论文标题
可以解释系统故障的AI：生成改善人类援助在失误恢复中的解释
Explainable AI for System Failures: Generating Explanations that Improve Human Assistance in Fault Recovery
论文作者
论文摘要
随着智能系统的不断增长，人工智能（AI）和日常生活中的机器人的整合正在增加。但是，在这种复杂的人类环境中进行互动时，智能系统（例如机器人）的故障可能是不可避免的，需要用户的恢复帮助。在这项工作中，我们为AI代理人的计划执行过程中遇到的失败而开发了自动的自然语言解释。这些解释是开发的，重点是帮助非专家用户了解不同的失败点，以更好地提供恢复帮助。具体来说，我们引入了一种基于上下文的信息类型，以进行解释，该信息既可以帮助非专家用户了解系统故障的根本原因，又可以选择适当的故障恢复。此外，我们将现有的序列到序列方法扩展到自动生成基于上下文的解释。通过这样做，我们可以开发一个模型，可以将基于上下文的解释概括为不同的故障类型和失败方案。
With the growing capabilities of intelligent systems, the integration of artificial intelligence (AI) and robots in everyday life is increasing. However, when interacting in such complex human environments, the failure of intelligent systems, such as robots, can be inevitable, requiring recovery assistance from users. In this work, we develop automated, natural language explanations for failures encountered during an AI agents' plan execution. These explanations are developed with a focus of helping non-expert users understand different point of failures to better provide recovery assistance. Specifically, we introduce a context-based information type for explanations that can both help non-expert users understand the underlying cause of a system failure, and select proper failure recoveries. Additionally, we extend an existing sequence-to-sequence methodology to automatically generate our context-based explanations. By doing so, we are able develop a model that can generalize context-based explanations over both different failure types and failure scenarios.
