Intelligent Anomaly Detection for Lane Rendering Using Transformer with Self-Supervised Pre-Training and Customized Fine-Tuning

The burgeoning navigation services using digital maps provide great convenience to drivers. However, there are sometimes anomalies in the lane rendering map images, which might mislead human drivers and result in unsafe driving. To accurately and effectively detect the anomalies, this paper transforms lane rendering image anomaly detection into...

Sequential Neural Network Model with Spatial-Temporal Attention Mechanism for Robust Lane Detection Using Multi Continuous Image Frames

Lane detection serves as a fundamental task for automated vehicles and Advanced Driver Assistance Systems. However, current lane detection methods can not deliver the versatility of accurate, robust, and realtime compatible lane detection in real-world scenarios especially under challenging driving scenes. Available vision-based methods in the...

Robust Lane Detection through Self Pre-training with Masked Sequential Autoencoders and Fine-tuning with Customized PolyLoss

Lane detection is crucial for vehicle localization which makes it the foundation for automated driving and many intelligent and advanced driving assistant systems. Available vision-based lane detection methods do not make full use of the valuable features and aggregate contextual information, especially <br/>the interrelationships between lane...

Influence of Behavioural Model Formulation on Surrogate Safety Measures in Traffic Microsimulation

Traffic microsimulation is a commonly used tool in traffic engineering. Given its flexibility and cost-efficiency, it is increasingly used for evaluating traffic safety. In real life traffic, unsafety is in many cases due to human error in driving behaviour. In traffic microsimulations however, driving behaviour is highly dependent on the...

Data-driven Semi-supervised Machine Learning with Surrogate Safety Measures for Abnormal Driving Behavior Detection

Detecting abnormal driving behavior is critical for road traffic safety and the evaluation of drivers' behavior. With the advancement of machine learning (ML) algorithms and the accumulation of naturalistic driving data, many ML models have been adopted for abnormal driving behavior detection. Most existing ML-based detectors rely on (fully)...

Social-aware Planning and Control for Automated Vehicles Based on Driving Risk Field and Model Predictive Contouring Control: Driving through Roundabouts as a Case Study

The gradual deployment of automated vehicles (AVs) results in mixed traffic where AVs will interact with human-driven vehicles (HDVs). Thus, social-aware motion planning and control while considering interactions with HDVs on the road is critical for AVs’ deployment and safe driving under various maneuvers. Previous research mostly focuses on...

A Hybrid Spatial-temporal Sequence-to-one Neural Network Model for Lane Detection

Reliable and accurate lane detection is of vital importance for the safe performance of Lane Keeping Assistance and Lane Departure Warning systems. However, under certain challenging peculiar circumstances (e.g., marking degradation, serious vehicle occlusion), it is quite difficult to get satisfactory performance in accurately detecting the...

Road Infrastructure Requirements for Improved Performance of Lane Assistance Systems

There is a pressing need for road authorities to take a proactive role in the deployment of automated vehicles on the existing road network. This requires a comprehensive understanding of the road infrastructure requirements that would lead to safe operation of automated vehicles. In this context, a field test with Lane Departure Warning and...