Toward an “Equal-Footing” Human-Robot Interaction for Fully Autonomous Vehicles

Amanatidis, Theocharis; Langdon, Patrick; Clarkson, P. John · 2017 · Crossref

DOI: 10.1007/978-3-319-60384-1_30

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper addresses the design of user interfaces for fully autonomous vehicles (Level 5 automation), motivated by societal needs to reduce congestion and provide mobility to populations with reduced functional abilities, such as the elderly or those with impairments. The authors argue that current interface research focuses heavily on partial automation and control handovers, leaving a gap in understanding interfaces for vehicles that require no manual control. To fill this gap, the paper proposes a theoretical framework that intersects autonomous vehicle design, human-robot interaction (HRI), and affective computing. The authors classify fully autonomous vehicles as robots and apply HRI principles to their interface design. They propose a spectrum of interaction ranging from a conventional "master-slave" model, where the user commands the machine, to an "equal-footing" model, where the interaction mimics natural human-to-human communication. The paper posits two guiding principles: different levels of automation require different interfaces, and interface automation should increase alongside vehicle automation. Consequently, the authors identify two primary research questions: determining the optimal position on this interaction spectrum for autonomous vehicles and identifying which technological advances best enable such interfaces. To support the move toward "equal-footing" interaction, the paper integrates affective computing, defined as systems that relate to or influence emotions. The authors argue that affective interfaces improve user experience, enable personalization, reinforce brand identity, and increase inclusivity by adapting to diverse user capabilities without requiring training. They propose a system utilizing facial and voice/tonal emotion recognition as input, paired with a virtual agent (such as a digital driver) as output. While noting that current emotion recognition technologies are limited in context sensitivity and long-term mood analysis, the authors suggest that multi-modal recognition offers significant potential for creating more natural and trustworthy interactions. The significance of this work lies in establishing a theoretical foundation for designing inclusive, natural interfaces for Level 5 autonomous vehicles, shifting the focus from control handovers to continuous, adaptive interaction. The authors outline a future experimental framework to validate these theories, starting with low-fidelity driving simulator experiments using "Wizard of Oz" techniques for emotion recognition and natural language dialogue. They plan to progressively increase fidelity using publicly available software tools to determine which technological components have the greatest impact. This approach aims to provide a guide for developing interfaces that treat users as partners rather than operators, potentially unlocking the full societal benefits of autonomous transportation.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• automation
• driverless ads
• ehmi external hmi
• voice interaction
• acceptance adoption

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Applied Guidance: design guidelines
• Theoretical Contribution: conceptual framework