SCH: INT: Adaptive Partnership for the Robotic Treatment of Autism

该项目旨在研究自闭症谱系障碍（ASD）儿童之间的人机交互（HRI），以及能够评估和适应个性化治疗目标的工程、自主、面部表情、类人机器人。专门针对ASD的自适应伴侣机器人有可能彻底改变治疗方法，改善数百万美国人的生活和生产力。我们设想下一代ASD机器人将主要用于家庭，除了专门的治疗设施。设想中的机器人伴侣将充当治疗师、导师、被动观察者或主动学习同伴，从而补充重要个体的角色：父母、照顾者或教师。进一步探索机器人和儿童群体在治疗中的应用将丰富和深化我们的研究理解，并可能为自闭症患者及其家庭带来有意义的未来结果。所提出的相互作用代表了一个独特的机会，可以捕捉和客观地测量ASD儿童在多种情况下的自然行为，而不考虑年龄、语言或认知能力，因为它是基于运动和情绪反应。本项目的研究有几个新颖的组成部分，包括制定新的定量的、无创的标记物，最终整合到一个新的ASD量表中，用于诊断和治疗，该量表基于实时评估机器人与儿童互动过程中的运动和情绪。ASD严重程度量表将基于机器人在交互过程中评估的动态时间扭曲运动指标和连续情绪指标。该量表将被机器人使用，以个性化的方式适应每个孩子在一对一治疗过程中的治疗活动，以及几个孩子和机器人在小组治疗过程中的治疗活动。在行业合作伙伴的帮助下，我们将把产生的新的运动和认知行为嵌入到一个没有威胁的伙伴机器人中，这个机器人是专门为自闭症儿童设计的，具有友好的外观，行为转换和神经适应控制器。该机器人将能够收集大量数据，这些数据可能有助于阐明ASD人群的运动、感觉和情感大脑功能之间的独特联系。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

This project targets research on Human-Robot Interaction (HRI) between children with Autism Spectrum Disorder (ASD) and engineered, autonomous, facially-expressive, human-like robots that can assess and adapt to personalized therapeutic goals. Adaptive partner robots specifically targeting ASD hold the potential to revolutionize treatment and improve the lives and productivity of millions of Americans. We envision that the next generation ASD robot will be used primarily in the home, in addition to specialized treatment facilities. The envisioned robotic partners will serve as therapists, instructors, passive observers, or active learning peers, thus supplementing the role of important individuals: parents, caregivers, or teachers. The further exploration of the application of groups of robots and children in therapy will enrich and deepen our research understanding and could produce meaningful future outcomes for individuals with ASD and their families. The proposed interactions represent a unique opportunity to capture and objectively measure the natural behavior of ASD children in multiple contexts, irrespective of the age, language or cognitive ability, because it is based on both motor and emotional responses. The research undertaken in this project has several novel components, including formulating new quantitative, non-invasive markers, eventually integrated into a new ASD scale for diagnosis and treatment based on real-time evaluation of motions and emotions during interaction between robot and child. The ASD severity scale will be based on a dynamic time-warping motion metric and on a continuous emotion metric assessed by the robot during interaction. The scale will be used by the robot to adapt therapeutic activities in a personalized manner for each child in one-one one therapy sessions, and for several children and robots in group therapy sessions. With the help of industry partners, we will embed the resulting novel motor and cognitive behaviors into a nonthreatening, partner robot, specifically designed for children with ASD, endowed with a friendly appearance, behavioral switching and neuroadaptive controllers. The robot will be capable of collecting large amounts of data that may be useful to elucidate unique connections between the motor, sensory and emotional brain functions of the ASD population.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.