Weiping Fu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Weiping Fu has a total of 59 co-authors. Here are the top co-authors by number of shared publications:
Wen Wang
School of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an, 710048, China
10 shared publications- Wen Wang
Xian University of Technology, Xian, China
8 shared publications Zhiqiang Gao
School of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an, China
7 shared publicationsDenggui Wang
Xi’an University of technology, Xi’an, China
3 shared publications- Jincao Zhou
School of Mechanical and Precision Instrument Engineering, Xian University of Technology, Xian, China
3 shared publications Qingyuan Song
Xi’an University of technology, Xi’an, China
3 shared publications
Latest Publications
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (3) , 3189-3207
Human-Like Assessment Method for Potential Risks in View Occlusion Scenarios Driven by Data and Knowledge
The potential risks associated with various visual occlusion scenarios (VOS) vary greatly. For autonomous vehicles to make informed collision avoidance decisions, it is crucial to accurately assess the potential risk of each type of visual obstruction. However, this problem remains unresolved. In this paper, we simulate the data and knowledge driven cognitive mechanisms of human drivers and propose a human-like potential risk assessment method for VOS. During the perception phase, we move beyond the traditional image feature-based perception paradigm. Instead, we use natural language processing (NLP) to obtain textual semantic features of the scene as the perception result. Specifically, we utilize NLP techniques to construct a data driven VOS description model that generates textual descriptions of visible information in VOS as the perception result. In the risk assessment phase, inspired by human inductive and analogical reasoning, we develop a knowledge driven risk assessment model. Experimental results show that the proposed method can accurately assess the potential risks associated with different types of VOS, and in some cases, even identify risks up to 0.5 seconds earlier than human drivers.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (3) , 3189-3207
Human-Like Assessment Method for Potential Risks in View Occlusion Scenarios Driven by Data and Knowledge
The potential risks associated with various visual occlusion scenarios (VOS) vary greatly. For autonomous vehicles to make informed collision avoidance decisions, it is crucial to accurately assess the potential risk of each type of visual obstruction. However, this problem remains unresolved. In this paper, we simulate the data and knowledge driven cognitive mechanisms of human drivers and propose a human-like potential risk assessment method for VOS. During the perception phase, we move beyond the traditional image feature-based perception paradigm. Instead, we use natural language processing (NLP) to obtain textual semantic features of the scene as the perception result. Specifically, we utilize NLP techniques to construct a data driven VOS description model that generates textual descriptions of visible information in VOS as the perception result. In the risk assessment phase, inspired by human inductive and analogical reasoning, we develop a knowledge driven risk assessment model. Experimental results show that the proposed method can accurately assess the potential risks associated with different types of VOS, and in some cases, even identify risks up to 0.5 seconds earlier than human drivers.
- Open Access
- 3 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 100957-100969
The Construction of Knowledge Graphs in the Assembly Domain Based on Deep Learning
The operation scenario of human-robot collaboration assembly involves multiple channels to acquire assembly domain knowledge data. In order to equip collaborative robots with certain general knowledge of assembly work and logical reasoning ability, this paper proposes a Chinese-character-based names entity recognition model Bert-BiLSTM-CRF and a relational extraction model Bert-BiGRU-ATT, based on the multiple heterogeneous data in the assembly domain, to construct an assembly domain knowledge graph centered on and for human-robot collaboration. Among them, the Chinese-character-based names entity recognition model avoids the error bias caused by Chinese word segmentation in traditional methods, while the relation extraction model fully extracts the association information between entities and relations. The proposed entity recognition model and relation extraction model are validated in a real scenario of mechanical product assembly. The experimental results show that the proposed models exhibit excellent performance in the human-machine collaborative assembly domain, with overall average F1-score of 84.02% and 94.92% for entities and relations, respectively. The constructed knowledge graph of the assembly domain contains 2724 triples, and the knowledge graph is presented through a visual interactive interface.
- 3 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 100957-100969
Open AccessThe Construction of Knowledge Graphs in the Assembly Domain Based on Deep Learning
The operation scenario of human-robot collaboration assembly involves multiple channels to acquire assembly domain knowledge data. In order to equip collaborative robots with certain general knowledge of assembly work and logical reasoning ability, this paper proposes a Chinese-character-based names entity recognition model Bert-BiLSTM-CRF and a relational extraction model Bert-BiGRU-ATT, based on the multiple heterogeneous data in the assembly domain, to construct an assembly domain knowledge graph centered on and for human-robot collaboration. Among them, the Chinese-character-based names entity recognition model avoids the error bias caused by Chinese word segmentation in traditional methods, while the relation extraction model fully extracts the association information between entities and relations. The proposed entity recognition model and relation extraction model are validated in a real scenario of mechanical product assembly. The experimental results show that the proposed models exhibit excellent performance in the human-machine collaborative assembly domain, with overall average F1-score of 84.02% and 94.92% for entities and relations, respectively. The constructed knowledge graph of the assembly domain contains 2724 triples, and the knowledge graph is presented through a visual interactive interface.
- Open Access
- 1 January 2025
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 84 (2) , 3787-3810
Prediction of Assembly Intent for Human-Robot Collaboration Based on Video Analytics and Hidden Markov Model
Despite the gradual transformation of traditional manufacturing by the Human-Robot Collaboration Assembly (HRCA), challenges remain in the robot’s ability to understand and predict human assembly intentions. This study aims... | Find, read and cite all the research you need on Tech Science Press
- 1 January 2025
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 84 (2) , 3787-3810
Open AccessPrediction of Assembly Intent for Human-Robot Collaboration Based on Video Analytics and Hidden Markov Model
Despite the gradual transformation of traditional manufacturing by the Human-Robot Collaboration Assembly (HRCA), challenges remain in the robot’s ability to understand and predict human assembly intentions. This study aims... | Find, read and cite all the research you need on Tech Science Press
- Open Access
- 27 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 46907-46918
Pedestrian Trajectory Prediction and Pose Estimation Considering Behavioral Characteristic Relationships and Noise Inhibition
In the domain of pedestrian trajectory prediction(PTP) from a roadbed perspective, the visibility of pedestrian feature points is inevitably compromised by external noise interference, impacting both pedestrian pose estimation(PPE) and PTP. This paper presents an innovative model for PTP. The model not only tackles noise interference but also takes into account the inherent correlation between pedestrian pose features and trajectory coordinates. To tackle the challenge of noise interference during pedestrian crossing, we reframe it as an anomalous feature detection problem using the Graph Deviation Network (GDN). Subsequently, we enhance the Long Short-Term Memory (LSTM) module by incorporating a time-domain anomaly suppression module, resulting in the development of an Anomaly Inhibition-LSTM (AI-LSTM) with robust noise suppression capabilities. Finally, by integrating the predicted values of behavioral pose and trajectory position, considering the behavioral characteristic relationship resolved by the GDN algorithm, we achieve accurate prediction and pose estimation of pedestrian crossing trajectories amidst noise interference. Experimental results demonstrate superior performance of our algorithm in the PPE task when compared to GDN and LSTM algorithms. In the PTP task, our algorithm exhibits performance comparable to the Transformer-based method, with the added advantage of improved interpretability.
- 27 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 46907-46918
Open AccessPedestrian Trajectory Prediction and Pose Estimation Considering Behavioral Characteristic Relationships and Noise Inhibition
In the domain of pedestrian trajectory prediction(PTP) from a roadbed perspective, the visibility of pedestrian feature points is inevitably compromised by external noise interference, impacting both pedestrian pose estimation(PPE) and PTP. This paper presents an innovative model for PTP. The model not only tackles noise interference but also takes into account the inherent correlation between pedestrian pose features and trajectory coordinates. To tackle the challenge of noise interference during pedestrian crossing, we reframe it as an anomalous feature detection problem using the Graph Deviation Network (GDN). Subsequently, we enhance the Long Short-Term Memory (LSTM) module by incorporating a time-domain anomaly suppression module, resulting in the development of an Anomaly Inhibition-LSTM (AI-LSTM) with robust noise suppression capabilities. Finally, by integrating the predicted values of behavioral pose and trajectory position, considering the behavioral characteristic relationship resolved by the GDN algorithm, we achieve accurate prediction and pose estimation of pedestrian crossing trajectories amidst noise interference. Experimental results demonstrate superior performance of our algorithm in the PPE task when compared to GDN and LSTM algorithms. In the PTP task, our algorithm exhibits performance comparable to the Transformer-based method, with the added advantage of improved interpretability.
- 1 December 2023
- Published by Springer Nature in Acta Mechanica Solida Sinica
- Vol. 37 (1) , 109-123
Elastohydrodynamic Lubrication Interface Stiffness and Damping Considering Asperity Lateral Contact
- 1 December 2023
- Published by Springer Nature in Acta Mechanica Solida Sinica
- Vol. 37 (1) , 109-123
Elastohydrodynamic Lubrication Interface Stiffness and Damping Considering Asperity Lateral Contact
- Open Access
- 27 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 9382-9391
Tangential Contact Stiffness Model of Solid-Liquid Interface Under Mixed Lubrication
In order to analyze and predict the performance of mechanical structure and system, the tangential contact of solid-liquid interface under normal and tangential loads is studied, and the tangential stiffness model of rough surfaces is established by analyzing various contact states of the asperity under normal elastic-plastic deformation and tangential stick-slip.Based on the contact model of closed oil pits based on the influence of rough surfaces, on the basis of fully considering the influence of gradual application of load on the number of closed oil pit, and then changing the load distribution of solid-liquid interface, a liquid tangential stiffness model is established. The tangential stiffness of solid-liquid interface is obtained by two parts in parallel. Through simulation and experimental analysis, the effects of normal load, deformation and lubricant viscosity on the tangential stiffness of solid-liquid interface are revealed, and the tangential stiffness with or without lubricating medium is compared and analyzed. The results show that the tangential stiffness of solid-liquid interface and solid-solid interface increases nonlinearly with the increase of normal load and deformation. Due to the contribution of liquid stiffness, the tangential stiffness of solid-liquid interface is always slightly higher than that of solid-solid interface. The greater the viscosity of the lubricating medium, the greater the tangential stiffness of the solid-liquid interface. At low load, liquid contact is dominant, and the tangential stiffness of solid-liquid interface is low. Under moderate and heavy loads, the solid contact is dominant, and the tangential stiffness of the solid-liquid interface increases rapidly. Therefore, the tangential contact stiffness of the solid-liquid interface in mixed lubrication can be effectively improved by increasing the normal load and increasing the viscosity of the lubricating medium.
- 27 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 9382-9391
Open AccessTangential Contact Stiffness Model of Solid-Liquid Interface Under Mixed Lubrication
In order to analyze and predict the performance of mechanical structure and system, the tangential contact of solid-liquid interface under normal and tangential loads is studied, and the tangential stiffness model of rough surfaces is established by analyzing various contact states of the asperity under normal elastic-plastic deformation and tangential stick-slip.Based on the contact model of closed oil pits based on the influence of rough surfaces, on the basis of fully considering the influence of gradual application of load on the number of closed oil pit, and then changing the load distribution of solid-liquid interface, a liquid tangential stiffness model is established. The tangential stiffness of solid-liquid interface is obtained by two parts in parallel. Through simulation and experimental analysis, the effects of normal load, deformation and lubricant viscosity on the tangential stiffness of solid-liquid interface are revealed, and the tangential stiffness with or without lubricating medium is compared and analyzed. The results show that the tangential stiffness of solid-liquid interface and solid-solid interface increases nonlinearly with the increase of normal load and deformation. Due to the contribution of liquid stiffness, the tangential stiffness of solid-liquid interface is always slightly higher than that of solid-solid interface. The greater the viscosity of the lubricating medium, the greater the tangential stiffness of the solid-liquid interface. At low load, liquid contact is dominant, and the tangential stiffness of solid-liquid interface is low. Under moderate and heavy loads, the solid contact is dominant, and the tangential stiffness of the solid-liquid interface increases rapidly. Therefore, the tangential contact stiffness of the solid-liquid interface in mixed lubrication can be effectively improved by increasing the normal load and increasing the viscosity of the lubricating medium.
- Open Access
- 29 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 109104-109120
Theoretical Model of Tangential Contact Stiffness and Damping of Solid-Liquid Interface in Macroscopic Relative Motion
The macroscopic relative motion solid-liquid interface widely exists in the contact motion pairs of machine tools and other mechanical equipment. In order to accurately obtain the tangential contact stiffness and damping parameters, the Savkoor asperity adhesion-sliding friction contact model is used to analyze the contact area and the corresponding tangential force changes of a single pair of solid contact asperity in the four typical phases of contact growth, contact stagnation, crack adhesion and crack propagation. According to the hypothesis of Gaussian distribution of asperity on rough surface, the contact model of single-pair asperities is extended to the whole joint. The tangential contact stiffness and damping models of solid-solid interface in macroscopic relative motion are obtained. For the fluid contact part, the oil film pressure distribution and film thickness are obtained by solving part of the film Reynold’s equation, and then the fluid tangential stiffness and damping model is established. The tangential contact stiffness and damping of the whole solid-liquid interface are obtained by analyzing the stiffness and damping of solid and fluid parts, and the effects of normal load and moving velocity on tangential contact stiffness and damping are obtained by simulation. The results show that the tangential contact stiffness and damping of solid-liquid interface increase with the increase of normal contact load and decrease with the increase of moving velocity.
- 29 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 109104-109120
Open AccessTheoretical Model of Tangential Contact Stiffness and Damping of Solid-Liquid Interface in Macroscopic Relative Motion
The macroscopic relative motion solid-liquid interface widely exists in the contact motion pairs of machine tools and other mechanical equipment. In order to accurately obtain the tangential contact stiffness and damping parameters, the Savkoor asperity adhesion-sliding friction contact model is used to analyze the contact area and the corresponding tangential force changes of a single pair of solid contact asperity in the four typical phases of contact growth, contact stagnation, crack adhesion and crack propagation. According to the hypothesis of Gaussian distribution of asperity on rough surface, the contact model of single-pair asperities is extended to the whole joint. The tangential contact stiffness and damping models of solid-solid interface in macroscopic relative motion are obtained. For the fluid contact part, the oil film pressure distribution and film thickness are obtained by solving part of the film Reynold’s equation, and then the fluid tangential stiffness and damping model is established. The tangential contact stiffness and damping of the whole solid-liquid interface are obtained by analyzing the stiffness and damping of solid and fluid parts, and the effects of normal load and moving velocity on tangential contact stiffness and damping are obtained by simulation. The results show that the tangential contact stiffness and damping of solid-liquid interface increase with the increase of normal contact load and decrease with the increase of moving velocity.
- Open Access
- 18 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 42809-42823
Occlusion-Aware Motion Planning for Autonomous Driving
Motion planning of autonomous vehicles is still challenging in urban road environments with occlusions. In this work, with the view of safety, comfort and efficiency, we present a motion planning framework that enables autonomous vehicles to navigate safely in urban road with occlusions. Our solution mainly includes three parts: local path planning, trajectory planning and speed planning. First, based on the improved Artificial Potential Field to generate the local path, then the optimal trajectory is solved in the S-L coordinate with the local path as the reference line. Finally, the potential risk probability of the occluded area is incorporated into the incomplete information static game framework and implement speed planning based on the game results and the proposed vehicle "safe driving" to complete the collision avoidance between the autonomous vehicle and visible or obscured dynamic traffic participants. Through simulation verification in common traffic scenarios and a comparison with some existing methods, the proposed method is proven to enable autonomous vehicles to navigate safely in traffic scenarios with occlusions and improve the driving efficiency and comfort of autonomous vehicles.
- 18 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 42809-42823
Open AccessOcclusion-Aware Motion Planning for Autonomous Driving
Motion planning of autonomous vehicles is still challenging in urban road environments with occlusions. In this work, with the view of safety, comfort and efficiency, we present a motion planning framework that enables autonomous vehicles to navigate safely in urban road with occlusions. Our solution mainly includes three parts: local path planning, trajectory planning and speed planning. First, based on the improved Artificial Potential Field to generate the local path, then the optimal trajectory is solved in the S-L coordinate with the local path as the reference line. Finally, the potential risk probability of the occluded area is incorporated into the incomplete information static game framework and implement speed planning based on the game results and the proposed vehicle "safe driving" to complete the collision avoidance between the autonomous vehicle and visible or obscured dynamic traffic participants. Through simulation verification in common traffic scenarios and a comparison with some existing methods, the proposed method is proven to enable autonomous vehicles to navigate safely in traffic scenarios with occlusions and improve the driving efficiency and comfort of autonomous vehicles.
- Open Access
- 25 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 13996-14005
Visual Navigation Based on Language Assistance and Memory
In order to solve outdoor mobile robots’ dependence on geographic information systems, and to realize automatic navigation in the face of complex and changeable scenes, we propose a method that selects landmark and adds prompt guidance so that the mobile robot can navigate relying on visual-language and memory. Visual-language can guide the direction of the mobile robot’s movement, obeying the annotation of people and according to its memory of the scene, which refers to the strategy of selecting passed-by landmarks for the route and remembering the scene features. When passing it, the agent can ascertain the position and match it to carry out the action. Experiments showed that our proposed method can achieve the purpose of independent navigation without GIS, and is superior to existing methods.
- 25 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 13996-14005
Open AccessVisual Navigation Based on Language Assistance and Memory
In order to solve outdoor mobile robots’ dependence on geographic information systems, and to realize automatic navigation in the face of complex and changeable scenes, we propose a method that selects landmark and adds prompt guidance so that the mobile robot can navigate relying on visual-language and memory. Visual-language can guide the direction of the mobile robot’s movement, obeying the annotation of people and according to its memory of the scene, which refers to the strategy of selecting passed-by landmarks for the route and remembering the scene features. When passing it, the agent can ascertain the position and match it to carry out the action. Experiments showed that our proposed method can achieve the purpose of independent navigation without GIS, and is superior to existing methods.
- Open Access
Visual Relationship Detection with Multimodal Fusion and Reasoning
Visual relationship detection aims to completely understand visual scenes and has recently received increasing attention. However, current methods only use the visual features of images to train the semantic network, which does not match human habits in which we know obvious features of scenes and infer covert states using common sense. Therefore, these methods cannot predict some hidden relationships of object-pairs from complex scenes. To address this problem, we propose unifying vision–language fusion and knowledge graph reasoning to combine visual feature embedding with external common sense knowledge to determine the visual relationships of objects. In addition, before training the relationship detection network, we devise an object–pair proposal module to solve the combination explosion problem. Extensive experiments show that our proposed method outperforms the state-of-the-art methods on the Visual Genome and Visual Relationship Detection datasets.
Open AccessVisual Relationship Detection with Multimodal Fusion and Reasoning
Visual relationship detection aims to completely understand visual scenes and has recently received increasing attention. However, current methods only use the visual features of images to train the semantic network, which does not match human habits in which we know obvious features of scenes and infer covert states using common sense. Therefore, these methods cannot predict some hidden relationships of object-pairs from complex scenes. To address this problem, we propose unifying vision–language fusion and knowledge graph reasoning to combine visual feature embedding with external common sense knowledge to determine the visual relationships of objects. In addition, before training the relationship detection network, we devise an object–pair proposal module to solve the combination explosion problem. Extensive experiments show that our proposed method outperforms the state-of-the-art methods on the Visual Genome and Visual Relationship Detection datasets.