Driving Automation

Driving automation research centers on developing safe and efficient systems for self-driving vehicles, focusing on ensuring reliable human-machine interaction and accurate prediction of vehicle behavior in complex traffic scenarios. Current research employs machine learning techniques, including LSTM and bidirectional LSTM architectures for driver readiness assessment, and convolutional neural networks like ResNet and EfficientNet for trajectory prediction, alongside model-based approaches like STEAM and MoSAFE for analyzing system safety. These advancements aim to improve the safety and reliability of automated driving systems, ultimately impacting traffic flow simulation, human-vehicle interaction modeling, and the overall design of autonomous vehicles.