NRI: FND: Assistive Child-Robot Interventions for Infants with Motor Disabilities

这个国家机器人计划（NRI 2.0）项目将对新型机器人介导的物理治疗干预措施进行基础研究，以鼓励发育迟缓婴儿期望的运动行为。在美国，大约7%的儿童经历了影响感觉运动、社交和认知功能的发育障碍。由于这些功能是密切相关的，儿童可以从早期运动干预中广泛受益，例如体重支持运动，旨在鼓励运动探索和实践。该项目将采用迭代设计技术来开发并测试一种智能移动机器人，该机器人能够学习如何最好地引发体重支持婴儿所需的运动行为。该项目将通过开发新的硬件和算法来促进科学进步和国民健康，这将提高辅助机器人对发育迟缓婴儿进行个性化治疗干预的能力。其他更广泛的影响包括在科学、技术、工程和数学领域吸引妇女和代表性不足的少数民族的教育和外联活动。该项目将开发和评估一种新型的移动机器人系统，该系统可使发育迟缓的婴儿参与游戏活动，从而促进所需的感觉运动功能。提出的工作分为三个“重点”：(1)迭代设计一个合适的、健壮的协作机器人；(2)建立一个自适应的“行为规划”框架，用于实施智能机器人介导的参与策略；(3)进行人体受试者实验，以评估该框架和评估机器人系统协助物理治疗干预的潜力。这个项目将产生算法，可以个性化的感觉运动的相互作用，以个别婴儿的需要。该项目将比较在有和没有辅助机器人的情况下参与运动干预的儿童的身体和社会行为。该项目将为未来的随机对照试验和机器人系统在自然环境（如诊所和家庭）中的长期研究提供硬件和计算框架。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 National Robotics Initiative (NRI 2.0) project will conduct fundamental research on novel robot-mediated physical therapy interventions encouraging desired motor behaviors in infants with developmental delays. About 7% of children in the US experience developmental disabilities that impact sensorimotor, social, and cognitive functioning. Because these functions are closely interrelated, children may benefit broadly from early motion interventions, such as body-weight-supported locomotion, designed to encourage motor exploration and practice. This project will employ iterative design techniques to develop and then test an intelligent mobile robot capable of learning how best to elicit desired motor behaviors in body-weight-supported infants. The project will advance the progress of science and advance the national health by developing novel hardware and algorithms that will advance the ability of assistive robots to personalize therapeutic interventions for infants with developmental delays. Additional broader impacts include education and outreach activities engaging women and underrepresented minorities in Science, Technology, Engineering, and Mathematics. This project will develop and assess a novel mobile robot system that engages infants with developmental delays in play activities that encourage desired sensorimotor functioning. The proposed work is organized into three "thrusts": (1) iteratively designing an appropriate and robust co-robot, (2) establishing an adaptive "behavior-planning" framework for implementing intelligent robot-mediated engagement strategies, and (3) performing human subject experiments to evaluate the framework and assess the robotic system’s potential to assist in physical therapy interventions. This project will yield algorithms that can personalize sensorimotor interactions to individual infant needs. The project will compare the physical and social behaviors of children participating in motor interventions with and without an assistive robot. This project will yield the hardware and computational framework for future randomized controlled trials and long-term studies of the robotic system in natural environments of interest, such as in clinics and homes.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.