摘要
机器人和机器学习的新闻编辑每日新闻-详细的机器人数据-机器人已经呈现。根据NewsRx记者从意大利佛罗伦萨发回的新闻报道，研究表明：“参与的概念在人-机器人互动(HRI)领域被广泛采用，作为互动中的一种核心社会现象。尽管这个术语被广泛使用，但这个概念的含义仍然很模糊。”这项研究的财政支持来自Ministero Dell’Universit e Della R Icerca。我们的新闻编辑引用了佛洛尼斯大学的一句话：“一种常见的方法是通过自我报告和观察网格来评估它。而前者的解决方案存在时间差异问题，因为感知的参与度是在互动结束时评估的。”后一种解决方案可能会受到观察者的主观性的影响。从开发能够在交互过程中自主适应其BehAviors的社会智能机器人的设想出发，复制正确检测参与的能力是社会机器人界面临的一个挑战。本文系统地重新审视了参与的概念化，从工作开始，T Hat试图在涉及机器人和真实用户的交互中自动检测它（即，在线调查不包括在内。目标是描述最多的研究工作，并概述通常采用的定义（定义作者对该主题的观点）及其与用于评估的ME理论的联系（如果有）。该研究在2009年11月至2023年1月期间在TW O数据库（Web of Science and Scopus）中进行。共发现590篇文章通过对排除标准的准确定义,确定了HRI中与自动检测和评估相关最多的文献,最后对28篇文献进行了全面评价,分析表明,电子检测任务主要是作为一个二进制或多类分类问题来处理的。考虑用户行为线索和基于背景的特征，这些特征是从记录的数据中得出的。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Data detailed on Robotics - Androids h ave been presented. According to news reporting originating from Florence, Italy , by NewsRx correspondents, research stated, “The concept of engagement is widel y adopted in the human-robot interaction (HRI) field, as a core social phenomeno n in the interaction. Despite the wide usage of the term, the meaning of this co ncept is still characterized by great vagueness.” Financial support for this research came from Ministero dell’Universit e della R icerca. Our news editors obtained a quote from the research from the University of Flore nce, “A common approach is to evaluate it through self-reports and observational grids. While the former solution suffers from a time-discrepancy problem, since the perceived engagement is evaluated at the end of the interaction, the latter solution may be affected by the subjectivity of the observers. From the perspec tive of developing socially intelligent robots that autonomously adapt their beh aviors during the interaction, replicating the ability to properly detect engage ment represents a challenge in the social robotics community. This systematic re view investigates the conceptualization of engagement, starting with the works t hat attempted to automatically detect it in interactions involving robots and re al users (i.e., online surveys are excluded). The goal is to describe the most w orthwhile research efforts and to outline the commonly adopted definitions (whic h define the authors’ perspective on the topic) and their connection with the me thodology used for the assessment (if any). The research was conducted within tw o databases (Web of Science and Scopus) between November 2009 and January 2023. A total of 590 articles were found in the initial search. Thanks to an accurate definition of the exclusion criteria, the most relevant papers on automatic enga gement detection and assessment in HRI were identified. Finally, 28 papers were fully evaluated and included in this review. The analysis illustrates that the e ngagement detection task is mostly addressed as a binary or multi-class classifi cation problem, considering user behavioral cues and context-based features extr acted from recorded data.”
NETL
NSTL