A5028359864- Autonomous Vehicle Technology and Safety
- Vehicle Dynamics and Control Systems
- Traffic control and management
- Robotic Path Planning Algorithms
- Traffic and Road Safety
- Image and Object Detection Techniques
- Visual perception and processing mechanisms
- Handwritten Text Recognition Techniques
- Digital Media Forensic Detection
- Metaheuristic Optimization Algorithms Research
- Human-Automation Interaction and Safety
- Virtual Reality Applications and Impacts
- Evolutionary Algorithms and Applications
- Advanced Battery Technologies Research
- Evacuation and Crowd Dynamics
- Advanced Optical Imaging Technologies
- Complex Network Analysis Techniques
- Neural Networks and Applications
- Anomaly Detection Techniques and Applications
- Data Visualization and Analytics
- Simulation and Modeling Applications
Zhejiang University
2015-2024
Sichuan University
2016
China Three Gorges University
2015
Chongqing University of Posts and Telecommunications
2010
Chongqing University
2009
The prevalence of motion sickness among passengers using personal electronic devices, such as smartphones, during vehicle journeys has become a growing concern. This issue is expected to intensify with the increasing adoption assistant or automated driving functions, which may lead non-driving tasks (NDT) being performed by all on-board passengers, including user in "driver" seat conditionally fully modes. trend presents challenges related sickness, particularly terms specific performance...
Chart classification is the foundation of chart analysis and document understanding. In this paper, we propose a novel framework to classify charts by combining convolutional networks deep belief networks. framework, firstly extract hidden features charts, which are taken from fully-connected layer We then utilize predict labels based on their features. The initialized using large number natural images fine-tuned prevent overfitting. Compared with previous methods primitive feature...
A novel character recognition system is proposed in this paper. By using the virtual reconfigurable architecture-based evolvable hardware, a series of systems are evolved. To improve accuracy systems, statistical pattern recognition-inspired methodology introduced. The performance method evaluated on characters with different levels noise. experimental results show that recognition-based scheme significantly outperforms traditional approach terms accuracy. For 1-bit noise, increased from...
<p>Driving strategy in dynamic environment is crucial to the automated vehicle safety. In extremely emergency scenarios with unavoidable collision (UC), especially those complex impact patterns, potential crash risk should be well considered. This paper proposes a mitigation (CM) algorithm for UCs, which directly embeds generalized severity index (CSI) model vehicle-to-vehicle collisions of multiple patterns. The idea that during short time before collision, will actively adapt its...
Driving on bumpy roads with potholes or bulges may severely compromise vehicle ride comfort, while in extreme cases safety be affected. Existing approaches mainly focus suspension control to ease the discomfort by adjusting equiv-alent damping and stiffness exerting active forces ride. In conventional approaches, these adjustments need know irregular input information of road ahead via camera lidar sensors. car following scenarios, it is difficult directly get such information, since a...
Autonomous vehicle, though rapidly developing, still faces several challenges, one of which is motion sickness. It necessary to mitigate sickness without sacrificing driving safety. Even if experiencing the same vibrational stimulus, people experience differently. However, in field planning that considers sickness, current studies are mostly focusing on how reduce discomfort index general ways, i.e. not considering for any specific passenger. Therefore, exploit further potential mitigation,...
Battery state-of-charge (SOC) is estimated for electric or hybrid vehicles by using Evolvable Hardware (EHW). SOC a key factor in the management of battery and its estimation an important challenging task. We combine EHW evolutionary algorithm to design system, which 16-row 4-layer with three inputs (voltage, magnification, charge-discharge mode) one output (estimated SOC). The used train chromosome structure after setting EHW. results show that it can obtain around experimental curve...
<div>Motion planning in dynamic environment is crucial to the automated driving safety. In extremely emergency scenarios with unavoidable collisions, especially those complex impact patterns, potential crash risk should be well considered motion planning. This paper proposes a algorithm for which directly embeds generalized severity index model vehicle-to-vehicle collisions of multiple patterns. Firstly, clothoid curve used sample vehicle trajectory before collision, and...
<div>Motion planning in dynamic environment is crucial to the automated driving safety. In extremely emergency scenarios with unavoidable collisions, especially those complex impact patterns, potential crash risk should be well considered motion planning. This paper proposes a algorithm for which directly embeds generalized severity index model vehicle-to-vehicle collisions of multiple patterns. Firstly, clothoid curve used sample vehicle trajectory before collision, and...
<p>Driving strategy in dynamic environment is crucial to the automated vehicle safety. In extremely emergency scenarios with unavoidable collision (UC), especially those complex impact patterns, potential crash risk should be well considered. This paper proposes a mitigation (CM) algorithm for UCs, which directly embeds generalized severity index (CSI) model vehicle-to-vehicle collisions of multiple patterns. The idea that during short time before collision, will actively adapt its...