Pengyu Xue
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Pengyu Xue has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Dawei Pi
Nanjing University of Science and Technology
4 shared publications - Hongliang Wang
School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China
3 shared publications - Yibo Hu
School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing, China
3 shared publications Yongjun Yan
School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing, China
3 shared publicationsDawei Pi
School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing, China
2 shared publicationsHongliang Wang
Nanjing University of Science and Technology
2 shared publications
Latest Publications
- 15 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (6) , 8694-8706
Drivable Area Detection Method in Dark Unstructured-Roads Based on CNN Data Fusion With Surface Normal Estimation
Vehicle perception of roads is a critical foundation for intelligent transportation systems. While most existing research on intelligent transportation focuses on structured roads, the identification of drivable areas in complex dark-field environments remains challenging and underexplored. To address this issue, this paper proposes a drivable area detection network based on the fusion of images and point clouds. Specifically, a convolutional neural network (CNN) architecture augmented with a surface normal estimator (SNE) model is proposed. This approach significantly reduces resolution while effectively extracting and fusing features from multiple sensors. The proposed model is trained and validated using the Off-Road Freex Detection (ORFD) dataset, demonstrating its effectiveness and accuracy through comprehensive performance metrics. Finally, real-world vehicle tests are conducted to evaluate the drivable area detection system. These tests involve real-time data collection, image enhancement, and dense upsampling of point clouds. The processed multimodal data are fed into the detection network in real time for synchronous training and learning. The detection and recognition of unstructured drivable areas in a real dark environment perception platform confirm the efficacy of the proposed method.
- 15 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (6) , 8694-8706
Drivable Area Detection Method in Dark Unstructured-Roads Based on CNN Data Fusion With Surface Normal Estimation
Vehicle perception of roads is a critical foundation for intelligent transportation systems. While most existing research on intelligent transportation focuses on structured roads, the identification of drivable areas in complex dark-field environments remains challenging and underexplored. To address this issue, this paper proposes a drivable area detection network based on the fusion of images and point clouds. Specifically, a convolutional neural network (CNN) architecture augmented with a surface normal estimator (SNE) model is proposed. This approach significantly reduces resolution while effectively extracting and fusing features from multiple sensors. The proposed model is trained and validated using the Off-Road Freex Detection (ORFD) dataset, demonstrating its effectiveness and accuracy through comprehensive performance metrics. Finally, real-world vehicle tests are conducted to evaluate the drivable area detection system. These tests involve real-time data collection, image enhancement, and dense upsampling of point clouds. The processed multimodal data are fed into the detection network in real time for synchronous training and learning. The detection and recognition of unstructured drivable areas in a real dark environment perception platform confirm the efficacy of the proposed method.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 11 (3) , 7979-7990
Research on Longitudinal–Vertical Coordinated Recovery Drive Control for Corner-Modular Distributed Drive Vehicles
This paper addresses the issue of rapid recovery for corner-modular electric vehicles on low-traction surfaces such as ice, snow, and sand. A drive anti-slip controller based on observing wheel dynamic load variations is proposed, integrating model predictive control (MPC) and sliding mode control (SMC). This approach achieves “synchronized” control between the drive system and active suspension for rapid vehicle recovery. In this study, an extended Kalman filter (EKF)-based observer is developed to monitor the vertical dynamic load between the wheel and the ground. Concurrently, a synchronous phase pre-compensation calculator (SPPC) is designed to address control signal delays. Building upon this, a fusion controller (SIMP-CISMC)—which utilizes the semi-implicit Euler method for model prediction (SIMP) and conditional integration for switching sliding mode control laws (CISMC)—is proposed. This controller enables coordinated control between the drivetrain and the active suspension system, enhancing effective driving force during recovery. The results indicate that the proposed method shows significant advantages in joint simulations with CarSim and Simulink, improving tire longitudinal driving force by 6.99%, 5.09%, and 4.13% compared to traditional SMC, MPC, and sliding mode predictive control (SMPC), respectively.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 11 (3) , 7979-7990
Research on Longitudinal–Vertical Coordinated Recovery Drive Control for Corner-Modular Distributed Drive Vehicles
This paper addresses the issue of rapid recovery for corner-modular electric vehicles on low-traction surfaces such as ice, snow, and sand. A drive anti-slip controller based on observing wheel dynamic load variations is proposed, integrating model predictive control (MPC) and sliding mode control (SMC). This approach achieves “synchronized” control between the drive system and active suspension for rapid vehicle recovery. In this study, an extended Kalman filter (EKF)-based observer is developed to monitor the vertical dynamic load between the wheel and the ground. Concurrently, a synchronous phase pre-compensation calculator (SPPC) is designed to address control signal delays. Building upon this, a fusion controller (SIMP-CISMC)—which utilizes the semi-implicit Euler method for model prediction (SIMP) and conditional integration for switching sliding mode control laws (CISMC)—is proposed. This controller enables coordinated control between the drivetrain and the active suspension system, enhancing effective driving force during recovery. The results indicate that the proposed method shows significant advantages in joint simulations with CarSim and Simulink, improving tire longitudinal driving force by 6.99%, 5.09%, and 4.13% compared to traditional SMC, MPC, and sliding mode predictive control (SMPC), respectively.
- 8 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 10 (3) , 1974-1988
A Real-Time Dynamic Adjustment Cooperative Adaptive Cruise Control Method Based on Fuzzy-Robust MPC
The cooperative adaptive cruise control (CACC) system can simplify the driver's operation and improve driving safety. However, the current CACC methods can not adapt to the rapid changes in following and comfort requirements caused by complex and time-varying traffic environments. In this paper, a novel CACC method is proposed. Firstly, a switching logic of cruise following mode is formulated. Secondly, a safety distance model for velocity classification under the requirements of full velocity region of vehicle is established. Thirdly, the CACC method is designed based on fuzzy-robust model predictive control (Fuzzy-RMPC) algorithm. A five-order model of vehicle longitudinal distance is constructed. According to the safety, compliance and comfort requirements, MPC cost function and constraints are obtained. A robust controller is constructed to provide error correction terms, and a relaxation factor is introduced to extend the feasible solution. The fuzzy weight factor of the performance index is given, so that the vehicle can adapt to the complex and changeable traffic conditions. Finally, four typical conditions are selected to verify the performance of the proposed method in complex traffic environment.
- 8 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 10 (3) , 1974-1988
A Real-Time Dynamic Adjustment Cooperative Adaptive Cruise Control Method Based on Fuzzy-Robust MPC
The cooperative adaptive cruise control (CACC) system can simplify the driver's operation and improve driving safety. However, the current CACC methods can not adapt to the rapid changes in following and comfort requirements caused by complex and time-varying traffic environments. In this paper, a novel CACC method is proposed. Firstly, a switching logic of cruise following mode is formulated. Secondly, a safety distance model for velocity classification under the requirements of full velocity region of vehicle is established. Thirdly, the CACC method is designed based on fuzzy-robust model predictive control (Fuzzy-RMPC) algorithm. A five-order model of vehicle longitudinal distance is constructed. According to the safety, compliance and comfort requirements, MPC cost function and constraints are obtained. A robust controller is constructed to provide error correction terms, and a relaxation factor is introduced to extend the feasible solution. The fuzzy weight factor of the performance index is given, so that the vehicle can adapt to the complex and changeable traffic conditions. Finally, four typical conditions are selected to verify the performance of the proposed method in complex traffic environment.
- 13 July 2024
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 136
Collaborative planning and control of heterogeneous multi-ground unmanned platforms
- 13 July 2024
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 136
Collaborative planning and control of heterogeneous multi-ground unmanned platforms
- Open Access
- 7 October 2020
- Published by Springer Nature in Research Square
Braking-Style-Based Optimization for Regenerative Braking System of an Electric Commercial Vehicle
With the development of intelligent transportation system, intelligent network technology has been studied on a large scale in vehicle field. Electrification of vehicles and drive-by-wire chassis provide possibilities for the application of connected autonomous electrified vehicles. Regenerative braking control is an important field among drive-by-wire chassis control technologies. Regenerative braking control is a multi-objective optimization problem, which has the aim of improving regenerative energy efficiency, brake performance, and brake comfort. Therefore, a model predictive control (MPC) is proposed to solve the problem with consideration of different brake styles, such as aggressive, moderate and conservative. Then, the models of the main components associated with the regenerative braking system are designed and built up in a typical deceleration process for simulation and analysis. The simulation results show that the aggressive style mode is the best brake performance, which cause issues on brake comfort as well. The conservative style mode makes full use of motor braking and has advantage of the brake comfort and regenerative energy efficiency. But, it is not good at rapid braking performance of low brake intensity. The moderate style mode is suitable for most drivers, which is balanced of the above characteristics. Finally, experimental tests under ECE driving cycle are also carried out to further verify the characteristics of proposed three brake modes.
- 7 October 2020
- Published by Springer Nature in Research Square
Open AccessBraking-Style-Based Optimization for Regenerative Braking System of an Electric Commercial Vehicle
With the development of intelligent transportation system, intelligent network technology has been studied on a large scale in vehicle field. Electrification of vehicles and drive-by-wire chassis provide possibilities for the application of connected autonomous electrified vehicles. Regenerative braking control is an important field among drive-by-wire chassis control technologies. Regenerative braking control is a multi-objective optimization problem, which has the aim of improving regenerative energy efficiency, brake performance, and brake comfort. Therefore, a model predictive control (MPC) is proposed to solve the problem with consideration of different brake styles, such as aggressive, moderate and conservative. Then, the models of the main components associated with the regenerative braking system are designed and built up in a typical deceleration process for simulation and analysis. The simulation results show that the aggressive style mode is the best brake performance, which cause issues on brake comfort as well. The conservative style mode makes full use of motor braking and has advantage of the brake comfort and regenerative energy efficiency. But, it is not good at rapid braking performance of low brake intensity. The moderate style mode is suitable for most drivers, which is balanced of the above characteristics. Finally, experimental tests under ECE driving cycle are also carried out to further verify the characteristics of proposed three brake modes.