SCH: INT: TAILORED: Training for Independent Living through Observant Robots and Design

该项目的目标是创造以人类为中心的机器人技术，提供个性化的神经康复，以支持患有轻度认知障碍的老年人。该项目探索这一研究领域的创新方法，并将为智能和互联健康做出以下贡献：创造新的方法，支持在现实世界环境中纵向的、个性化的机器人学习；开创提供和维持认知神经康复的新方法，这是目前已知的仅有的延长独立和减缓MCI导致的残疾发作的治疗方法之一；并为人-机器人交互(HRI)、衰老科学和行为科学领域贡献新方法，以支持与患有认知障碍的老年人、他们的照顾者和他们的提供者共同创造新技术和新的干预提供方法。利用技术为老年人提供认知支持和康复可能有助于数百万人保持或改善他们的功能和生活质量，并保持他们独立生活的能力。最终，这些改进可以减轻人类的巨大痛苦，并降低数百万人的医疗成本。该项目将为多个关键研究问题提供信息，包括：发现纵向偏好学习的新方法，特别是关于如何在概念漂移下的时变背景下在多模式数据集中使用；确定与MCI患者进行以社区为中心、以利益相关者为中心的研究的原则，特别注重设计复原力和自主性；发现通过机器人提供的认知训练的混合方法如何为认知功能提供信息；以及探索如何为MCI患者和其他人群设计可持续发展的干预措施。该项目团队还将让公众参与老年人和大学生之间的代际研究，通过赋予认知障碍老年人及其家庭成员在技术创造中的发言权来增强他们的能力，从计算机和行为科学中代表性较低的群体中招募研究学生，并通过出版物、陈述和带有模型、算法和评估指标的公开软件框架广泛传播研究。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The goal of this project is to create human-centered robotics technology to provide personalized neurorehabilitation to support older adults with mild cognitive impairment. The project investigates innovative approaches to this research area, and will make the following contributions to smart and connected health: create new approaches to support longitudinal, personalized robot learning in real-world environments; pioneer novel methods for delivering and sustaining cognitive neurorehabilitation, currently one of the only known treatments to prolong independence and slow the onset of disability caused by MCI; and contribute new methods to the fields of human-robot interaction (HRI), aging science, and behavioral science to support the co-creation of new technologies and new intervention delivery methods with older adults with cognitive impairments, their caregivers, and their providers. Harnessing technology to provide cognitive support and rehabilitation for older adults could potentially assist millions of people to maintain or improve their functioning and quality of life, and maintain their ability to live independently. Ultimately, these improvements could alleviate significant human suffering and lower healthcare costs for millions of people. This project will inform multiple key research questions including: uncovering new methods for longitudinal preference learning, particularly with regard to how time-varying contextual bandits under concept drift can be employed across multimodal datasets; identifying principles for engaging in community-focused, stakeholder-centered research with people with MCI, with a particular focus on designing for resilience and autonomy; discovering how hybrid approaches to cognitive training delivered via a robot can inform cognitive functioning; and exploring how to design interventions for sustainability, both for people with MCI and other populations. The project team will also engage the public in intergenerational research between older adults and college students, empower older adults with cognitive impairments and their family members by giving them a voice in technology creation, recruit research students from groups underrepresented in computing and behavioral science, and broadly disseminate the research via publications, representations, and publicly available software frameworks with models, algorithms, and evaluation metrics.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.