External Human-Machine Interfaces (eHMIs) are key to facilitating interaction between autonomous vehicles and external road actors, yet most remain reactive and do not account for scalability and inclusivity. This paper introduces a conceptual design framework for adaptive eHMIs-interfaces that dynamically adjust communication as road actors vary and context shifts. Using the cyber-physical system as a structuring lens, the framework comprises three layers: Input (what the system detects), Processing (how the system decides), and Output (how the system communicates). Developed through theory-led abstraction and expert discussion, the framework helps researchers and designers think systematically about adaptive eHMIs and provides a structured tool to design, analyse, and assess adaptive communication strategies. We show how such systems may resolve longstanding limitations in eHMI research while raising new ethical and technical considerations.
@article{arxiv.2508.12518,
title = {Towards Adaptive External Communication in Autonomous Vehicles: A Conceptual Design Framework},
author = {Tram Thi Minh Tran and Judy Kay and Stewart Worrall and Marius Hoggenmueller and Callum Parker and Xinyan Yu and Julie Stephany Berrio Perez and Mao Shan and Martin Tomitsch},
journal= {arXiv preprint arXiv:2508.12518},
year = {2025}
}