SBIR Phase II: Intelligent Drone Ignitions To Manage Fires

小型企业创新研究(SBIR)第二阶段项目的更广泛影响/商业潜力将是通过提高安全性、降低成本和提高效率来改变消防员扑灭野火的方式。野火的数量和严重程度正在增加，造成数十亿美元的损失，并导致数千人失去家园和无数人死亡。今天，消防员无法在不将消防员置于危险之中的情况下执行遏制野火所需的背燃。该项目将通过提高无人机系统的智能和能力，产生直接解决消防员关键痛点的技术。这项研究将开发协调机器人组的算法、深度学习方法和开发新的数据集、可以预测火灾活动和计划任务的算法，以及自主健康监测方法。该项目将导致安全、快速、负担得起的火灾管理。这一小型企业创新研究(SBIR)第二阶段项目将有助于开发将改变消防管理的关键技术部分。更具体地说，拟议的工作侧重于将情报纳入火灾管理的下列关键技术挑战和活动：1)扩展到多架无人机智能串联作业，以及更大规模的无人机更快地覆盖复杂、大地形；2)转变火前和火后测绘过程，目前是一个人工过程，需要比实际灭火更多的时间；3)创建智能点火规划和自动传感能力，用于预测和考虑火灾活动，以提高安全性和效率；4)与客户进行Beta测试，以收集数据以学习算法，并在实地条件下验证研究。考虑到恶劣的火灾环境，这些活动首选的商用无人机的重量和功率限制，以及无人机空中导航和火灾管理这两个不同领域的集成，这些挑战尤其困难。这一奖项反映了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 broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project will be to transform how firefighters battle wildfires by improving safety, decreasing costs, and increasing effectiveness. Wildfires are increasing in number and severity, costing billions of dollars and resulting in thousands of lost homes and numerous deaths. Today, firefighters are unable to perform the backburns needed to contain wildfires without putting firefighters at risk. This project will result in technologies that directly address the critical pain points of firefighters by improving the intelligence and capabilities of drone systems. The research will develop algorithms for coordinating groups of robots, deep learning approaches and the development of novel datasets, algorithms that can predict fire activity and plan missions, and autonomous health monitoring approaches. This project will lead to safe, fast, affordable fire management. This Small Business Innovation Research (SBIR) Phase II project will enable the development of the critical pieces of the technology that will transform fire management. More specifically, the proposed work focuses on the following key technical challenges and activities to incorporate intelligence into fire management: 1) Scaling to multiple drones intelligently operating in tandem and larger drones to cover complex, large terrain faster; 2) Transformation of pre- and post-fire mapping, currently a manual process taking more time than actual firefighting; 3) Creation of intelligent ignition planning and automated sensing capabilities that predict and take into account fire activity to increase safety and efficiency; and 4) Beta tests with customers to collect data for learning algorithms and to validate the research under field conditions. These challenges are especially difficult given the harsh fire environment, the weight and power constraints of commercial drones preferred for these activities, and the integration of two distinct domains, drone aerial navigation and fire management.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.