Search Results (132)

Image segmentation is a foundation for autonomous driving frameworks that empower vehicles to explore and navigate their surrounding environment. It gives a fundamental setting to the dynamic cycles by dividing the image into significant parts like streets, vehicles, walkers, and traffic signs. Precise segmentation ensures safe navigation and the avoidance of collisions, while following the rules of traffic is very critical for seamless operation in self-driving cars. The most recent deep learning-based image segmentation models have demonstrated impressive performance in structured environments, yet they often fall short when applied to the complex and unpredictable conditions encountered in autonomous driving. This study proposes an Adaptive Ensemble Attention (AEA) mechanism within a Generative Adversarial Network architecture to deal with dynamic and complex driving conditions. The AEA integrates the features of self, spatial, and channel attention adaptively and powerfully changes the amount of each contribution as per input and context-oriented relevance. It does this by allowing the discriminator network in GAN to evaluate the segmentation mask created by the generator. This explains the difference between real and fake masks by considering a concatenated pair of an original image and its mask. The adversarial training will prompt the generator, via the discriminator, to mask out the image in such a way that the output aligns with the expected ground truth and is also very realistic. The exchange of information between the generator and discriminator improves the quality of the segmentation. In order to check the accuracy of the proposed method, the three widely used datasets BDD100K, Cityscapes, and KITTI were selected to calculate average IoU, where the value obtained was 89.46%, 89.02%, and 88.13% respectively. These outcomes emphasize the model’s effectiveness and consistency. Overall, it achieved a remarkable accuracy of 98.94% and AUC of 98.4%, indicating strong enhancements compared to the State-of-the-art (SOTA) models. 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

Passenger safety remains a primary goal in vehicle engineering, requiring the development of advanced passive safety systems to reduce injuries during collisions. Impact attenuators (particularly for race cars) are a crucial component for the safety of the driver. The impact of the impact attenuator (IA) is demonstrated by the behavior of a seat-belted dummy in a frontal collision with a rigid wall. The aim of this paper is to confirm the qualities of water as a damping agent in the manufacturing of the IA. To reach a conclusion, a theoretical model is used and experimental tests are performed. Once the loads operating on the dummy have been identified, it is confirmed that they fall within the range that the existing requirements recommend. The car is viewed as a structure with a seat-belt-fastened dummy and an impact attenuator. Research is being conducted on a new water-based impact attenuator technology. A frontal collision of the car–dummy assembly was taken into consideration when analyzing the dummy’s behavior in accordance with the criteria. A simulation program was used to calculate the accelerations at various points on the mannequin’s body as well as the force that manifested on the seat belts. So, the good qualities of IAs using water are revealed and support designers in their efforts to obtain better shock behavior. In the simulation, the variation of internal energy accumulated by the vehicle, displacements and velocities of various points on the chassis, as well as the accelerations of the vehicle and the occupant were determined. In the experiment, the vehicle velocities for both test cases were established and used in the simulation, and the accelerations of the vehicle and dummy were measured. The assessment was carried out by comparing experimental and simulation data, focusing on acceleration values recorded on both the dummy and the vehicle. Evaluation criteria such as HIC and ThAC were applied to determine the severity of the impact and the effectiveness of the proposed water-based attenuator. Full article

Background and Objectives: Older adults are a vulnerable population to unintentional injuries due to age-related physiological decline and the presence of various chronic conditions. Unintentional injuries occurring in the home, such as falls, burns, poisoning, cuts, and suffocation, have been reported at higher rates in this age group compared to younger populations. This study examines the prevalence and types of unintentional in-home injuries in older adults and identifies the risk factors associated with falls and cuts/collisions. Materials and Methods: A cross-sectional study was conducted on 309 older adults (aged ≥ 65 years) recruited from eight senior welfare centers in South Korea. Results: The most frequent cause of injury was falls (28.7%), followed by cuts/collisions (27.0%), burns/fire (11.4%), and other injuries (8.1%). In the model adjusted for age and sex, risk factors for falls included a history of outdoor falls or indoor cuts/collisions, dizziness, and the use of two or more medications. Risk factors for cut/collision injuries included a history of indoor burns or falls, numbness in hands and feet, and visual impairment. Conclusions: To effectively prevent home injuries among older adults, it is crucial to focus not only on falls but also on frequent minor injuries caused by cuts and collisions. Full article

This study analyses the dynamic impact between winter wheat grains (‘Memory’ cultivar) and a flat metal surface under normal collisions. Four moisture levels (7%, 10%, 13% and 16%) and impact velocities from 1.0 to 4.5 m·s⁻¹ were chosen to reflect conditions in agricultural machinery. A custom test rig—comprising a transparent drop guide, a high-sensitivity piezoelectric force sensor and a high-speed camera—recorded grain velocity by vision techniques and contact force at 1 MHz. Force–time curves were examined to evaluate restitution velocity, the coefficient of restitution (CoR) and the effect of moisture on elastic–plastic deformation. CoR decreased non-linearly as impact velocity rose from 1.0 to 5.0 m·s⁻¹, and moisture content increased from 7% to 16%, falling from ≈ 0.60 to 0.40–0.50. Grains with higher moisture struck at higher velocities showed greater plastic deformation, longer contact times and intensified energy dissipation, making them more susceptible to internal damage. The data provide validated reference values for discrete element method (DEM) calibration and will assist engineers in designing grain-handling equipment that minimises mechanical damage during harvesting, conveying and processing. Full article

Side impacts tend to produce more severe injuries than frontal collisions, particularly for vulnerable occupants such as children. Despite this, there is a limited number of studies and developments focused on side impact protection systems, and existing airbag evaluations often rely on destructive and high-cost test methods. This study introduces a novel, cost-effective, and nondestructive experimental testbed designed to evaluate curtain airbags for vehicles in segments B, C, D, and E. The main objective is to develop an adjustable mechanical structure that replicates the side frame geometry of multiple vehicles, allowing the mounting and evaluation of various curtain airbags under realistic conditions. The prototype, capable of withstanding deployment forces of up to 7000 N, was tested with a 3-year-old child dummy, recording a peak head acceleration of 136.17 g, corresponding to AIS level 2. Deployment speeds reached 7.77 m/s, with inflation times between 29 and 36 ms—values that fall within the range reported in previous experimental and numerical studies. The testbed demonstrated consistency in its performance metrics and offers a valuable tool for enhancing child occupant safety in side impacts. Furthermore, it provides a measurable Head Injury Criterion (HIC) range that can be used to interpret injury severity in child occupants. This work contributes significantly to the development of flexible and safe testing methodologies for side airbag systems, reducing the reliance on full-scale crash testing. Full article

Energy absorption capacity (EAC) is a parameter that expresses how much energy materials can store or dissipate under an external load or impact. EAC plays a critical role in understanding soil deformations and dynamic stability under impact loads (e.g., falling masses, projectile penetration, blast impacts, or vehicle collisions). Impact loads are sudden and high-accelerated forces that cause soils to deform rapidly and absorb energy differently. Understanding the EAC of soils under impact loads is critical for various geotechnical applications, particularly understanding soil behavior under blast loads, which is critical for military and civil structures, and the reinforcement of soils and design of protective structures that will be subjected to similar sudden impacts. This study aims to develop a novel experimental method and apparatus to evaluate the EAC of sandy soils under controlled laboratory conditions. A custom-designed test device was used to measure impact forces exerted by a metal sphere dropped from a fixed height onto soil samples with varying grain sizes (coarse, medium, and fine) and relative densities (40%, 70%, and 90%) under different moisture conditions (dry, optimum, and wet). The results showed that fine-grained sands exhibited the highest EAC, with absorbed energy values reaching 23.15 J, while coarse-grained sands under dense and saturated conditions exhibited the lowest capacity (22.05 J). An increase in moisture content from dry water content to optimum water content resulted in a moderate increase in energy absorption followed by a slight decrease under saturated conditions. Similarly, higher relative density marginally reduced energy absorption, reflecting reduced soil deformation at higher densities. The study introduces a potentially standardizable testing procedure for assessing soil impact response, providing valuable insights for geotechnical engineering applications, including soil stabilization, pavement design, and impact-resistant infrastructure. Full article

To address the problems of corn harvesting in the Yellow Huaihai region with high moisture content, such as grain damage and high failure rate, a wider and taller ripple block threshing element was designed by combining the threshing principles of different threshing elements and analyzing the effects of the overall layout and parameters of the element on the threshing process. The threshing element can improve the collision attitude between the corn and the element and prioritize part of the corn kernels falling off during the collision, which makes the subsequent threshing smoother and realizes a low crushing rate of corn in the process of corn detachment. The different stages of the corn-threshing process were analyzed, a threshing simulation test was carried out, and the threshing force of the intact corn on the top side was measured to be 42.86 N; the closer the kernel was to the position of the dislodged kernel, the more the dislodging force was gradually reduced, with a minimum of 2.09 N, which verified that it was difficult to dislodge the kernel when the ear was intact and that the difficulty of dislodging the kernel around the kernel decreased as the corn was dislodged. Full article

Rockfalls pose significant threats to infrastructure, transportation routes, and human safety in mountainous regions, making them a critical concern in natural hazard and risk management. Accurate prediction of rockfall behavior is essential for designing effective mitigation strategies. The normal coefficient of restitution (R_n) is a key kinematic parameter for modeling falling rock dynamics, specifically quantifying the energy retained after collision between a rock and a slope surface. While this parameter is not directly used in prevention design, it is crucial for predicting the movement and trajectory of falling rocks and can indirectly support the development of more effective hazard mitigation strategies. However, R_n is influenced by multiple factors, including slope angle, surface material, falling rock shape, and initial velocity. The interactions among these factors make a precise prediction of R_n particularly challenging. Existing theoretical and empirical formulas typically consider individual factors in isolation, often neglecting their interactions, which leads to significant discrepancies in the results. To address this gap, we conducted a series of laboratory physical model tests to investigate the interactions among highly sensitive controlling factors and improve the accuracy of R_n prediction. A self-designed release apparatus, coupled with a high-speed recording and analysis system, was used to capture full kinematic data during rockfall collisions on slopes. This study not only examined how the main controlling factors and their interactions affect R_n but also developed a multi-factor interaction regression model, which was verified using on-site test data. The results show that the effect of the main controlling factors decreases in the following order: falling rock shape, slope surface material, initial velocity, and slope angle. Considering that falling rock shape and slope surface material cannot be quantitatively evaluated, the shape factor (η) and material factor (A_slope) are proposed to represent two controlling factors, respectively. Specifically, increases in η, A_slope, initial velocity, and slope angle are negatively correlated with R_n. Highly significant interactions were observed among falling rock shape–slope surface material, falling rock shape–initial velocity, falling rock shape–slope angle, slope surface material–initial velocity, and falling rock shape–slope surface material–initial velocity. These interactions mitigate the R_n reduction, resulting in a weaker effect than the stacking effect of the individual factors. The phenomenon is primarily attributed to the fact that high-level η, A_slope, initial velocity, and slope angle diminish the effect of intersecting factors. Finally, a comparison of the multi-factor interaction model with on-site tests and empirical formulas revealed the accuracy of the proposed model. Full article

This paper presents a complete system for autonomous navigation in GPS-denied environments using a minimal sensor suite that operates onboard a robotic vehicle. Our system utilizes a single camera and, given a target destination without prior knowledge of the environment, replans in real time to generate a collision-free trajectory that avoids static and dynamic obstacles. To achieve this, we introduce, for the first time, a local Euclidean Signed Distance Field (ESDF) map with variable size and resolution, which scales as a function of the vehicle’s velocity. The map is updated at a high rate, requiring minimal computational power. Additionally, a short-term vicinity-based memory is maintained for previously observed areas to facilitate smooth trajectory generation, addressing the limited field-of-view provided by the RGB-D camera. System validation is carried out by deploying our algorithm on a differential drive vehicle in both simulation and real-world experiments involving static and dynamic obstacles. We benchmark our robotic system against state-of-the-art autonomous navigation frameworks, successfully navigating to designated target locations while avoiding obstacles in both static and dynamic scenarios, all without introducing additional computational overhead. Our approach consistently achieves the target goals even in complex settings where current state-of-the-art methods may fall short. Full article

The seeds of Cyperus esculentus L. exhibit an uneven surface and irregular shape, which adversely affect precision seeding. Pre-sowing seed soaking treatment not only improves seeding performance, but also enhances the germination capability of C. esculentus seeds. However, the intrinsic parameters of the seeds undergo significant changes after soaking in terms of their physical properties, such as volume, weight, and density. These changes directly influence the fluidity and positioning accuracy of the seeds during the seeding process. Additionally, contact parameters, such as the coefficient of friction and the contact area between the seeds and the seeding apparatus, are altered by soaking. These parameters are crucial for designing efficient seeding devices. Therefore, it is necessary to measure the intrinsic parameters of soaked C. esculentus seeds and their contact parameters with the seeding apparatus to provide parameter support for the precision seeding analysis of pre-soaked C. esculentus. This study focuses on the calibration and experimental investigation of discrete element parameters for soaked C. esculentus seeds. Free-fall collision tests, static friction tests, and rolling friction tests were conducted to calibrate the contact parameters between soaked C. esculentus seeds and between the seeds and steel materials. Using Design-Expert, Plackett–Burman tests, steepest ascent tests, and Box–Behnken response surface tests were designed to obtain the optimal parameter combination for the C. esculentus contact model. The optimal parameters were validated through angle of repose simulation tests and physical experiments. The results indicate that the rolling friction coefficient (F) between seeds, the static friction coefficient (E) between seeds, and the rolling friction coefficient (J) between seeds and steel plates significantly affect the angle of repose. The optimal combination of discrete element parameters is as follows: the static friction coefficient (E) between seeds is 0.675, the rolling friction coefficient (F) between seeds is 0.421, and the rolling friction coefficient (J) between seeds and steel plates is 0.506. Using the calibrated parameters for simulation, the average angle of repose was 32.31°, with a relative error of 1.1% compared to the physical experiments. Full article

The safety of small drones in collision with humans has become a key focus in engineering and research fields. This study presents a vertical drop test platform for collision tests involving three representative drones (Air, Mavic 2, and M200) impacting the head of a Hybrid III dummy from different heights and orientations. The deformation and damage of the drones during various collision scenarios, as well as the dynamic responses of the dummy head and neck, are analyzed. The head injury criterion (HIC), together with 3 ms cumulative acceleration (head acc 3 ms), are used to evaluate head injury, while the shear force, axial force, as well as bending moment are applied to evaluate neck injury. The effects of drone type, drop height, and drone collision position on dummy head and neck injury risk are comprehensively analyzed, as well as the quantitative relations between the head and neck injury metrics, and the drop height for the three typical drones are derived. Via the acquired equations, the head and neck injury risks for the three typical drones involved in this study and other similar drones falling from distinct heights shall be predicted. This study proposes a novel method focusing on classifying the safety grades of drone collision with dummy. The safety grades for these three typical drones are categorized via the drop height. The findings further provide crucial data and analytical methods for establishing drone safety standards. Full article

Reciprocating liquid hydrogen pumps are essential equipment for hydrogen refueling stations with liquid hydrogen stored. The valves play a crucial role in facilitating unidirectional flow and the pressurization of liquid hydrogen within the pump. This paper establishes a comprehensive numerical model to simulate the whole working cycle of a reciprocating liquid hydrogen pump. The influence of valve parameters and pump operating conditions on the motion characteristics of valves, including lift, closing lag angle, and impact velocity, is investigated. The results indicate that with the maximum lift of the suction valve at 10 mm and the discharge valve at 5 mm, the closing lag angle is minimal, and the impact velocity of the valve falls within an acceptable range. The optimal rotation speed range is between 200 and 300 rpm, within which both the closing lag angle and impact velocity of valves are minimized. Excessive maximum lift and low rotational speed lead to significant oscillations and high impact velocity in valve movement with the effects being more pronounced in the suction valve. The effects of the subcooling degree of inflow liquid hydrogen on the valve motion are further analyzed. The findings suggest that the subcooling degree of inflow liquid hydrogen helps inhibit the vaporization in the pump operation and ensures the valves work correctly. This work would contribute to pump optimization and valve collision failure analysis in reciprocating liquid hydrogen pumps. Full article

For multi-obstacle complex scenarios, the traditional artificial potential field method suffers from the defects of potential field imbalance, its capability to easily fall into the local minima, and encounter unreachable targets in complex navigation environments. Therefore, this paper proposes a three-dimensional adaptive potential field algorithm (SAPF) based on multi-agent reinforcement learning. First, in this paper, the gravitational function in the artificial potential field (APF) is modified to weaken the gravitational effect on the UAV in the region far away from the target point in order to reduce the risk of collision between the UAV and the obstacles during the moving process. Second, in the region close to the target point, this paper improves the artificial potential field function to ensure that the UAV can reach the target point smoothly and realize path convergence by considering the relative distance between the UAV’s current position and the target point. Finally, for the characteristics of UAV trajectory planning, a 3D state space is designed based on the 3D coordinates of the UAV, the distance between the UAV and the nearest obstacle, and the distance between the UAV and the target point; an action space is designed based on the displacement increment of the UAV in the three coordinate axes; and the specific formulas for collision penalties and path optimization rewards are re-designed, which effectively avoids the UAV from entering the local minimal points. The experimental results show that the artificial potential field method designed with reinforcement learning can plan shorter paths and exhibit better planning results. In addition, the method is more adaptable in complex scenes and has better anti-interference. Full article

This paper proposes a new strategy for a collision avoidance system leveraging time-to-collision (TTC) metrics for handling cut-in scenarios, which are particularly challenging for autonomous vehicles (AVs). By integrating deep learning with TTC calculations, the system predicts potential collisions and determines appropriate evasive actions compared to traditional TTC-based approaches. The methodology is validated through extensive simulations, demonstrating a significant improvement in collision avoidance performance compared to traditional TTC-based approaches. By integrating deep learning models with TTC calculations, the system predicts potential collisions and determines appropriate evasive actions. The use of the Gaussian model to contributes to time-to-collision (TTC) analysis by providing a probabilistic framework to quantify collision risk under uncertainty. It calculates the likelihood that TTC will fall below a critical threshold (TTC_crit), indicating a potential collision. By modeling input variations—such as sensor inaccuracies, fluctuating vehicle velocity, and unpredictable driving behavior—as a Gaussian distribution, the system can handle real-world uncertainties more effectively. This enables continuous, real-time risk prediction, allowing for dynamic and adaptive collision avoidance decisions. The Gaussian approach enhances the robustness of TTC-based systems by improving their ability to predict and prevent collisions in uncertain driving conditions. Full article