A Customizable Neural Network Based Framework for Autonomous Vehicle Control with Human-Guided Learning

This study introduces a novel control framework for adaptive cruise control (ACC) in autonomous vehicles (AVs), utilizing Long Short-Term Memory (LSTM) networks and physics-informed constraints. The LSTM component captures complex vehicle dynamics and temporal dependencies, while physics constraints ensure realistic operational limits. This framework supports customization of control objectives, allowing for the integration of various performance metrics to achieve specific goals such as reducing speed variation and enhancing traffic flow. A distinctive feature of this framework is the implementation of human-guided learning, where a human-controlled lead vehicle profile informs the training process. This human-in-the-loop approach allows the controller to adapt to real-world driving patterns and complexities effectively. Extensive simulations demonstrate the framework's adaptability across different scenarios, highlighting its capability to maintain safe vehicle spacing, ensure smooth speed profiles, and optimize energy efficiency. The results highlight the controller's ability to maintain safe spacing while ensuring smooth speed profiles and optimizing energy efficiency, depending on the chosen customization settings. This research paves the way for the development of more intelligent, safe, and efficient ACC systems that can be tailored to various driving conditions and user preferences while benefiting from the knowledge and experience of human drivers during the learning process.

I. Introduction

With the rapid advancement of emerging technologies, autonomous driving has become increasingly available and is expected to transform the landscape of future transportation systems by enhancing traffic safety [1], smoothing traffic flow [2], and improving transportation energy efficiency [3], among others. These potential benefits of autonomous ve-hicles (AVs) are becoming increasingly prominent thanks to the development of sensing, automation, and computing tech-nologies. While numerous potential benefits of AVs hinge on achieving a high market penetration rate (MPR) [4], recent studies suggest that even a modest MPR of intelligently controlled AVs can significantly enhance traffic flow [5]. This revelation underscores the opportunity to develop efficient AV controllers to improve traffic performance without ne-cessitating additional infrastructure installation.