Ethical Decision-Making In Sustainable Autonomous Transportation: A Comparative Study Of Rule-Based And Learning-Based Systems

Abstract

Abstract- As autonomous vehicles (AVs) play an increasingly central role in sustainable and intelligent transportation systems, one critical challenge lies in how these systems make decisions in ethically complex scenarios. The ability of AVs to navigate moral dilemmas—such as prioritizing human life versus property—not only affects road safety but also has broader implications for public trust, environmental accountability, and regulatory compliance. This paper examines two prominent approaches to ethical decision-making in AVs: Rule-Based Systems (RBS) and Learning-Based Systems (LBS). RBS operate using predefined ethical rules crafted by experts, ensuring transparent and predictable behavior aligned with safety standards. LBS, in contrast, leverage machine learning to adapt based on real-world data, offering greater flexibility in dynamic environments. Through a comparative analysis of their capabilities and limitations, this study explores how each system responds to ethical challenges in autonomous mobility. It also advocates for a hybrid framework that integrates both approaches to promote safer, ethically responsible, and environmentally aware autonomous driving technologies.