CAREER: Next Generation Patient Simulators

据估计，在美国，每年有成千上万的人死于医疗事故，数十亿美元的损失。PI认为，减少此类错误发生率的一种方法是通过涉及人类患者模拟器（HPS）系统的教育。尽管可能是美国最常用的机器人，但一个关键的技术差距是，商用的HPS系统都没有表现出真实的面部表情、凝视或嘴部运动，尽管这些线索对医生如何评估和治疗病人至关重要。PI在这个项目中的目标是通过开发新的表达合成算法和社会控制方法来解决这个缺点，从而推进情感计算和人机交互领域。为此，PI将模拟3种病理特征的面部特征（中风、脑瘫和肌张力障碍，后者是一种神经系统疾病，其中躯干、肩膀和颈部的肌肉进入痉挛状态，从而使头部和四肢处于不自然的位置），以及2种情感状态（疼痛和困倦）。她将在一个新的HPS系统上综合这些面部特征，并为表情机器人的操作员创建一个共享社会控制模型，并评估它们对教育和任务结果的影响。更广泛的影响：这项研究将改变HPS技术的现状，使教育工作者能够运行目前商用技术无法实现的模拟，从而为医生、护士和战斗医务人员带来更现实的培训经验，最终改善医疗保健。它将创建中风、肌张力障碍和脑瘫的新面部模型，这可能会影响计算机视觉和生物识别等领域，同时也会增强我们对这些疾病的理解，并提供一种教育人们如何更好地与这些残疾患者互动和/或快速识别中风迹象的手段。PI还将为本科生开展大量指导活动，并为K-12学生开展拓展活动。

It is estimated that in the United States many thousands of people are killed each year and billions of dollars lost due to medical errors. The PI argues that one way to reduce the incidence of such errors is through education involving human patient simulator (HPS) systems. Although perhaps the most commonly used android robots in America, a critical technology gap is that none of the commercially available HPS systems exhibit realistic facial expressions, gaze, or mouth movements, despite the vital importance of these cues in how providers assess and treat patients. The PI's goal in this project is to address this shortcoming by developing novel expression synthesis algorithms and social control methods, thereby advancing the fields of affective computing and human-robot interaction. To these ends the PI will model facial features characteristic of 3 pathologies (stroke, cerebral palsy and dystonia, the latter being a neurological disorder in which the muscles of the trunk, shoulders, and neck go into spasm so that the head and limbs are held in unnatural positions), and 2 affective states (pain and drowsiness). She will synthesize these facial features on a new HPS system and create a model of shared social control for operators of expressive robots, and evaluate their impact on educational and task outcomes. Broader Impacts: This research will transform the state of the art in HPS technology by enabling educators to run simulations currently impossible with commercially available technology, thereby leading to more realistic training experiences for doctors, nurses, and combat medics, which will ultimately improve healthcare. It will create new facial models of stroke, dystonia and cerebral palsy, which may impact fields such as computer vision and biometrics while also enhancing our understanding of these disorders and providing a means for educating people how to better interact with those suffering from these disabilities and/or to quickly recognize signs of stroke. The PI will also conduct substantial mentoring activities for undergraduates and outreach activities for K-12 students.