This paper presents an overview of robot failure detection work from HRI and adjacent fields using failures as an opportunity to examine robot explanation behaviours. As humanoid robots remain experimental tools in the early 2020s, interactions with robots are situated overwhelmingly in controlled environments, typically studying various interactional phenomena. Such interactions suffer from real-world and large-scale experimentation and tend to ignore the 'imperfectness' of the everyday user. Robot explanations can be used to approach and mitigate failures, by expressing robot legibility and incapability, and within the perspective of common-ground. In this paper, I discuss how failures present opportunities for explanations in interactive conversational robots and what the potentials are for the intersection of HRI and explainability research.

翻译：本文概述了人机交互及其相关领域中机器人故障检测的研究，将故障视为审视机器人解释行为的契机。在21世纪20年代初，人形机器人仍处于实验工具阶段，与它们的交互绝大多数发生在受控环境中，通常用于研究各种交互现象。此类交互缺乏真实世界和大规模实验的验证，且往往忽略了普通用户的不完美性。机器人解释可通过表达其可读性与能力不足，并基于共同背景的视角，来应对并缓解故障。在本文中，我将探讨交互式对话机器人中故障如何为解释提供契机，以及人机交互与可解释性研究交叉领域的潜在可能。