A5077728417- Traffic and Road Safety
- Traffic control and management
- Autonomous Vehicle Technology and Safety
- Transportation Planning and Optimization
- Traffic Prediction and Management Techniques
- Vehicle emissions and performance
- Urban Transport and Accessibility
- Hybrid Renewable Energy Systems
- Transportation and Mobility Innovations
- Human-Automation Interaction and Safety
- Injury Epidemiology and Prevention
- Infrastructure Maintenance and Monitoring
- Electric Vehicles and Infrastructure
- Transportation Safety and Impact Analysis
- Metal Alloys Wear and Properties
- Autopsy Techniques and Outcomes
- Automotive and Human Injury Biomechanics
- Microstructure and Mechanical Properties of Steels
- Energy and Environment Impacts
- Metallurgy and Material Forming
- Hydrogen Storage and Materials
Changsha University of Science and Technology
2020-2025
Tsinghua University
2023-2024
The University of Texas at Austin
2023
Southeast University
2016-2020
Freeway bottlenecks lead to traffic congestion and speed reduction, resulting in increased risks of rear-end collision. This paper aimed develop a control strategy an integrated system cooperative adaptive cruise (CACC) variable limit (VSL) reduce collision near freeway bottlenecks. A microscopic simulation testbed was first constructed, which the realistic PATH CACC models surrogate safety measures time exposed time-to-collision (TET) (TIT) were used. feedback algorithm then developed for...
The accuracy of the data is crucial to real-time prediction autonomous driving. Due factors such as weather and collection equipment, there frequently exist noises in collected real time. Therefore, it necessary perform analysis on acquired kinematic features related driving behavior prediction. This study proposes a novel deep learning framework explore influences lane-changing intention Kinematic including longitudinal distance difference, velocity acceleration, lateral acceleration...
The strip crown or profile generated by the cooperation of finishing mills is affected many factors, so obtaining an accurate has always been a challenge in hot rolling. As kind solution to ensure accuracy hot-rolled strips, this study develops three novel prediction models using well-performing and efficient tree-based ensemble learning algorithms, including Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Light Machine (LightGBM), respectively. comparison results measured predicted...
Complex road sections without lane markings cannot constrain vehicles to follow the disciplines. As a result, often exhibit more disorderly rapid lateral movements (RLMs) in these areas, making it difficult accurately predict vehicle trajectories. This study takes toll plaza diverging area as an example propose framework incorporated Hidden Markov Model (HMM) and Temporal Fusion Transformer (TFT) for trajectory prediction non-lane based complex sections. The results demonstrate that RLMs...
Existing research on decision-making of autonomous vehicles (AVs) has mainly focused normal road sections, with limited exploration in complex traffic environments without lane markings. Taking toll plaza diverging area as an example, this study proposes a lateral motion strategy for AVs based deep reinforcement learning (DRL) algorithms. First, microscopic simulation platform is developed to simulate the realistic trajectories human-driven (HVs), providing high-fidelity training...
Among the factors affecting road traffic safety, alignment characteristics are often ignored by people because they cause accidents in an indirect way. In view of this problem, total number accidents, casualties (deaths, minor injuries, serious injuries), and time closures were chosen as safety evaluation indices ranked technique for order preference similarity to ideal solution (TOPSIS) method. The sections whose ranking index value C < 0.8 identified accident blackspots. On basis, slope...