FW-HTF-RL: Personalized Virtual Job Assistants to Prepare Individuals with Neurodevelopmental Disabilities for Entry Level IT Jobs

在美国，大约4%的儿童和年轻人被诊断为神经发育障碍，其特征是运动功能、学习、语言和非语言交流受损等困难。受这些残疾影响的年轻人找到工作的可能性大大降低，如果他们被雇用，收入也会减少。该项目主要针对轻度至中度神经发育障碍的未来工作者。该项目的目标是获得科学理解和开发技术，以支持神经多样性个体在未来劳动力中的更大参与。该项目将重点关注入门级信息技术（IT）工作，因为：(1)对IT技能的需求正在增长，(2)神经多样性的个人通常具有许多IT工作所需的能力，(3)IT工作提供了定期和灵活工作时间的机会，这对这类工人很重要。该项目的成果将是一个支持人工智能（AI）的软件平台，该平台将在未来的工人、雇主和中间工作教练之间建立协同作用，从而降低住宿成本和监督需求，并提高工人的生产力和工作满意度。该项目汇集了一个跨学科的研究团队，他们在数据科学、软件工程、人机交互、行为科学和特殊教育方面具有专业知识，他们将与职业项目和雇主合作，改变患有轻度至中度神经发育障碍的年轻人的就业现状。该项目将整合来自应用行为分析的科学知识和工作微任务中的最佳实践，以指导人工智能软件平台的开发，该平台可实施有效的工作定制、工作培训和在职支持策略。该平台将允许雇主和职业教练轻松地为他们神经多样性的员工设计和投入生产工作任务。该项目将解决重要的跨学科研究挑战：(a)哪些任务适合神经多样性工作者人群的哪一部分；(b)什么是基本的任务分析原则，使工作分解和连锁；(c)什么样的用户界面设计原则可以减少工作人员的认知负担；(d)工人行为和表现的哪些方面可以不引人注目地和合乎道德地观察，以及何时和如何提供支持；(e)工人、雇主、职业教练和研究人员之间如何更有效地沟通。该项目的成功转化为提高劳动力中神经多样性个体的自主权和包容性，减少职业培训和在职支持成本，改善公共卫生，提高经济生产力。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。

About 4% of children and young adults in the U.S. are diagnosed with neurodevelopmental disabilities, characterized by difficulties such as impaired motor function, learning, language, and non-verbal communication. Young adults affected by those disabilities are significantly less likely to find employment and have smaller earnings if they become employed. This project focuses on future workers with mild to moderate neurodevelopmental disabilities. The objective of this project is to gain scientific understanding and to develop technology to support stronger participation of neurodiverse individuals in a future workforce. The project will focus on entry-level information technology (IT) jobs because: (1) the demand for IT skills is growing, (2) neurodiverse individuals often have abilities desirable in many IT jobs, and (3) IT jobs provide opportunities to work regular and flexible hours, which is important for this population of workers. The outcome of the project will be an artificial intelligence (AI)-enabled software platform that creates a synergy between future workers, employers, and intermediate job coaches in a way that reduces accommodation costs and supervision needs, and increases worker productivity and job satisfaction. This project brings together an interdisciplinary team of researchers with expertise in data science, software engineering, human-computer interaction, behavioral science, and special education, who will collaborate with vocational programs and employers to transform the current state of employment for young adults with mild to moderate neurodevelopmental disabilities. This project will integrate scientific knowledge from applied behavior analysis and best practices in job micro-tasking to guide the development of an AI-enabled software platform that implements effective strategies for job customization, job training, and on-job support. The platform will allow employers and job coaches to easily design and put into production job tasks for their neurodiverse workers. This project will address important interdisciplinary research challenges: (a) what tasks are appropriate for what segment of the neurodiverse worker population; (b) what are the basic task analysis principles that enable job decomposition and chaining; (c) what user interface design principles can minimize cognitive burden of workers; (d) what aspects of worker behavior and performance can be observed unobtrusively and ethically, and when and how to provide support; and (e) how communication between workers, employers, job coaches, and researchers can be more effective. Success in this project translates to increased autonomy and inclusivity of neurodiverse individuals in the workforce, reduced job training and on-job support costs, improved public health, and a more productive economy.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.