Dissertation Defense Announcement for Fahmida Islam – 06/27/2024 at 10:30 AM

Dissertation Title: Enhancing Longitudinal Velocity Control in Advanced Driving Systems using Deep Reinforcement Learning Approach
When: June 27, 2024, 10:30 AM
Where: Simrall 228
Candidate: Fahmida Islam
Degree: Doctor of Philosophy in Electrical and Computer Engineering
Committee Members: Dr. John E. Ball, Dr. Ali C. Gurbuz, Dr. Chris Goodin, and Dr. Nick Goberville

Abstract:
Longitudinal velocity control, or adaptive cruise control (ACC), is a common advanced driving feature aimed at assisting the driver and reducing fatigue. It maintains the velocity of a vehicle and ensures a safe distance from the preceding vehicle. Many models for ACC are available, such as Proportional, Integral, and Derivative (PID) and Model Predictive Control (MPC). However, conventional models have some limitations as they are designed for simplified driving scenarios. Artificial intelligence (AI) and machine learning (ML) have made robust navigation and decision-making possible in complex environments. Recent approaches, such as reinforcement learning (RL), have demonstrated remarkable performance in terms of faster processing and effective navigation through unknown environments. This dissertation explores an RL approach, deep deterministic policy gradient (DDPG), for longitudinal velocity control. The baseline DDPG model has been modified in two different ways. In the first method, an attention mechanism has been applied to the neural network (NN) of the DDPG model. Integrating the attention mechanism into the DDPG model helps in decreasing focus on less important features and enhances overall model effectiveness. In the second method, the inputs of the actor and critic networks of DDPG are replaced with outputs of the self-supervised network. The self-supervised learning process allows the model to accurately predict future states from current states and actions. A custom reward function has been designed for the RL algorithm considering overall safety, efficiency, and comfort. The proposed models have been trained with human trajectory data, and evaluated on multiple datasets, including publicly available data, simulated data, and sensor data collected from real-world environments. The analyses demonstrate that the new architectures can maintain strong robustness across various datasets and outperform the current state-of-the-art models.