Social Robots (SRs) are substantially becoming part of modern society, given their frequent use in many areas of application including education, communication, assistance, and entertainment. The main challenge in human–robot interaction is in achieving human-like and affective interaction between the two groups. This study is aimed at endowing SRs with the capability of assessing the emotional state of the interlocutor, by analyzing his/her psychophysiological signals. The methodology is focused on remote evaluations of the subject’s peripheral neuro-vegetative activity by means of thermal infrared imaging. The approach was developed and tested for a particularly challenging use case: the interaction between children and a commercial educational robot, Mio Amico Robot, produced by LiscianiGiochi©. The emotional state classified from the thermal signal analysis was compared to the emotional state recognized by a facial action coding system. The proposed approach was reliable and accurate and favored a personalized and improved interaction of children with SRs.

鉴于社交机器人（SR）在教育，通讯，帮助和娱乐等许多应用领域中的频繁使用，它们已实质上已成为现代社会的一部分。人机交互的主要挑战是实现两组之间类似人的情感互动。这项研究旨在通过分析社交者的心理生理信号，使他们具有评估对话者情绪状态的能力。该方法的重点是通过热红外成像对受试者的周围神经营养活动进行远程评估。该方法已针对特别具有挑战性的用例进行了开发和测试：儿童与LiscianiGiochi©生产的商业教育机器人Mio Amico Robot之间的交互。将根据热信号分析分类的情绪状态与面部动作编码系统识别的情绪状态进行比较。所提出的方法可靠，准确，并支持儿童与SR的个性化和改善的互动。