Designing Value-Aligned Traffic Agents through Conflict Sensitivity

TL;DR

This paper proposes a formal conflict analysis framework for designing autonomous traffic agents that are aligned with stakeholder values, emphasizing proactive value-sensitive design over runtime moral dilemma resolution.

Contribution

It introduces the use of epistemic game theory for conflict analysis in traffic agents and develops the concept of Value-Aligned Operational Design Domains (VODDs).

Findings

Conflict analysis informs value elicitation and system refinement.

VODDs structure autonomy according to contextual values.

Approach shifts focus from runtime dilemmas to development-time design.

Abstract

Autonomous traffic agents (ATAs) are expected to act in ways tat are not only safe, but also aligned with stakeholder values across legal, social, and moral dimensions. In this paper, we adopt an established formal model of conflict from epistemic game theory to support the development of such agents. We focus on value conflicts-situations in which agents face competing goals rooted in value-laden situations and show how conflict analysis can inform key phases of the design process. This includes value elicitation, capability specification, explanation, and adaptive system refinement. We elaborate and apply the concept of Value-Aligned Operational Design Domains (VODDs) to structure autonomy in accordance with contextual value priorities. Our approach shifts the emphasis from solving moral dilemmas at runtime to anticipating and structuring value-sensitive behaviour during development.