SBIR Phase I: Autonomous Living Assistant

这个小企业创新研究（SBIR）第一阶段项目的更广泛的影响/商业潜力是在住宅建筑中更广泛地采用自主技术。本研究建议评估使用先进的传感器技术和机器学习算法，使廉价的硬件基础设施能够自主控制室内空间的条件。这项技术很适合住宅建筑的容量。室内自动化的一个主要好处是深度节能。能源部估计，如果现有住宅建筑的能源消耗减少25%，全国总能源账单将减少5%。该项目评估的自动控制器有可能实现这一目标，为国家节省630亿美元，为地球减少2.84亿吨二氧化碳排放。除了能源效率外，拟议项目的相关社会效益还可能挽救生命。这些技术可能会在许多未受保护的住宅空间中刺激更高水平的安全保护。此外，跟踪居住者的习惯可以在紧急情况下向护理人员或家庭成员发出警报。这对于想要呆在自己家里的老年人来说是有益的。这项小型企业创新研究（SBIR）第一阶段项目将推进实现室内空间完全自主控制所需的科学知识。将评估在建筑物中使用先进感知传感器的情况。其丰富的数据流将用于开发室内空间自主控制的先进算法。传感技术和机器学习算法的进步将用于推动自主建筑系统的技术进化。将开发概念验证，以减轻在室内空间应用自主控制所带来的独特风险，特别是：实现高级感知、自编程性和可靠性。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。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is a wider adoption of autonomous technologies among residential buildings. This research proposes evaluating the use of advanced sensor technologies and machine learning algorithms to enable inexpensive hardware infrastructures to control the conditions in indoor space autonomously. This technology fits well within the capacity of residential buildings. One main benefit of indoor automation is deep energy savings. The Department of Energy estimates a 5% reduction of the country's total energy bill if existing residential buildings save 25% of their energy consumption. The autonomous controller evaluated in this project has the potential to reach this goal, saving the nation up to $63 billion and the planet 284 million metric tons of carbon dioxide emissions. Alongside energy efficiency, the associated societal benefits of the proposed project can potentially save lives. The technologies may spur a higher level of security protection among many unprotected residential spaces. Additionally, tracking occupants’ habits may enable alerts to caregivers or family members in critical emergency situations. This can be beneficial for the aging population that wants to stay within the comfort of their own home.This Small Business Innovation Research (SBIR) Phase I project will advance the scientific knowledge required to approach full autonomous control in indoor spaces. The use of advanced perception sensors in buildings will be evaluated. Their rich data stream will be utilized to develop advanced algorithms for autonomous control of indoor spaces. Advances in sensing technologies and machine learning algorithms will be used to instigate technological evolution in autonomous building systems. A proof of concept will be developed to mitigate the unique risks associated caused by applying autonomous control in indoor spaces, specifically: achieving advanced perception, self-programmability, and reliability.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.