| Summary

The research developed an automated driving framework, integrating lateral previewed steering control, longitudinal car-following acceleration control, and lane-change decision for minimizing braking.  The driving control algorithm considers risk assessment, predicted occupancy, human comfort, and vehicle dynamics using techniques including potential fields, previewed control, Intelligent Driver Model (IDM), and Minimizing Overall Braking Induced by Lane-change (MOBIL) model. Simulations showed effective and human-like driving control in obstacle avoidance and severe lane cut-in events. 

The algorithm was implemented for the connected autonomous vehicles in a 4-screen driving simulator during my internship at Volvo Group Trucks Technology. The simulator was built in the Blender game engine in Linux, along with a joystick-controlled drone view monitoring traffic conditions and a head-up display (HUD) for distraction studies. 

Additional related work includes creating a graphic user interface (GUI) using wxPython for automating highway scene generation following NHTSA guidelines and establishing the distraction study baseline.

Thesis Advisor: Prof. Sean N. Breanna; Internship Supervisor: Dr. Deborah D. Thompson