Search Results for author:
Found 5 papers, 0 papers with code
In the driver's mind: modeling the dynamics of human overtaking decisions in interactions with oncoming automated vehicles
To address these gaps, we conducted a "reverse Wizard-of-Oz" driving simulator experiment with 30 participants who repeatedly interacted with oncoming AVs and HDVs, measuring the drivers' gap acceptance decisions and response times.
Data-driven Semi-supervised Machine Learning with Surrogate Safety Measures for Abnormal Driving Behavior Detection
Moreover, previous ML-based approaches predominantly utilize basic vehicle motion features (such as velocity and acceleration) to label and detect abnormal driving behaviors, while this study seeks to introduce Surrogate Safety Measures (SSMs) as the input features for ML models to improve the detection performance.
Intelligent Anomaly Detection for Lane Rendering Using Transformer with Self-Supervised Pre-Training and Customized Fine-Tuning
In conclusion, the proposed pipeline, with its incorporation of self-supervised pre-training using MiM and other advanced deep learning techniques, emerges as a robust solution for enhancing the accuracy and efficiency of lane rendering image anomaly detection in digital navigation systems.
A cognitive process approach to modeling gap acceptance in overtaking
In this study, we address this issue by employing a cognitive process approach to describe the dynamic interactions by the oncoming vehicle during overtaking maneuvers.
A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection
Since lane markings are continuous lines, the lanes that are difficult to be accurately detected in the current single image can potentially be better deduced if information from previous frames is incorporated.
