomous driving behaviors in signalized urban environments. Full article

When UAV(Unmanned Aerial Vehicle) carry out wildlife inspection for biodiversity protection, there are challenges such as low target, complex background, variable shape and serious occlusion, which lead to insufficient accuracy and a high misjudgment rate of the existing lightweight detection model. We propose an improved lightweight YOLOv8n model, which aims to achieve higher accuracy and more real-time animal target detection under the UAV platform. To address the issue of small target features being easily lost in the deep network, we introduce a dynamic upsampling convolution for accurate feature-aware upsampling, which can effectively reconstructs target details and suppress background noise. In order to enhance the feature discrimination ability of the model in complex environments, a convolution block attention mechanism was integrated in the model, and the key features of the target were adaptively focused through the channel–spatial dual attention mechanism. Finally, in order to improve the positioning accuracy in dense and occluded scenes, we used MPDIoU loss function to optimize the bounding box regression, and achieve more stable and accurate alignment by minimizing the vertex distance between the prediction box and the real box. Experiments on public data sets show that the detection accuracy and efficiency of the proposed model are significantly improved compared with the original YOLOv8n: the number of model parameters is reduced by 10.7%, the amount of calculation is reduced by 9.9%, and the inference speed is improved by 25%. In terms of comprehensive performance, our method achieved a mAP@0.5 of 96.4%, a mAP@0.5:0.95 improvement of 6.0 percentage points, and an F1 score of 93.5%, while also significantly reducing the false positive rate. Experiments on self-made aerial animal data sets further fully verify that the algorithm can achieve high-precision real-time animal target detection in the actual UAV platform. Full article

The high speed and manoeuvrability of cross-domain unmanned aerial vehicles (CDUAVs) significantly reduce the handover window between mid-terminal guidance stages, challenging reliable target acquisition. To address this, we propose an optimisation method for interceptor selection and field-of-view (FOV) cooperative coverage based on high-probability region (HPR) modelling. First, a predictive error covariance propagation model is constructed based on error propagation theory, and the HPR is established via eigenvalue decomposition. Second, the cooperative detection by heterogeneous interceptor seekers is formulated as a coverage optimisation problem with mixed FOV, and a cost minimisation model under complete coverage constraints is established. Finally, an improved genetic algorithm (IGA) is employed for solution, and a coverage area ratio screening mechanism based on two-dimensional close-packing theory is designed to enhance optimisation efficiency. Simulation results demonstrate that the probabilistic modelling approach for CDUAV HPR can accurately characterise the anisotropic distribution of target position uncertainty; the algorithmic mechanism reduces redundant computational load by 62.5% and shortens the optimisation time by 36.7%; the intelligent coverage optimisation framework provides a more generalisable solution for cooperative detection by heterogeneous interceptors’ seekers under conditions of target localisation uncertainty. Full article

The two-speed transmission system significantly enhances the powertrain matching performance of heavy-duty electric military armored vehicles by optimizing high-torque output at low speed and energy efficiency at high speed. However, most existing electric vehicles do not incorporate driving styles or real-time driving condition prediction into their shift control strategies, resulting in suboptimal gear shift timing and smoothness that fail to align with driver expectations and operational requirements. To address these limitations, this study focuses on the two-speed automated manual transmission (AMT) system in heavy-duty electric military armored vehicles. Firstly, a comprehensive shift control model is established, integrating key components such as the drive motor and power battery. Furthermore, a shift control strategy based on vehicle speed prediction and driving style recognition is proposed. The operational logic of this strategy is systematically analyzed under various driving cycles. Simulation and hardware-in-the-loop (HIL) results confirm the performance gains. Simulation and hardware-in-the-loop (HIL) results indicate that the proposed approach improves vehicle power performance by 21.36%, increases energy efficiency by 3.94%, and reduces powertrain shock by 31.81% compared to the conventional vehicle-speed-based gear shifting method. Compared to the adaptive shift schedule design method, the proposed approach reduces shifting frequency by 21.43% and improves ride comfort by at least 19.17% while maintaining comparable dynamic performance and energy efficiency. Full article

The dust extraction impeller is a core component of the vehicle engine auxiliary system that filters dust from the intake air to ensure stable engine operation; its reliability directly affects the performance and operational safety of the vehicle. Critically, the dust extraction impeller can exhibit severe erosion wear in extreme environments, but conventional degradation testing methods are costly and require considerable time to complete. Therefore, this study conducted accelerated degradation testing using the change in impeller blade thickness as the degradation indicator and the dust concentration and impeller rotational speed as dual elevated stress factors to obtain time-series degradation data from 48 blade samples. Linear, exponential, power-law, natural logarithmic, and Gompertz models were subsequently fit to the data for a single sample, and then the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method was employed to select the optimal degradation trajectory model. The accuracy of the selected linear model was verified using the data from all samples, confirming that it can be applied to predict the degradation of the dust extraction impeller over time. The contribution of this study comprises the establishment of a degradation assessment framework combining accelerated degradation testing with TOPSIS-based model selection to provide a practical basis for the reliability design and maintenance planning of vehicle dust extraction impellers operating in extreme environments. Full article

Autonomous Underwater Vehicles (AUVs) are widely employed for deep sea exploration and underwater operations, but their navigation performance is often degraded in complex environments due to time-varying measurement noise, abnormal observations, and Doppler Velocity Log (DVL) outages. To address these challenges, this paper proposes an integrated SINS/DVL/PS navigation framework that combines an Adaptive Huber and Sage–Husa Extended Kalman Filter (AHR-EKF) with a Nonlinear AutoRegressive with eXogenous inputs (NARX)-based velocity prediction model. The AHR-EKF effectively suppresses outliers and adapts to time-varying noise, thereby enhancing filter stability and state estimation accuracy. During DVL outages, the NARX model predicts short-term AUV velocity using propeller speed, velocity increments from the navigation system, and attitude information as exogenous inputs. This data-driven approach compensates for lag and mismatch in propeller-based velocity measurements, while capturing both short-term fluctuations and overall velocity trends. Simulations and sea trials were conducted to validate the method. In the simulation experiment during DVL outages, the V-NARX method achieved east and north positioning of RMS errors of 8.397 m and 6.530 m, compared with 24.699 m and 10.218 m for the V-RPM method. In the sea trial, the V-NARX method achieved east and north RMS errors of 41.160 m and 28.023 m, respectively, compared with 52.820 m and 67.057 m for V-RPM, corresponding to reductions of 22.1% and 58.2%. The proposed method maintains trajectory continuity and effectively suppresses rapid INS error accumulation during DVL outages, significantly enhancing emergency navigation capability under DVL outages. Although its positioning accuracy does not match that of normal DVL operation, the method provides a practical and reliable engineering solution for continuous AUV navigation when DVL is unavailable. Full article

Traffic crash severity modeling is an important and promising aspect of road safety research. It aims to assess how key human-, vehicle-, roadway-, and environment-related factors interact to shape severity outcomes of crashes. Existing studies in this regard have predominantly relied on traditional statistical methods and simple machine learning approaches. While statistical analysis techniques are often based on unrealistic underlying assumptions, conventional machine learning models often suffer from interpretability issues. This study proposes an interpretable crash severity prediction framework that combines machine learning and deep learning models with post hoc explainability using SHAP. The research utilizes crash data from a rapidly developing region of Qassim in the Kingdom of Saudi Arabia. Crash severity was classified into three groups: fatal, injury, and property damage only (PDO). Four predictive models were developed and evaluated. These include: Random Forest (RF), Support Vector Machine (SVM), Feedforward Neural Network (FFNN), and Gradient-Boosting Machine (GBM). Various performance metrics, including accuracy, balanced accuracy, macro F1-score, and ROC–AUC, were used to assess the model. Descriptive statistical analysis showed that speeding, head-on collisions, wrong-way driving, blown-out tires, and driver fatigue are the major causes of fatal injuries. Empirical results revealed that the proposed prediction models achieved an accuracy ranging between 0.94 and 0.96 for the test data, with the RF model slightly outperforming the other models. Model interpretability analysis indicated that crash severity is significantly influenced by parameters such as crash cause, type, speed, and roadway type. The proposed framework demonstrated the effectiveness of machine learning (ML) and deep learning (DL) approaches for crash severity prediction and provides practical insights to support roadway safety interventions and policy development aimed at reducing severe and fatal crashes. Full article

Accurately predicting human lane-changing (LC) decisions is critical for enhancing the safety and efficiency of autonomous driving. Most existing machine learning-based LC decision models rely on immediate neighboring vehicle interaction features, which may fail to capture drivers’ consideration of long-term traffic conditions in the target lane. Using discretionary LC trajectory data from the US101 dataset, this paper first qualitatively identifies key latent variables influencing LC decisions, then quantitatively ranks these factors using feature importance analysis, and finally constructs a prediction model based on ensemble learning. The analysis reveals that drivers consider not only neighboring vehicles but also multi-vehicle information further ahead, particularly the average speed and average spacing of multiple preceding vehicles. Feature importance ranking shows that safety-related features, especially the spacing with the following vehicle in the target lane ($d_{Lag}$, 0.187), rank significantly higher than benefit-related features such as the average speed of the target lane (${\overline{v}}_T$, 0.091), suggesting that safety considerations play a dominant role in the observed LC decisions. Among five imbalanced processing methods, SMOTE+Tomek achieves the best balance (F1 = 0.68). When the Full Feature Set is used, the KNN model achieves the best performance (F1 = 0.79, AUC = 0.97) among six baseline models. This study contributes to the understanding of LC behavior and provides insights that could inform future development of LC prediction models for autonomous vehicles. Full article

A methodology for the development of nonlinear model predictive control for thermal management of a 40-ton fuel-cell heavy-duty truck is presented, using the medium-temperature cooling circuit as a case study. The approach integrates control-oriented modeling, parameter estimation, and experimental validation based on drivetrain test bench measurements under controlled high-temperature ambient conditions. A lumped-parameter model of the medium-temperature circuit, including coolant, oil, electric motors, and power-electronics auxiliaries, is derived and implemented in a Simulink environment, with heat-transfer parameters calibrated from test bench data and radiator air-side resistance and fan characteristics derived from CFD simulations and manufacturer specifications, respectively. Model parameters are identified using a systematic estimation procedure and the resulting model is validated against long-duration roller test measurements, achieving coefficients of determination above R² = 0.9 and normalized RMSE values below 10% for all key temperatures. The validated model is then used as the prediction model in a model predictive controller that manipulates radiator fan and coolant-pump speeds, while treating component heat losses, vehicle speed and ambient temperature as measured disturbances. The controller is evaluated in a model-in-the-loop environment for representative long-haul and urban driving cycles and different ambient temperatures, and its performance is benchmarked against conventional rule-based and PI-based control strategies. Depending on the driving cycle and ambient conditions, the proposed NMPC reduces cooling system energy consumption by up to 39.6% compared to a PI controller (VECTO Urban Delivery cycle, 35 °C ambient), with an average reduction of 16.6% across all investigated driving cycles and ambient conditions, without a significant increase in average or maximum coolant temperature. The proposed methodology provides a transferable workflow for developing predictive thermal management control in fuel-cell heavy-duty vehicles and other complex automotive cooling systems. Full article

Analyses of electric two-wheeler (E2W) accident causes often overlook individual heterogeneity and non-linear effects among influencing factors, causing risk prediction models to fail. Based on 742 motor vehicle–E2W collisions from the China In-Depth Accident Study (CIDAS) database, we established the correlated random parameter ordered probit model with heterogeneity in means (CRPOPH) and the generalized additive model (GAM) to analyze the effects of discrete and continuous variables on E2W accident severity. The results show that injury severity increases significantly for the following characteristics: male, 51–60 years old, <170 cm, SUV or truck, intersection road, non-asphalt pavement, daytime and side impact accidents. With all other factors held constant, injury severity decreases with increasing seat height and seat–handlebar distance; when the wheelbase is approximately between 1000 mm and 1400 mm, injury severity tends to be the lowest; when the E2W speed is about 15–30 km/h, injury severity is positively correlated with speed; in other speed ranges, E2W speed is negatively correlated with injury severity. Compared with traditional linear models, the proposed method achieves both high interpretability and high fitting accuracy in modeling E2W accident severity. Full article

Corner-module electric vehicles equipped with four-wheel independent drive, four-wheel independent steering, and electromechanical braking (EMB) actuators provide a flexible platform for software-defined chassis control, but braking-in-turn maneuvers impose severe longitudinal–lateral coupling and competition for tire adhesion resources. This paper proposes an actuator-oriented hierarchical coordinated control strategy for EMB-based corner-module vehicles. At the upper level, a Model Predictive Controller optimizes lateral tire force allocation under a tire-friction-ellipse hard constraint and coordinates the four-wheel steering response. At the lower level, a three-intensity adaptive braking-force distribution algorithm converts the vehicle-level demand into wheel-level EMB clamping-force commands while considering braking intensity, steering intensity, load transfer, and yaw stability. To improve actuator tracking accuracy, the EMB subsystem combines nonlinear actuator modeling, offline parameter identification, online recursive-least-squares correction, and force–speed–position cascade control. MATLAB (R2025b)/Simulink-CarSim co-simulation and EMB hardware-in-the-loop (HIL) tests verify the proposed strategy under fixed-angle emergency braking and lane-change braking conditions with high, low, and variable-adhesion roads. The results show improved trajectory tracking and yaw stability, reduced braking-torque fluctuation, and faster EMB clamping-force response, demonstrating the suitability of the proposed actuator-level coordination method for intelligent electric chassis applications. Full article

Real-time traffic safety analysis is necessary to determine proactive risks associated with traffic conflicts. This study presents a driving-risk detection framework based on high-precision naturalistic vehicle trajectory data to support host vehicle driver-warning systems. A rear-end conflict identification approach based on time-to-collision (TTC) is employed to detect vehicle interactions as safe or unsafe. To capture temporal driving patterns, frame-level observations are transformed into sequential samples using a sliding-window strategy while preserving the natural class imbalance of real-world traffic data. Several conventional machine learning models, including CatBoost, LightGBM, XGBoost, Random Forest, Extra Trees, Decision Tree, and SVM, as well as recurrent deep learning models such as Simple RNN, LSTM, and GRU, are evaluated using leave-one-subject-out cross-validation across seven expressways. Among the evaluated models, the Simple RNN achieves a recall of 99.12% and an F1-score of 98.48%, outperforming the conventional machine learning models. Its predictive performance is comparable to that of LSTM and GRU while offering lower inference latency, making it suitable for real-time deployment. A SHAP-based Explainable AI analysis is conducted to identify the most influential factors in conflict detection and to provide insight into model predictions. The analysis supports that host vehicle speed, preceding vehicle speed, and inter-vehicle gap are the primary determinants of rear-end conflict risk. This proactive and interpretable framework, evaluated offline on naturalistic trajectory data, demonstrates strong potential for integration into real-time driver-warning systems. Full article

To address the issues of slow response to preceding vehicles and poor string stability in distributed platoon control of connected and autonomous vehicles (CAVs) under mixed traffic flow, this paper proposes a sliding mode control method based on LSTM trajectory prediction, denoted as LSTM-SMC, within a multi-agent framework. The LSTM model is trained using the HighD naturalistic driving dataset to achieve high-precision prediction of the leader vehicle’s trajectory over a horizon of 3 s, with root mean square errors (RMSE) of 8.52 m in the X-direction and 0.896 m in the Y-direction. The predicted trajectory information is converted into a preview error and embedded directly into the design of the sliding surface, enabling each following vehicle to anticipate disturbances before they propagate. A diminishing preview gain strategy (${\gamma }_1=0.4$, ${\gamma }_2=0.2$, ${\gamma }_3=0.1$) is employed to suppress error propagation along the platoon, while a saturation function is introduced to eliminate chattering and ensure smooth control inputs. Three simulation scenarios—prescribed leading, HDV (human-driven vehicle) leading, and curved road scenario—are constructed to validate the proposed method against traditional constant time headway (CTH) control, pure sliding mode control (SMC), and LSTM-MPC. Results demonstrate that under extreme conditions, the proposed method reduces the speed RMSE of the 3rd following vehicle by 18.3% compared to CTH and by 39.7% compared to SMC. Under HDV leading conditions, all string stability amplification factors are less than 1, and the position RMSE of the 3rd vehicle is only 5.03 m in the curved road scenario. Compared with LSTM-MPC, the proposed LSTM-SMC achieves comparable tracking accuracy while reducing computational cost by 1.43–3.51×. The proposed method achieves a native integration of prediction and robust control, significantly improving tracking accuracy, string stability, and computational efficiency across diverse operating conditions in mixed traffic flow. Full article

In this study, we propose SiStNet, a single-stage deep learning architecture for vehicle detection in autonomous driving scenarios. The proposed architecture is trained entirely from scratch on domain-specific data without relying on pretrained backbones and is evaluated against representative baseline detectors under identical training conditions. Experiments are conducted on the KITTI dataset under a consistent training and evaluation protocol. An ablation study conducted under a reduced training budget (20% of data, 30 epochs) revealed that multi-scale detection, data augmentation, and anchor-based prediction did not contribute positively to detection performance under the given training conditions. Based on these findings, the final SiStNet architecture was simplified by removing these three components and re-trained under the full training budget. The resulting model achieves a mean Average Precision (mAP) of $0.5033\pm 0.0072$ and a recall of $0.6935\pm 0.0214$, representing substantial improvements over the initially reported values ($0.3896$ and $0.439$, respectively). The inference speed of SiStNet is $24.41\pm 0.02$ FPS, which satisfies the real-time threshold of 20 FPS defined in this study. The model achieves lower mAP than baseline detectors that employ larger and deeper architectures; all models were trained from scratch under identical conditions, so the accuracy gap reflects architectural capacity differences rather than pretraining advantages. SiStNet is presented as a domain-specific, scratch-trained alternative that achieves competitive detection performance without reliance on large-scale pretraining, at the cost of lower mAP relative to deeper baselines. Full article

This study proposes an adaptive multi-mode graph search algorithm that integrates spatial previewing with terminal analytics to address node proliferation and terminal oscillation in path planning for four-wheel independent steering (4WIS) vehicles under complex, low-speed conditions. By employing line-of-sight checking and the Douglas–Peucker algorithm to extract the environmental topological skeleton, the proposed method generates Predictive Spatial Profiling (PSP) fields that precisely quantify channel safety margins. Departing from conventional soft-weight arbitration, a dynamic driving state machine leverages these rigid spatial constraints to deterministically prune redundant expansion branches—including Ackermann steering, crab steering, and in-place rotation—prior to node generation. Furthermore, a comprehensive cost function incorporating a mode-switching penalty and a gradient-heading heuristic is formulated to accelerate search convergence. To circumvent reliance on traditional empirical distance thresholds, a topology-triggered, multi-dimensional terminal analytical strategy is introduced, enabling a seamless transition from discrete search node expansion to continuous curve generation near the target. Extensive simulations demonstrate that the proposed algorithm reduces both the node expansion scale and optimization time by over 80% compared with conventional unconstrained methods, while effectively mitigating chaotic motion-mode transitions. Ultimately, integrating environmental spatial dimensionality reduction with terminal analytics yields a highly efficient and smooth global path-planning solution for 4WIS vehicles. Full article