HCC-Medium: Personalized Socially-Assistive Human-Robot Interaction: Applications to Autism Spectrum Disorder

机器人技术目前处于技术的前沿，具有公认的影响人类生活质量的潜力。为了应对日益增长的老年人和具有特殊认知和社会需求的人群对个性化一对一护理的巨大需求，必须在人-机器人交互(HRI)领域取得重大进展，以便将机器人技术引入人类日常生活的此类应用领域。这个跨学科项目确定了社会辅助机器人学中的一组特定的HRI研究问题，即研究能够通过社会而不是物理互动提供帮助的机器人系统。研究重点集中在两个关键问题上：(1)机器人的物理体现在交互中的作用；(2)使用富有表现力的具体化交流和用户建模来实现个性化的时间扩展的辅助交互。对社会交流异质性和缺陷挑战下的互动给予了具体考虑。基于多通道感知、具体化表达与交流和在线用户建模，开发了一种新型的辅助机器人控制体系结构，并在三种不同类型的社交辅助系统中实现。为了给这项研究提供一个现实的背景，我们对来自典型人群和患有自闭症谱系障碍(ASD)的儿童进行了实验测试和评估，ASD是一个已经被确定为易于接受技术，特别是机器人干预和治疗的障碍家族。这项研究的一个关键贡献在于统一和紧密集成的端到端方法，该方法基于假设驱动的实验数据，联合研究体现和多通道表达交流，以及开发和使用用于人机交互设计的新的信号处理和用户建模方法。该项目本质上是为了影响受自闭症谱系障碍影响的庞大且不断增长的人群。在将收集和分析的庞大而独特的数据语料库的支持下，预期的科学影响将远远超出新的见解，有助于更好地理解HRI的基本原理及其与不同用户群体的相关性，以及对患有自闭症儿童的社会化。除了基础研究，两个互补的教育推广计划扩大了工作的影响：(1)通过使用机器人教授STEM主题，专门针对特殊教育的新颖的K-12推广和教师培训计划；(2)本科生研究培训和从大学预科到本科生再到研究生的角色建模。教育计划与研究计划相吻合，使研究团队的所有参与者都参与到综合活动中来。

Robotics is currently at the forefront of technologies with recognized potential for impacting quality of human life. In response to the large need for personalized one-on-one care for the growing populations of elderly individuals and those with special cognitive and social needs throughout life, great strides must be made in the domain of human-robot interaction (HRI) in order to bring robotics into such application domains in human everyday life. This interdisciplinary project identifies a specific set of HRI research questions in socially assistive robotics, the study of robotic systems capable of providing help through social rather than physical interaction. The research focus is on two key issues: (1) the role of the robot's physical embodiment in the interaction; and (2) the use of expressive embodied communication and user modeling toward personalized time-extended assistive interaction. A specific consideration is given to interactions under the challenges of socio-communicative heterogeneity and deficits. A novel assistive robot control architecture is developed, based on multi-modal perception, embodied expression and communication, and on-line user modeling, implemented in three different types of real-world socially assistive systems. To give a realistic context to the research, the experimental testing and evaluation are performed with children drawn from a typical population and a population with Autism Spectrum Disorders (ASD), a family of disorders that have already been identified as amenable to technological, and in particular robotic, intervention and therapy. A key contribution of the research lies in the unified and tightly integrated end-to-end approach that jointly studies embodiment and multimodal expressive communication, grounded in data from hypothesis-driven experiments, and the development and use of novel signal processing and user modeling methods for human-machine interaction design. This project, by its very nature, aims to impact the large and growing population affected by Autism Spectrum Disorders. With the support of the large and unique corpus of data that will be collected and analyzed, the expected scientific impact will go well beyond novel insights toward a better understanding of the fundamentals of HRI and its relevance for diverse user populations and for socialization of children with ASD. In addition to the basic research, two complementary educational outreach programs broaden the impact of the work: (1) a novel K-12 outreach and teacher training program specifically aimed at special education through the use of robotics for teaching STEM topics; and (2) undergraduate research training and pipelined role-modeling from pre-university to undergraduate to graduate students. The education programs dovetail with the research plan, resulting in integrated activities involving all participants in the research team.