多方对话中人机感知机器人的多模态可解释性方法
A Multi-Modal Explainability Approach for Human-Aware Robots in Multi-Party Conversation
AI总结：
本文提出一种多方对话中基于注意力机制的可解释听话人估计模型，并将其集成于iCub机器人的认知架构中，通过实时人机交互验证与在线用户研究，提升了机器人的透明度、交互性能及人类信任度。
摘要：
听话人估计（理解某人正在对谁说话）是多方对话场景中人类活动识别的一项基本任务。具体而言，在人机交互领域，使社交机器人能够参与此类交互情境变得尤为关键。然而，它通常被实现为二元分类任务，限制了机器人估计自身是否被称呼的能力，这制约了其交互技能。为了使社交机器人获得人类的信任，展现出一定程度的透明度和可解释性同样重要。因此，可解释人工智能在当前的机器学习应用和模型中扮演着重要角色，除了优异的性能外，还能为其决策提供解释。在我们的工作中，我们a）提出了一种听话人估计模型，其性能较先前最先进水平有所提升；b）进一步修改该模型，以包含固有的、基于注意力机制的可解释模块；c）将可解释的听话人估计作为iCub机器人多方对话模块化认知架构的一部分予以实现；d）在多方人机交互中验证该可解释模型的实时性能；e）提出在上述架构中融入可解释性和透明度的几种方法；以及f）进行一项在线用户研究，以分析各种解释对人类参与者感知机器人的影响。
英文摘要：
The addressee estimation (understanding to whom somebody is talking) is a fundamental task for human activity recognition in multi-party conversation scenarios. Specifically, in the field of human-robot interaction, it becomes even more crucial to enable social robots to participate in such interactive contexts. However, it is usually implemented as a binary classification task, restricting the robot's capability to estimate whether it was addressed \review{or not, which} limits its interactive skills. For a social robot to gain the trust of humans, it is also important to manifest a certain level of transparency and explainability. Explainable artificial intelligence thus plays a significant role in the current machine learning applications and models, to provide explanations for their decisions besides excellent performance. In our work, we a) present an addressee estimation model with improved performance in comparison with the previous state-of-the-art; b) further modify this model to include inherently explainable attention-based segments; c) implement the explainable addressee estimation as part of a modular cognitive architecture for multi-party conversation in an iCub robot; d) validate the real-time performance of the explainable model in multi-party human-robot interaction; e) propose several ways to incorporate explainability and transparency in the aforementioned architecture; and f) perform an online user study to analyze the effect of various explanations on how human participants perceive the robot.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
