International Journal of Vehicle Systems Modelling and Testing (17 papers in press)

Regular Issues

• Dynamic performance analysis of suspended monorail vehicles under various operating conditions  
  by Yongzhi Jiang, Pingyi Duan, Wenjie Liu, Zixue Du, Renxiang Chen 
  Abstract: This paper presents the impact of various operating conditions on the dynamic performance of suspended monorail vehicles through simulations with focusing on vehicle speed, curve radius, gradient and crosswind. A multi-body dynamic model of a two-car train is developed by incorporating the effect of track beams under crosswind conditions using a flexible track beam model to construct a wind-vehicle-bridge coupling model. To improve computational efficiency, a parameter batch processing method is used for the numerical simulation. The results show that under curved ramp conditions, the combined effects of centrifugal and gravitational forces lead to reducing the lateral stability as compared to regular curved conditions. In crosswind conditions, increasing wind speed intensifies lateral force. However, the vehicle’s vertical stability remains excellent across all conditions due to the high vertical damping of the suspension system. This study supports the application of suspended monorail systems in mountainous regions.
  Keywords: suspended monorail vehicle; stability analysis; multi-body model; wind-vehicle-bridge coupling model; batch processing method; curve condition; crosswind condition.
  DOI: 10.1504/IJVSMT.2025.10071184
   
  
• A dynamic visual SLAM method based on ORB-SLAM3 for intelligent mobile robots  
  by Yongxun Yu, Jie Yu, Penghui Fu, Xiaolei Yan 
  Abstract: Accurately detecting and removing dynamic targets is crucial for enhancing the precision of visual simultaneous localisation and mapping (SLAM) systems in complex environments. To achieve high-precision and robust visual SLAM in dynamic settings, we propose a novel method called Dynamic-objects Semantic Visual SLAM, which integrates ORB-SLAM3 with YOLOv8. First, YOLOv8 is employed to detect and segment dynamic objects in real-time, and the feature information of these objects is seamlessly integrated into the ORB-SLAM3 front-end. Sparse optical flow tracking is subsequently utilised to track dynamic objects across frames, while enhanced multi-view geometry addresses potential incomplete object detection issues in semantic segmentation. Finally, highly dynamic objects are filtered out to generate accurate localised maps. The dataset Technische Universit
  Keywords: SLAM; YOLOV8; instance segmentation; dynamic object detection.
  DOI: 10.1504/IJVSMT.2025.10071527
   
  
• A 3D target detection algorithm for low-speed unmanned vehicles in closed parks based on redundant fusion of multi-sensor information  
  by Zhiqun Yuan, Jiayue Li, Jian Jiang, Xiujing Gao 
  Abstract: To address the issues of object segmentation and pedestrian mis-detection, this paper proposes a redundant target detection method based on multi-level Euclidean clustering and view cone point cloud fusion. First, the joint calibration of LiDAR and camera is completed. Then, the pedestrian information and point cloud fusion are used to form a pedestrian cone point cloud, in addition, the multi-level threshold Euclidean clustering algorithm and the optimal 3D bracket selection method are designed. Finally, the pedestrian 3D bounding box is obtained by solving the point cloud confidence function, and fusion matching with the LiDAR detection results is performed to output the multi-sensor fusion perception results. Real-vehicle experimental data show that this method improves the accuracy of the whole sensing module, reduces the number of missed and misdetected boxes, and achieves 94.94% detection accuracy, which is 8.68% higher than the LiDAR detection algorithm, demonstrating its effectiveness and reliability.
  Keywords: autonomous driving; closed park; multi-level Euclidean clustering; multi-sensor fusion; point cloud target detection.
  
  
• On driving style recognition methods considering multiple factors  
  by Lixin Yan, Yating Gao, Guangyang Deng, Ziyan Zhou 
  Abstract: The diversity of driving styles triggers driver differences in terms of traveling risks and energy-saving potential. To accurately assess driving styles, this study constructs seven different lane-changing scenarios by combining forced and free lane-changing. A driving style recognition model for lane-changing behavior is constructed by considering multiple factors in various scenarios. In addition, this study analyzes the correlation among different lane-changing scenarios, driving styles and safety levels and energy-saving efficiency. The results show that there are lower potential hazards and better energy-saving efficiencies are demonstrated for the right lane change as compared to the left lane change. Meanwhile, potential hazards and fuel consumption are significantly higher for drivers with aggressive driving styles than for drivers with cautious and normal driving styles. Therefore, reasonable regulation of driver’s behaviors to avoid undesirable driving operations is essential to enhance the safety level and energy use efficiency of the road transportation system.
  Keywords: road traffic; driving style; lane-changing scenarios; safe driving; energy saving; emission reduction.
  DOI: 10.1504/IJVSMT.2025.10071814
   
  
• Penetration resistance of ceramic with aluminum alloy/UHMWPE backplate  
  by Zhangxia Guo, Limao Wang, Zihao Huang, Chen Wan, Zeng Xie, Zekun Yuan, Taiyang Li 
  Abstract: At present, in the field of single-soldier protection panels, a large number of studies have been carried out on the performance of composite protective materials with different fibers and the results show that the main damage models are interlaminar delamination, fiber fracture and matrix cracking Therefore, we proposed that adding metal to the backplate to improve the ballistic impact behavior of composite materials and conducted a series studies about the ballistic impact performance of different aluminum (Al) alloy/ultra-high molecular weight polyethylene (UHMWPE) ceramic composite materials through numerical simulation and ballistic tests The results show that when the thickness of Al alloy in the composite backplate was 1 mm, the penetration resistance of ceramic composite materials could be effectively improved, and the Al alloy interlayer could effectively improve the resistance and erosion of ceramic panels to projectiles also.
  Keywords: UHMWPE; aluminum Alloy; Ballistic penetration; Finite element simulation; Single-soldier protection.
  
  
• Game theory-based lane-changing decisions in adverse weather conditions  
  by Jian Ma, Zheng Qian, Liyan Zhang, Xiaofei Hu, Keyi Cao, Qianlong Fu 
  Abstract: Adverse weather conditions significantly impact driving safety and greatly increase road accidents. Lane-changing is essential for safe and efficient vehicle operation and the factors influencing lane-changing behaviors are very complicated under adverse weather. This study presents an improved lane-changing safety distance model by introducing the fuzzy evaluation quantification value of severe weather for the decision-making of lane-changing. In addition, the Gazis-Herman-Rothery model, an anchoring effect model and the full velocity difference model are refined. Based on a non-cooperative dynamic game (NCDG) model, a joint simulation environment is developed using Python. Simulation of urban mobility is conducted to simulate experiments. The simulation results indicate that, using the improved lane-changing model and the NCDG model, vehicles in adverse weather conditions are able to select the optimal driving strategy in interactive conflict scenarios, effectively alleviating conflicts and enhancing driving efficiency and safety.
  Keywords: severe weather; NCDG; non-cooperative dynamic game; lane-changing decision; SUMO.
  DOI: 10.1504/IJVSMT.2025.10071855
   
  
• Construction of traffic accident knowledge graph based on the correlation analysis of risk factors  
  by Liyan Zhang, Keyi Cao, Jian Ma, Yuan Wen, Zheng Qian, Yuchen Zhang 
  Abstract: With an increase of vehicles, traffic accidents have also risen. This paper presents a novel approach to creating a traffic knowledge graph using a keyword extraction algorithm to analyze accident data from a specific city, focusing on identifying key terms related to the causes of accidents. The data are analyzed from four aspects: human factors, vehicles, road conditions and environmental factors, to construct the knowledge graph. The findings indicate that the improved TextRank algorithm, which incorporates word vectors and a multi-feature weighting mechanism, outperforms traditional TextRank and inverse document frequency methods in keyword extraction. The present TextRank algorithm effectively combines word-specific attributes and structural features, delivering better extraction performance.
  Keywords: traffic accidents; knowledge graph; TextRank algorithm; keyword extraction.
  DOI: 10.1504/IJVSMT.2025.10072046
   
  
• Experimental research on the threshold of traffic signs information quantity in mountainous roads  
  by Yunwei Meng, Lei Wang, Zixiao Wang, Shibao Li, Zhenyu Quan, Guangyan Qing 
  Abstract: The complexity of mountain roads requires drivers to maintain heightened attention and quick reaction times. Insufficient recognition of traffic signs is a major cause of traffic risks. To enhance driving safety on mountain roads, a simulated experiment combining information theory and psychological tests was conducted with 45 selected drivers. Data on drivers response time (RT) and accuracy (ACC) under different traffic sign information densities (TSID) were collected, and a mathematical fitting model was established. The study found that when TSID 13.64 bits/m2, the average RT 1300 ms. When a single traffic sign displays up to 6 information items and TSID 15.5 bits/m2, ACC 80%. When multiple traffic signs are used together, the total number of information items displayed should not exceed 7. These findings provide theoretical guidance for the placement of traffic signs on mountain roads.
  Keywords: traffic sign; mountainous roads; traffic sign information quantity; cognitive load.
  DOI: 10.1504/IJVSMT.2025.10072047
   
  
• Research on injury characteristics of dummies based on secondary collision between occupant and seat in metro trains  
  by Jinle Wang, Bing Yang, Honglei Tian, Wenbin Wang, Xu Sang 
  Abstract: Collision accidents, such as frontal collisions in metro trains, can cause serious occupant injuries. This study investigates the injury characteristics of dummies based on secondary collision between occupant and seat in metro trains. A full-scale finite element model of a frontal collision was developed. Using a simplified dummy-carriage coupling model, we compared acceleration boundary conditions and explored the protective effects of three seat structures, as well as the influence of occupant numbers and seating angles on secondary collisions. Results showed that enclosed seats offered the best protection. Occupants sitting at larger angles experienced more severe injuries, with those closest to the seat side panel suffering the most. Injury severity increased with the number of occupants. The research results are helpful for understanding the mechanisms of secondary collision injuries in metro trains.
  Keywords: metro tarins; frontal collisions; secondary collisions; occupants injuries; seat structures; dummies; dummy-carriage coupling model; side panels.
  DOI: 10.1504/IJVSMT.2025.10072069
   
  
• Spinal segmentation algorithm for modelling Chinese digital human models  
  by HongJi Xiong, Cheng Chen, Yu Liu, Xiaofan Wu, Zhong Hao Bai 
  Abstract: Low-dose spinal CT images often suffer from issues such as blurred boundaries, significant noise, and poor contrast, which complicating manual segmentation. Traditional spinal image segmentation algorithms, although fast, generally lack precision and require manual intervention. Meanwhile, deep learning-based methods require extensive datasets for support, limiting their widespread applicability. To overcome these limitations, this paper introduces the 3D-TSUnet, this method first employs traditional segmentation algorithms for pre-segmentation, followed by detailed segmentation using the refined 3D-Unet network. Comparisons with manual segmentation show a 98.28% reduction in self-intersections, 95.05% decrease in highly refractive edges, 89.59% re-duction in nail-like artifacts, and 96.48% reduction in segmentation errors, with segmentation time reduced by 91.67%. These results demonstrate that the proposed network efficiently performs low-dose CT spinal segmentation, offering substantial practical value for developing Chinese human finite element models and advancing related research.
  Keywords: 3D-TSUnet; medical image segmentation; low-dose spinal CT images; supervised Learning; Chinese human finite element model.
  DOI: 10.1504/IJVSMT.2025.10072187
   
  
• Optimisation cost and carbon emission in vehicle drone collaborative delivery under dynamic traffic conditions  
  by Kai Wu, Zhijiang Lu, E. Bai 
  Abstract: The rising number of vehicles in urban areas has caused severe congestion in logistics, increasing delivery and carbon costs. To address this, the Vehicle and Drone Co-Delivery Model (VDCDM) has become a research focus, yet existing studies lack a strong connection to urban traffic conditions. This paper develops a multi-objective path optimization model for vehicle-drone collaborative delivery, incorporating traffic congestion to minimize carbon emissions and total delivery costs. We introduce an improved BBO algorithm (IBBO) that enhances global search capability while reducing complexity. Testing reveals stable optimization across various traffic scenarios. Our findings on the Collaborative Delivery Index (CDI) show that lower CDIs lead to more drone-served customers, increasing overall costs but decreasing emissions. This highlights the need for companies to assess their strategies and choose suitable CDIs, offering valuable insights for urban logistics and emergency transport applications.
  Keywords: traffic congestion; VDCDM; vehicle and drone co-delivery model; low carbon; BBO.
  DOI: 10.1504/IJVSMT.2025.10072191
   
  
• Evaluating two control cases of pneumatic suspensions on the working performance of heavy vehicles  
  by Li Zhang, Hui Zan 
  Abstract: To evaluate the performance of control pneumatic suspensions using the air valve control and damping control on the working performance of heavy vehicles (HV), an HV model is established to simulate dynamic equations under excitations of ISO-B to ISO-E. Optimal controls of the fuzzy logic optimized by the genetic algorithm are applied to control pneumatic suspensions. HV’s working performance is evaluated through two indexes of the comfortable level and road friendliness. Results show that both control cases of the air valve and damping value greatly ameliorate HV’s working performance in comparison with passive pneumatic suspensions. However, the road friendliness with air valve control is higher than the road friendliness with damping control. This means that HV’s working performance using air valve control is better than damping control. Therefore, the air valve control of pneumatic suspensions should be applied to ameliorate HV’s working performance further.
  Keywords: heavy vehicle model; pneumatic suspensions; optimal control methods; comfortable level; coefficient of dynamics load.
  DOI: 10.1504/IJVSMT.2025.10072320
   
  
• Semantic context-induced fast fusion network based driver attention prediction in complex scenarios  
  by Jinglei Ren, Hailong Zhang, Yongjuan Zhao, Cong Lan 
  Abstract: Clarifying driving intention through the utilisation of the visual selective attention mechanism remains a pivotal research question in a domain of advanced driver assistance systems (ADAS) and human-machine collaborative autonomous driving technology. This paper proposes a semantic context-induced fast fusion network (SCFF-Net) segmenting the red green blue (RGB) video frames into images with different semantic regions, and develops an attention strategy to fuse the semantic context features of semantic images with the features of RGB frames to explore the complementarity among different features. A mixed model of self-attention and convolution integrated with the self-attention mechanism is further introduced by combining the global perception capability and the local feature extraction capability. Experimental results on the driver attention in driving accident scenarios dataset show that the proposed SCFF-Net can effectively improve the prediction accuracy of driver attention and the computing efficiency. It can also reduce redundant calculations.
  Keywords: driver attention prediction; AC-mix; complex driving scenarios; computer vision; deep learning.
  DOI: 10.1504/IJVSMT.2025.10069760
   
  
• On pantograph-catenary coupling vibration based on neural network finite element strategy  
  by Zhixin Ou 
  Abstract: When the traditional high-speed train pantograph-catenary system is used for the coupling parameter calculation, there exist problems of uneven mechanical vibration force, changes in parameters and model structures. Based on analysing the finite element modelling process of the pantograph-catenary system, the neural network finite element cutting method is used to optimise the overall structure of the pantograph-catenary, and a dynamic coupling equation is developed to stabilise the data. By comparing finite element control strategy based on neural network with the least squares algorithm based on model identification, neural network control strategies have better parameter tuning and fitting characteristics. The vibration frequency and error parameters of the pantograph-catenary model can be automatically adjusted to match with the set values. The experiments show that the vibration frequency of the pantograph is decreased by 5%; the overall stability is improved by 8% and the parameter coupling accuracy is increased by 30%.
  Keywords: pantograph-catenary coupling system; vibration model; BP neural network; finite element strategy.
  DOI: 10.1504/IJVSMT.2025.10071367
   
  
• On dynamic path planning based on the DBSCAN-AGA algorithm  
  by Jiangyong Mi, Yongjuan Zhao, Hailong Zhang, Pengfei Zhang, Wenzheng Cheng, Haidi Wang, Chaozhe Guo 
  Abstract: With the advancement of intelligent vehicles, unmanned driving technology has achieved significant progress, particularly in low-speed park settings. However, challenges arise in the park connections due to the dynamic variations of passengers and the complexities of road conditions, making it difficult to implement dynamic path planning for traffic demand distributions. This paper introduces a path planning algorithm based on the adaptive genetic algorithm (AGA) for connecting vehicles on variable routes. This approach involves constructing an origin-destination (OD) matrix based on passengers' origin and destination points, and incorporates the density-based spatial clustering of applications with noise (DBSCAN) to reassign traffic demand by adjusting routing of connecting vehicles according to traffic demand and road network traffic conditions. The obtained results validate the effectiveness of the proposed method, demonstrating that the DBSCAN-AGA algorithm exhibits strong robustness and reliability in dynamic environment path planning.
  Keywords: intelligent vehicles; dynamic path planning; complex road conditions; DBSCAN-AGA.
  DOI: 10.1504/IJVSMT.2025.10070326
   
  
• TWICE dataset: digital twin of test scenarios in a controlled environment  
  by Leonardo Novicki Neto, Fabio Reway, Yuri Poledna, Maikol Funk Drechsler, Christian Icking, Werner Huber, Eduardo Parente Ribeiro 
  Abstract: Ensuring autonomous vehicle safety in adverse weather remains a challenge. To address this, we developed a validation dataset using data from cameras, radar, and LiDAR, collected both on a real test track and in simulation. Our dataset supports the evaluation of object detection algorithms in conditions like rain, nighttime, and snow. Inspired by Euro European New Car Assessment Programme (Euro NCAP), it includes scenarios with cars, cyclists, trucks, and pedestrians. Data was recorded in a simulation-based hardware-in- the-loop testing framework, which utilises the same sensors (camera and radar) used in real-world test drives and features a digital twin of the proving ground. Spanning over 2 h and 280GB, this dataset aids researchers in testing and improving detection algorithms in both real and virtual environments. Available at: https://twicedataset.github.io/site/
  Keywords: autonomous driving; environment sensors; camera; radar; LiDAR; hardware-in-the-loop.
  DOI: 10.1504/IJVSMT.2025.10070327
   
  
• A PSO-based method for road rut measurement with line-structured light  
  by Yuanbo Mu, Qingzhou Mao, Guangqi Wang, Chaowen Tu, Dehui Lai 
  Abstract: Road rut depth is a vital metric for evaluating pavement quality, traditionally measured manually but now assessed using automatic laser-based devices for the efficient data collection. This technique faces challenges due to the complex and variable nature of rut profiles and road conditions, leading to inconsistencies and interference from lane edges and debris. This study presents a novel method for rapid and precise rut depth measurement by employing line-structured light technology integrated with the inertial measurement unit (IMU) and global position system (GPS) sensors. The device undergoes meticulous calibration for accurate 3D road surface data acquisition, involving both line-structured light and positioning sensor calibrations. The collected high-resolution data is then refined using particle swarm optimisation (PSO) algorithms to enhance the accuracy of rut depth estimates. Experimental results demonstrate that this method not only improves the measurement accuracy and efficiency but also shows strong adaptability, making it a reliable tool for the road quality assessment.
  Keywords: rut depth; line-structured light; 3D measurement; PSO; particle swarm optimisation.
  DOI: 10.1504/IJVSMT.2025.10070437