Search Results (119)

The collision dynamics of binary seawater droplets are pivotal in marine engineering applications, like spray desalination and engine cooling. While high-fidelity simulations can resolve these dynamics, they are computationally prohibitive for rapid design and analysis. This study introduces the first interpretable machine learning (ML) framework to predict and elucidate the collision outcomes of head-on binary seawater droplets. A high-fidelity numerical dataset, generated via Modified Coupled Level Set-VOF (M-CLSVOF) simulations across a broad Weber number (We) range, serves as the foundation for training multiple classifiers. Among the tested algorithms, the Random Forest model achieved superior performance with 96.2% accuracy. The model’s predictions precisely identified the critical Weber number for the transition from coalescence to reflexive separation at We ≈ 22.3 for seawater. Moving beyond black-box prediction, we employed SHapley Additive exPlanations (SHAP) to quantitatively deconstruct the model’s decision-making process. SHAP analysis confirmed the dominance of the Weber number (75% contribution) and revealed the context-dependent role of the Reynolds number (25% contribution) in modulating the collision outcome. Furthermore, a comparative analysis with freshwater droplets quantified a 6% elevation in the critical Weber number for seawater, attributed to salinity-induced modifications in fluid properties. Finally, a machine-learned regime map in the We-Ohnesorge space was constructed, delineating the coalescence and separation boundaries. This work establishes ML as a powerful, interpretable surrogate model that not only delivers rapid, accurate predictions but also extracts fundamental physical insights, offering a valuable paradigm for optimizing marine spray systems. Full article

Collision avoidance between unmanned aerial vehicles (UAVs) and non-cooperative targets (e.g., off-nominal operations or birds) presents significant challenges in urban air mobility (UAM). This difficulty arises due to the highly dynamic and unpredictable flight intentions of these targets. Traditional collision-avoidance methods primarily focus on cooperative targets or non-cooperative ones with fixed behavior, rendering them ineffective when dealing with highly unpredictable flight patterns. To address this, we introduce a deep reinforcement learning-based collision-avoidance approach leveraging global and local intent prediction. Specifically, we propose a Global and Local Perception Prediction Module (GLPPM) that combines a state-space-based global intent association mechanism with a local feature extraction module, enabling accurate prediction of short- and long-term flight intents. Additionally, we propose a Fusion Sector Flight Control Module (FSFCM) that is trained with a Dueling Double Deep Q-Network (D3QN). The module integrates both predicted future and current intents into the state space and employs a specifically designed reward function, thereby ensuring safe UAV operations. Experimental results demonstrate that the proposed method significantly improves mission success rates in high-density environments, with up to 80 non-cooperative targets per square kilometer. In 1000 flight tests, the mission success rate is 15.2 percentage points higher than that of the baseline D3QN. Furthermore, the approach retains an 88.1% success rate even under extreme target densities of 120 targets per square kilometer. Finally, interpretability analysis via Deep SHAP further verifies the decision-making rationality of the algorithm. Full article

High-speed train derailments can cause severe vehicle collisions with rail bridges and adjacent infrastructure; however, full-scale evidence for the collision response of trackside intrusion-protection walls and for material measures that limit concrete fragmentation remains scarce. This study addresses this safety-driven knowledge gap by reporting a full-scale collision test of a polyurea-coated reinforced concrete (RC) wall and by clarifying its governing response mechanisms and coating benefits. The inverted T-shaped RC wall was post-anchored to an existing deck and spray-coated with approximately 5 mm polyurea on the collision face and across the wall-footing junction. A 17.68 t container wagon was propelled to 34.59 km/h to reproduce the normal kinetic energy of a representative 68 t KTX car derailing at 300 km/h with a 3° collision angle. High-speed video tracking and post-test mapping captured displacements, rotations, and damage. The wall contained the container wagon without climb-over and without severe local crushing at the collision face; the response was dominated by stable wall-footing rocking, with a peak top displacement of 0.571 m, peak rotation of 19.9°, and residual inclination of approximately 15–17°. The peak collision-force estimate was approximately 1.17 MN, and most input energy (approximately 647–816 kJ) was dissipated through inelastic rocking and sliding while the anchors remained intact. The polyurea layer restrained spalling and fragment release and promoted a more global, repairable rocking-dominated damage state. These results provide rare full-scale benchmarks and mechanistic insight to support performance-based design and retrofit of derailment intrusion-protection walls for improved rail-bridge safety. Full article

Second-order damping oscillation models are incapable of precisely predicting superimposed and multi-fruit collision-induced oscillations. In view of this problem, an ARIMA-EEMD-LSTM hybrid model for predicting the oscillation trajectories of trellised tomatoes was proposed in this study. First, the oscillation trajectories of trellised tomatoes under different picking forces were captured with the aid of the Nokov motion capture system, and then the collected oscillation trajectory datasets were then divided into training and test subsets. Afterwards, the ensemble empirical mode decomposition (EEMD) method was employed to decompose oscillation signals into multiple intrinsic mode function (IMF) components, of which different components were predicted by different models. Specifically, high-frequency components were predicted by the long short-term memory (LSTM) model while low-frequency components were predicted by the autoregressive integrated moving average (ARIMA) model. The final oscillation trajectory prediction model for trellised tomatoes was constructed by integrating these components. Finally, the constructed model was experimentally validated and applied to an analysis of single-fruit oscillations and multi-fruit oscillations (including collision oscillations and superposition oscillations). The following experimental results were yielded: Under single-fruit oscillation conditions, the prediction accuracy reached an RMSE of 0.1008–0.2429 mm, an MAE of 0.0751–0.1840 mm, and an MAPE of 0.01–0.06%. Under multi-fruit oscillation conditions, the prediction accuracy yielded an RMSE of 0.1521–0.6740 mm, an MAE of 0.1084–0.5323 mm, and an MAPE of 0.01–0.27%. The research results serve as a reference for the dynamic harvesting prediction of tomato-picking robots and contribute to improvement of harvesting efficiency and success rates. Full article

The rapid growth of technology has introduced robots into daily life, necessitating navigation frameworks that enable safe, human-friendly movement while accounting for social aspects. Such methods must also scale to situations with multiple humans and robots moving simultaneously. Recent advances in Deep Reinforcement Learning (DRL) have enabled policies that incorporate these norms into navigation. This work presents a socially aware navigation framework for mobile robots operating in environments shared with humans and other robots. The approach, based on single-agent DRL, models all interaction types between the ego robot, humans, and other robots. Training uses a reward function balancing task completion, collision avoidance, and maintaining comfortable distances from humans. An attention mechanism enables the framework to extract knowledge about the relative importance of surrounding agents, guiding safer and more efficient navigation. Our approach is tested in both dynamic and static obstacle environments. To improve training efficiency and promote socially appropriate behaviors, Imitation Learning is employed. Comparative evaluations with state-of-the-art methods highlight the advantages of our approach, especially in enhancing safety by reducing collisions and preserving comfort distances. Results confirm the effectiveness of our learned policy and its ability to extract socially relevant knowledge in human–robot environments where social compliance is essential for deployment. Full article

Robots are used more and more in manufacturing, especially in tasks like robotic machining, where understanding their vibration behavior is very important. However, robot vibrations vary with posture, and evaluating all representative postures requires significant time and cost. This study proposes a deep learning (DL) based transfer learning (TL) approach to predict robot vibration behavior using fewer experiments. A large dataset was collected from a KUKA KR300 robot (Robot A) by testing nearly 250 postures. This dataset was then used to train a model to predict modal parameters such as natural frequencies (ω_n), damping ratios (ξ), and modal stiffness (k) within the workspace. TL was then used to apply the knowledge from Robot A to two other robots: a Comau NJ 650-2.7 (Robot B, high-payload) and an ABB IRB 4400 (Robot C, low-payload). Only a small number of postures were tested for Robots B and C. They were chosen carefully to cover different workspace areas and avoid collisions. Hammer tests were performed, and a four-step process was used to identify the real vibration modes. Stabilization diagrams were applied to confirm valid modes and remove noise. The results show that TL can accurately predict modal parameters for both Robot B and Robot C, even with limited data. These predictions were also used to estimate frequency response functions (FRFs), which matched well with experimental results. The main novelties of this work are: achieving accurate prediction of posture-dependent dynamics using minimal experimental data, demonstrating generalization across robots with different payload capacities, and revealing that data coverage across the workspace is more critical than dataset size. Full article

This article presents a novel methodology for evaluating the safety of forklift operations in intralogistics systems using a multi-user simulation model integrated with virtual reality (MUSM-VR). Set against the backdrop of persistent safety challenges in warehouse environments, particularly for inexperienced operators, the study addresses the need for proactive safety assessment tools. The authors develop a simulation framework within the FlexSim 24.2 environment, enhanced by proprietary VR and server integration libraries, enabling interactive, immersive testing of warehouse layouts and operational scenarios. Through literature review and analysis of risk factors, the methodology incorporates human, infrastructural, organizational, and technical dimensions of forklift safety. A case study involving inexperienced participants demonstrates the model’s capability to identify high-risk areas, assess operator behavior, and evaluate the impact of visibility and speed parameters on collision risk. Results highlight the effectiveness of MUSM-VR in pinpointing hazardous intersections and inform design recommendations such as optimal speed limits and layout modifications. The study concludes that MUSM-VR not only facilitates early-stage safety analysis but also supports ergonomic design, operator training, and iterative testing of preventive measures, aligning with Industry 4.0 and 5.0 paradigms. The integration of immersive simulation into design and safety workflows marks a significant advancement in intralogistics system development. Full article

With the continuous maturation of prefabricated buildings, the errors and efficiency issues in the design of prefabricated buildings have gradually drawn the attention of architectural designers. The characteristics of standardized design for prefabricated buildings also provide a foundation for the application of computer-learning methods in the field of architectural design, thereby improving design quality and efficiency. This study combined BIM technology to construct the information data on prefabricated buildings, applied the transfer-learning method to build the training model, and utilized the traditional architectural design collision concept to construct a prediction model applicable to the collision detection of prefabricated building design. The training set and test set were constructed in a 9:1 ratio, and the loss function and accuracy function were calculated. The error rate of the model was verified to be within 10% through trial calculations based on engineering cases. The results show that, in the selected engineering cases, the collision detection accuracy of the model reached 90.3%, with an average absolute error (MAE) of 0.199 and a root mean square error (RMSE) of 0.245. The prediction error rate was controlled within 10%, representing an approximately 65% improvement in efficiency compared to traditional manual inspections. This method significantly improves the efficiency and accuracy of collision detection, providing reliable technical support for the optimization of prefabricated building design. Full article

This study presents a comprehensive simulation-driven approach to identify and mitigate bottlenecks in the supply flows of an automotive manufacturing system. The supply process relies on a Kanban-based assembly line replenishment, supported by multiple material transports per shift using tugger trains. To analyze flow constraints, the research combines time–motion studies with data from a Real-Time Locating System (RTLS), enabling spatial-temporal mapping of material movements. Based on this data, digital-twin simulation models of the supply process were developed and validated. These models allowed testing of improvements aimed at increasing throughput and efficiency. The proposed methodology demonstrates effective bottleneck resolution and provides a structured framework for data collection and simulation integration. Unlike traditional observation-based approaches, the use of RTLS enables precise detection of routing deviations and operator behaviors. The simulation model was tested under real operating conditions and validated against ground-truth data. Results showed a reduction in collisions and delivery delays, as well as measurable productivity and financial gains. This approach offers a practical and transferable method for optimizing intralogistics in modern production environments. Full article

As a high-market-value sector, the consumer electronics industry is particularly vulnerable to reputational damage from surface defects in shipped products. However, the high level of automation and the short product life cycles in this industry make defect sample collection both difficult and inefficient. This challenge has led to a severe shortage of publicly available, comprehensive datasets dedicated to surface defect detection, limiting the development of targeted methodologies in the academic community. Most existing datasets focus on general-purpose object categories, such as those in the COCO and PASCAL VOC datasets, or on industrial surfaces, such as those in the MvTec AD and ZJU-Leaper datasets. However, these datasets differ significantly in structure, defect types, and imaging conditions from those specific to consumer electronics. As a result, models trained on them often perform poorly when applied to surface defect detection tasks in this domain. To address this issue, the present study introduces a specialized optical sampling system with six distinct lighting configurations, each designed to highlight different surface defect types. These lighting conditions were calibrated by experienced optical engineers to maximize defect visibility and detectability. Using this system, 14,478 high-resolution defect images were collected from actual production environments. These images cover more than six defect types, such as scratches, plain particles, edge particles, dirt, collisions, and unknown defects. After data acquisition, senior quality control inspectors and manufacturing engineers established standardized annotation criteria based on real-world industrial acceptance standards. Annotations were then applied using bounding boxes for object detection and pixelwise masks for semantic segmentation. In addition to the dataset construction scheme, commonly used semantic segmentation methods were benchmarked using the provided mask annotations. The resulting dataset has been made publicly available to support the research community in developing, testing, and refining advanced surface defect detection algorithms under realistic conditions. To the best of our knowledge, this is the first comprehensive, multiclass, multi-defect dataset for surface defect detection in the consumer electronics domain that provides pixel-level ground-truth annotations and is explicitly designed for real-world applications. Full article

Despite navigation advancements in enhanced sensor utilization and increased focus on maritime training and education, most marine accidents still involve collisions with high human involvement. Furthermore, navigators’ knowledge and application of the most often misunderstood Rule 10 Traffic Separation Schemes (TSS) according to the Convention on the International Regulations for Preventing Collisions at Sea (COLREG) represents the first focus in this study. To provide insight into the level of understanding and knowledge regarding COLREG Rule 10, a customized, worldwide survey has been created and disseminated among marine industry professionals. The survey results reveal a notable knowledge gap in Rule 10, where we initially assumed that more than half of the respondents know COLREG regulations well. According to the probability calculation and chi-square test results, all three categories (OOW, Master, and others) have significant rule misunderstanding. In response to the COLREG misunderstanding, together with the increasing density of maritime traffic, the implementation of Decision Support Systems (DSS) in navigation has become crucial for ensuring compliance with regulatory frameworks and enhancing navigational safety in general. This study presents a structural approach to vessel prioritization and decision-making within a DSS framework, focusing on the classification and response of the own vessel (OV) to bow-crossing scenarios within the TSS. Through the real-time integration of AIS navigational status data, the proposed DSS Architecture offers a structured, rule-compliant architecture to enhance navigational safety and the decision-making process within the TSS. Furthermore, implementing a Fall-Back Strategy (FBS) represents the key innovation factor, which ensures system resilience by directing operator response if opposing vessels disobey COLREG rules. Based on the vessel’s dynamic context and COLREG hierarchy, the proposed DSS Architecture identifies and informs the navigator regarding stand-on or give-way obligations among vessels. Full article

The ability to autonomously generate up-to-date 3D models of robotic workcells is critical for advancing smart manufacturing, yet existing Next-Best-View (NBV) methods often rely on paradigms ill-suited for the fixed-base manipulators found in dynamic industrial environments. To address this gap, this paper proposes a novel NBV method for the complete exploration of a 6-DOF robotic arm’s workspace. Our approach integrates collision-based information gain metric, a potential field technique to generate candidate views from exploration frontiers, and a tunable fitness function to balance information gain with motion cost. The method was rigorously tested in three simulated scenarios and validated on a physical industrial robot. Results demonstrate that our approach successfully maps the majority of the workspace in all setups, with a balanced weighting strategy proving most effective for combining exploration speed and path efficiency, a finding confirmed in the real-world experiment. We conclude that our method provides a practical and robust solution for autonomous workspace mapping, offering a flexible, training-free approach that advances the state-of-the-art for on-demand 3D model generation in industrial robotics. Full article

The automatic identification of traffic collisions is an emerging topic in modern traffic surveillance systems. The increasing number of surveillance cameras at urban intersections connected to traffic surveillance systems has created new opportunities for leveraging computer vision techniques for automatic collision detection. This study investigates the effectiveness of transfer learning utilizing pre-trained deep learning models for collision detection through dashcam images. We evaluated several state-of-the-art (SOTA) image classification models and fine-tuned them using different hyperparameter combinations to test their performance on the car collision detection problem. Our methodology systematically investigates the influence of optimizers, loss functions, schedulers, and learning rates on model generalization. A comprehensive analysis is conducted using 7 performance metrics to assess classification performance. Experiments on a large dashcam-based images dataset show that ResNet50, optimized with AdamW, a learning rate of 0.0001, CosineAnnealingLR scheduler, and Focal Loss, emerged as the top performer, achieving an accuracy of 0.9782, F1-score of 0.9617, and IoU of 0.9262, indicating a strong ability to reduce false negatives. Full article

Epidemiological analysis has revealed key insights into the frequency, severity, and circumstances surrounding subway-to-pedestrian incidents; however, there remains a lack of available impact test data specific to this impact type that can be used in modelling and countermeasure design studies. To address this gap, nine controlled impact tests were conducted using a cylindrical headform to derive force–penetration relationships for foam, as well as foam encased in 1 mm aluminium or 3 mm ABS shells. These relationships were validated in MADYMO multibody simulations. Building on a previous multibody computational study of subway-to-pedestrian collisions this research evaluates three passive countermeasure designs using a reduced simulation test matrix: three impact velocities (8, 10, and 12 m/s) and a trough depth of 0.75 m. In subway collisions, due to the essential rigidity of a subway front relative to a pedestrian, it is the pedestrian stiffness characteristics that primarily dictate the contact dynamics, as opposed to a combined effective stiffness. However, the introduction of energy-absorbing countermeasures alters this interaction. Results indicate that modular energy-absorbing panels attached to the train front significantly reduced the Head Injury Criterion (HIC) (by 90%) in the primary impact and pedestrian-to-wheel contact risk (by 58%), with greater effectiveness when a larger frontal area was covered. However, reducing primary impact severity alone did not substantially lower total fatal injury risk. A rail-guard design, used in combination with frontal panels, reduced secondary impact severity and led to the largest overall reduction in fatal injuries. This improvement came with an expected increase in hospitalisation-level outcomes, such as limb trauma, reflecting a shift from fatal to survivable injuries. These findings demonstrate that meaningful reductions in fatalities are achievable, even with just 0.5 m of available space on the train front. While further development is needed, this study supports the conclusion that subway-to-pedestrian fatalities are preventable. Full article

Deep Reinforcement Learning (DRL)-based algorithms have demonstrated substantial effectiveness in tackling complex control problems for autonomous underwater vehicles (AUVs). This paper attempts to evaluate reinforcement learning (RL)-based methods for AUV trajectory planning by incorporating a model of a vehicle’s full motion. In this study, the agent (AUV) is assumed to have no prior knowledge of the environment in which it navigates. Instead, it only receives inputs from navigation sensors and a simulated sonar. Additionally, in the article, a reward function is proposed and described, along with its optimization process, to elicit the desired behaviors in the underwater vehicle. The models are trained and tested on simplified electronic navigation chart (ENC) maps, followed by a comparative analysis against five effective classical methods for trajectory planning. The proposed solution enables efficient, collision-free route planning for the autonomous underwater vehicle, taking its motion dynamics into account to reach the designated target successfully. Full article