Agent-Based Pathfinding Method For Indoor Fire Emergency Evacuation,
2026
School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, China
Agent-Based Pathfinding Method For Indoor Fire Emergency Evacuation, Ao Tian, Jianqin Zhang, Zheng Wen, Chaonan Hu, Hong Zhao, Bo Shen
Journal of System Simulation
Abstract: To improve emergency evacuation efficiency and reduce casualties in dynamic fire scenarios, a real-time path re-planning method based on agents and dynamic A* algorithm framework is proposed. The behavior and actions of the agent is modeled. A reward function is designed, and an agent-based evacuation framework is constructed. Based on fire simulation data, a dynamic cost network involving parameters such as thermal radiation, smoke visibility, and CO concentration is constructed to achieve spatiotemporally continuous modeling of fire environments. By optimizing the composite cost function through dynamic weight allocation, combined with an improved heuristic function and dynamic search mechanism, local …
A Semantic Knowledge-Enhanced Assessment Method For Spectrum Effectiveness Of Low Earth Orbit Constellations,
2026
Joint Laboratory for Space Information Network Frequency and Orbit Technology and Applications, China Satellite Network System Research Institute Co., Ltd, Beijing 100000, China
A Semantic Knowledge-Enhanced Assessment Method For Spectrum Effectiveness Of Low Earth Orbit Constellations, Yiqing Liu, Qiuyang Zhang, Chunyu Liu, Yao Xue, Zhiwei Wei, Yan Feng
Journal of System Simulation
Abstract: In order to scientifically assess the spectrum effectiveness of low earth orbit constellations, the problems of insufficient adaptability of the traditional assessment framework and inaccurate estimation of KPIs under sparse data conditions were solved, a semantic knowledge-enhanced assessment method for spectrum effectiveness of low earth orbit constellations was proposed. A comprehensive multi-level, all band, and multi-dimensional spectrum effectiveness assessment framework covering link level, system level, geographical level, and service application level was constructed. A KPI intelligent prediction agent model integrating semantic knowledge and machine learning was proposed to quantify text-like design parameters using SentenceTransformer, so as to rapidly …
Simulation Method For Multi-Crew Construction Processes Based On Large Language Model-Powered Agent,
2026
College of Civil Engineering, Tongji University, Shanghai 200092, China
Simulation Method For Multi-Crew Construction Processes Based On Large Language Model-Powered Agent, Yifan Wang, Bin Yang, Congjun Wang
Journal of System Simulation
Abstract: Traditional construction simulation methods typically rely on predefined rules or static scheduling mechanisms, making it difficult to simulate interactive decision-making under complex constraints by dynamically adapting multi-crew construction scenarios. As a result, workforce idleness caused by process dependencies and spatial occupation fails to be solved. A simulation method for multicrew construction processes based on a LLM-powered agent was proposed. The distributed crew agents endowed with construction scenario understanding and reasoning capabilities were constructed, as well as a centralized project manager agent. A “single-manager and multiple-crew” decision-making mechanism for multi-agent interaction in construction was designed. Autonomous decision-making and coordination mechanism …
3d Object Tracking Registration Based On Improved Rbot Method,
2026
College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
3d Object Tracking Registration Based On Improved Rbot Method, Jiarui Zhou, Haihua Cui, Pengcheng Li, Shihao Gu, Huipu Hao, Xifu Zhao, Anan Zhao, Tao Jiang
Journal of System Simulation
Abstract: To address the limitations of region-based object tracking (RBOT) in handling isotropic objects and scenarios with similar foreground-background colors, an improved method integrating edge features is proposed. The approach employs edge detection to extract object contours and designs a region segmentation strategy incorporated into an energy function framework to optimize internal line and edge consistency, thereby enhancing adaptability in dynamic environments and improving pose estimation accuracy. Validation through augmented reality assembly experiments on an aero-engine demonstrates that the proposed method effectively reduces rotational and translational errors, achieving initialization deviations of less than 1.5° and 0.5%, respectively. For static …
3d Reconstruction For Stadium Cad Drawings Based On Graphic Element Arrangement Pattern Analysis,
2026
School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China
3d Reconstruction For Stadium Cad Drawings Based On Graphic Element Arrangement Pattern Analysis, Shang Ma, Mengyu Zhang, Lan Zhang, Gang Yang
Journal of System Simulation
Abstract: To address the issue of the time-consuming and labor-intensive manual conversion of two-dimensional CAD design drawings of buildings into three-dimensional models, and leveraging the characteristic that stadiums contain a large number of repetitively and regularly arranged objects, this study proposes a similar graphical element detection algorithm. This algorithm detects similarities between graphical elements by constructing their bounding boxes and calculating the L2-Norm distance, identifying all graphical elements of the same type within the CAD drawing. Furthermore, a transformation sequence detection algorithm is proposed. Based on the geometric transformation relationships between graphical elements, a geometric transformation space is defined. By …
Visual Relocalization Method Combining Region Classification And Local Feature Enhancement,
2026
College of Computer Science, Sichuan University, Chengdu 610065, China
Visual Relocalization Method Combining Region Classification And Local Feature Enhancement, Yining Wang, Yanli Liu, Guanyu Xing
Journal of System Simulation
Abstract: Visual relocalization tasks have important application value in fields such as digital twin and augmented reality. The current mainstream methods still face challenges such as mismatch between coordinate regression scale and receptive field and insufficient attention to local information. A visual relocalization method that combines region classification and local feature enhancement is proposed. The coordinate regression problem in large space is transformed into a multi-region classification problem and a coordinate regression problem inside a small scene, which significantly reduces the uncertainty of coordinate regression and makes the network globally have a large receptive field. A conditioning layer using deep …
Diffusion Model For Human Motion Generation With Fine-Grained Text And Spatial Control Signals,
2026
Beijing Information Science & Technology University, Beijing 102206, China
Diffusion Model For Human Motion Generation With Fine-Grained Text And Spatial Control Signals, Binze Jiang, Wenfeng Song, Xia Hou, Shuai Li
Journal of System Simulation
Abstract: To improve the accuracy, controllability, and realism of text-driven human motion generation, a novel method is proposed that integrates fine-grained textual semantics with spatial control signals. Within the diffusion model framework, both global text tokens and body-part-level local tokens are introduced. These are encoded using CLIP to obtain corresponding features, which are then fed into the motion diffusion model to enable fine control over different body parts. Spatial guidance is used to dynamically adjust joint positions during the diffusion denoising process, ensuring that the generated motion adheres to spatial constraints. Realism guidance is incorporated to enhance the naturalness and …
Virtual Reality Rehabilitation Training System Based On Multimodal Brain-Computer Interface,
2026
School of Software, Shandong University, Jinan 250101, China; Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong
University, Jinan 250101, China
Virtual Reality Rehabilitation Training System Based On Multimodal Brain-Computer Interface, Jing Qu, Kaining Fang, Shantong Zhu, Lingguo Bu
Journal of System Simulation
Abstract: The aging population has led to an increasing demand for rehabilitation for cognitive and motor functions. In response to the lack of interest in traditional rehabilitation and the absence of objective physiological assessment in existing virtual reality (VR) rehabilitation systems, a VR rehabilitation training system based on multimodal brain computer interface is developed by integrating VR interaction, near-infrared brain functional imaging, and motion capture technology. An immersive cognitive-motor integrated training environment was constructed to guide users in completing upper limb tasks. By recruiting subjects and synchronously collecting brain network data and Kinect upper limb motion parameters, multimodal assessment …
Defect Detection Method Based On Hierarchical Microscopic Feature Modeling And Simulation,
2026
School of Computer Science, Zhejiang University of Science and Technology, Hangzhou 310023, China
Defect Detection Method Based On Hierarchical Microscopic Feature Modeling And Simulation, Jing Zou, Xu Tan, Junji Mao, Haidong Gao, Jianrong Tan
Journal of System Simulation
Abstract: To address the challenge of detecting small and low-contrast defects in complex microscopic images, a defect method technology based on hierarchical microscopic feature modeling and simulation is proposed. The method is built on the RT-DETR (real-time detection transformer)framework to construct the HM-RTDETR (hierarchical microscopic RT-DETR) model. It maintains the global feature modeling ability of the Transformer and introduces a Dense O2O-Mosaic, a high-density one-to-one Mosaic augmentation strategy, to increase supervision density for small samples. A depthwise separable convolution (DWConv) module is used to enhance local detail extraction in microscopic textures, and a learnable PatchExpand module is applied …
Material Reconstruction From Single Image Combining Neural Networks With Singular Value Decomposition,
2026
National Engineering Laboratory for Modeling and Emulation in E-Government, Harbin Engineering University, Harbin 150001, China
Material Reconstruction From Single Image Combining Neural Networks With Singular Value Decomposition, Zhiqiang Li, Xukun Shen, Yong Hu, Xueyang Zhou, Yifan Chen
Journal of System Simulation
Abstract: The tabulated BRDFs (bidirectional reflectance distribution function) can realistically reproduce the surface appearance of objects. However, due to their high-dimensional characteristics and the fact that a single planar image contains limited reflectance information and small differences, methods for estimating tabulated BRDFs typically require complex equipment or the capture of multiple images. To address this issue, a method is proposed for reconstructing material properties from a single image by combining neural networks with singular value decomposition. The singular value decomposition is introduced to compress the material into a lower-dimensional space. The task of solving the tabulated BRDFs is simplified to …
Full-Body Co-Speech Gesture Generation Based On Spatial-Temporal Enhanced Generation Model,
2026
Beijing Information Science & Technology University, Beijing 102206, China
Full-Body Co-Speech Gesture Generation Based On Spatial-Temporal Enhanced Generation Model, Shuozhe Zhang, Wenfeng Song, Xia Hou, Shuai Li
Journal of System Simulation
Abstract: Full-body co-speech gesture generation significantly enhances the interactivity of virtual digital humans, requiring generated gestures to not only align accurately with speech but also demonstrate realistic full-body dynamics. To address limitations of existing methods—Transformer-based approaches often overlook temporal features of action sequences, while diffusion model-based ones inadequately capture spatial correlations between body parts, a full-body action generation method integrating diffusion models, Mamba, and attention mechanisms is proposed. We introduce the spatial self-attention-temporal state space model (STMamba Layer) as the core of denoising network to extract
inter-part spatial features and intra-part temporal features, thus enhancing action quality and diversity. …
Vrbt: Vr Badminton Training With Multitask Injury Alerts Based On Lightweight 3d Skeletal Reconstruction,
2026
School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China
Vrbt: Vr Badminton Training With Multitask Injury Alerts Based On Lightweight 3d Skeletal Reconstruction, Yuning Zhu, Meng Yang, Tianyue Chen, Weiliang Meng
Journal of System Simulation
Abstract: To overcome the limitations of traditional badminton training, a VR training method that integrates multiple models for collaborative simulation is proposed. A "perception-decision- interaction" framework is developed within Unity, featuring diverse training modules powered by a physics engine for realistic trajectory simulation. The system employs a lightweight MHFormer for 3D pose estimation and a novel multi-task model (enhanced injury prediction system, EIPS) that combines random forest and XGBoost to jointly assess injury risk. This approach offers a solution for balancing real-time performance with accuracy in skeleton reconstruction and enables personalized training through dynamic risk assessment.
Military Metaverse: Conceptual Connotation, Construction And Application Framework, Key Issues,
2026
Army Arms University of PLA, Beijing 100072, China; PLA 32302 Troops
Military Metaverse: Conceptual Connotation, Construction And Application Framework, Key Issues, Dayong Liu, Zhiming Dong, Jiancheng Gao
Journal of System Simulation
Abstract: Based on the analysis of the concept of the metaverse, the military metaverse concept model is established and compared with virtual-real fusion systems such as the digital twin battlefield, analyzing its core characteristics and construction significance. To accelerate the construction of the military metaverse, an overall logical architecture for the construction and application of the military metaverse is designed, the concept of military metaverse primitives is proposed, and the technical architecture is designed. The main application directions of the military metaverse are analyzed, and the construction stage division and overall thinking are provided. The key issues in construction and …
Virtual-Real Fusion Simulation Technology And Application Research For Industrial Control Systems Cybersecurity Of Process Manufacturing,
2026
College of Safety and Ocean Engineering, China University of Petroleum, Beijing 102249, China; Key Laboratory of Oil and Gas Production Safety and Emergency Technology, Ministry of Emergency Management, Beijing 102249, China
Virtual-Real Fusion Simulation Technology And Application Research For Industrial Control Systems Cybersecurity Of Process Manufacturing, Xinwei Wang, Jinjiang Wang, Zheng Wang, Laibin Zhang
Journal of System Simulation
Abstract: Aiming at the problem that the industrial control system in the process manufacturing industry lacks an effective attack and defense drill platform when facing network attacks, it is difficult to truly simulate the attack situation, verify the protective measures, and accurately evaluate the impact of attacks on the physical system, an industrial control cybersecurity simulation technology based on virtual-real fusion is proposed to build an efficient attack and defense drill range. The industrial control cybersecurity simulation architecture based on virtual-real fusion is designed, and the consistency analysis of virtual-real fusion data is carried out. At the same time, …
Spatio-Temporal Swin Transformer-Based Flow-Solid Coupling Interaction Sequence Image Prediction Network,
2026
School of Information and Software Engineering, East China Jiaotong University, Nanchang 330013, China
Spatio-Temporal Swin Transformer-Based Flow-Solid Coupling Interaction Sequence Image Prediction Network, Changjun Zou, Zhiyu Ge, Chenxi Zhong
Journal of System Simulation
Abstract: To address limitations in modeling long-term dependencies and multi-scale features in fluidstructure interaction scenarios, a spatiotemporal deep learning model (SwinLSTM) integrating ConvLSTM and Swin Transformer is proposed. The model employs a gated spatiotemporal attention mechanism that dynamically embeds Swin Transformer's window-based multi-head self-attention into ConvLSTM's output gate, enabling adaptive temporal-spatial feature coupling, and designs a multi-level ConvLSTM framework to hierarchically capture complex spatiotemporal correlations. Experiments on a self-built fluid-interaction dataset show that our method achieves the highest PSNR and leading SSIM scores, with superior performance in preserving vortex details and boundary consistency. This work provides an efficient solution …
Pl-Mamba: A 3d Point Cloud Semantic Segmentation Network Based On Bimodal Fusion,
2026
North China University of Technology, Beijing 100044, China
Pl-Mamba: A 3d Point Cloud Semantic Segmentation Network Based On Bimodal Fusion, He Zhu, Feng Zhou, Mengxiao Zhu, Ju Dai
Journal of System Simulation
Abstract: To enhance the semantic discrimination capability in point cloud semantic segmentation, a 3D point cloud semantic segmentation network named PL-Mamba is proposed, which is centered on the fusion of point cloud (P) and language (L) dual modalities. This method takes PointMamba as the backbone network, leveraging its excellent long-sequence modeling and global perception capabilities. It introduces a language prompt mechanism and uses a pretrained language model BERT to encode the context of category labels, obtaining semantically rich text features. The text information serves as a language guided token and is deeply integrated with point cloud features through cross modal …
Dehpr: A Diffusion-Based End-To-End Hand Pose Reconstruction Network,
2026
Modern Industry School of Virtual Reality (VR), Jiangxi University of Finance and Economics, Nanchang 330032, China; Jiangxi Tourism and Commerce Vocational College, Nanchang 330100, China
Dehpr: A Diffusion-Based End-To-End Hand Pose Reconstruction Network, Guoqiong Liao, Longjie Huang, Qingxin Li, Jiajun Zhang, Kefan Chen
Journal of System Simulation
Abstract: Traditional methods such as convolutional neural networks (CNNs) and Transformers suffer from strong dependence on large-scale annotated data and limited generalization capability when dealing with hand pose reconstruction in complex scenarios. To address these issues, a diffusion-based end-to-end hand pose reconstruction network (DEHPR) is proposed. This method employs a diffusion model to directly generate and refine 3D predictions, thereby reducing spatial uncertainties inherent in 2D-to-3D modeling paradigms. By incorporating an end-to-end framework that reprojects multiple 3D candidate predictions to select optimal joint positions, the approach ultimately produces accurate hand pose estimations. Comprehensive evaluations conducted on HO3D V2, DexYCB, …
Cross-Domain Crowd Counting Model Based On Frequency Domain Enhancement,
2026
School of Intelligence Science and Technology, Beijing University of Civil Engineering and Architecture, Beijing 102616, China; Beijing Key
Laboratory of Super Intelligent Technology for Urban Architecture, Beijing University of Civil Engineering and Architecture, Beijing 102616, China
Cross-Domain Crowd Counting Model Based On Frequency Domain Enhancement, De Zhang, Zishan Liang, Ningning Liu
Journal of System Simulation
Abstract: Crowd counting takes video surveillance data as input and can be applied to the construction of city digital twin platforms, virtual city modeling and smart city management, etc. However, when there are data domain differences between the application scenario and training scenario, counting performance often significantly decreases. A cross-domain crowd counting model based on frequency domain enhancement is proposed. To alleviate the distribution differences between domains, a frequency domain feature enhancement module and a domain invariant frequency domain adapter module are constructed: the former uses discrete cosine transform to extract key statistical features to enhance spatial representation ability, while …
Research On Real-Time Animatable Human Avatar Generation Via 3d Gaussian Splatting,
2026
School of Computing, Beihang University, Beijing 100191, China
Research On Real-Time Animatable Human Avatar Generation Via 3d Gaussian Splatting, Yuyou Zhong, Xukun Shen, Yong Hu
Journal of System Simulation
Abstract: Real-time animatable 3D human avatar generation technology hold significant application value in fields such as virtual reality and remote collaboration. To address the limitations of existing methods in detail modeling, real-time performance, and robustness under novel pose driving, an efficient human avatar generation and driving method based on 3D Gaussian splatting (3DGS) is proposed. This method integrates optimized parametric human reconstruction, tri-plane feature encoding, and dynamic offset prediction to achieve efficient modeling from monocular video input. By introducing a skeleton binding and visibility analysis strategy, while designing a multi-scale regularization loss to address the overfitting problem. Simulation experiments demonstrate …
Inverse Kinematics 3d Human Modeling Simulation Based On Multi-View Vision,
2026
College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Inverse Kinematics 3d Human Modeling Simulation Based On Multi-View Vision, Guoyu Fang, Yanze Li, Kai Chen, Xiaodong Zhao, Zizhuo Hu, Mingshi Yang, Wanqing Wu, Zichen Wang, Wenkai Guo
Journal of System Simulation
Abstract: In autonomous driving simulation and industrial virtual reality simulation, there is a high demand for accuracy and robustness in 3D human body modeling. However, current joint-based human modeling approaches suffer from issues such as continuous modeling jitter, local distortion, and poor adaptability to occlusion, which degrade model quality and limit the development of practical applications such as intelligent driving and digital factories. To address these challenges, this paper proposes a multi-view vision-based inverse kinematics 3D human modeling method using a vector quantized variational autoencoder(IK-VQ-VAE). By integrating joint training with an automatic variational gradient descent approach, the proposed method achieves …
