SBIR Phase I: Autonomous Construction UAV Flight Controller

这个小企业创新研究（SBIR）第一阶段项目的更广泛的影响是显着降低环保，新家园建设的成本。目前，超过六分之一的美国家庭将一半以上的收入用于住房。该项目正在开发一种基于人工智能（AI）的自主重型无人机（UAV），能够用最便宜，最丰富的建筑材料-地球建造房屋。由于劳动力成本高，这种被称为土坯房的房屋历来都很昂贵。然而，人工智能控制的无人机的高精度和多功能性使自主建筑具有成本竞争力，并提供显著的额外好处，如能源效率，耐火性和隔音。这个小型企业创新研究（SBIR）第一阶段项目将制作一个自动重型无人机的原型，该无人机能够执行使用新型机械臂建造整体土坯结构的墙壁所需的单独任务。例如，形成土坯需要用铲子将仍然潮湿的墙壁推成所需的形状。这种力传递给无人机，无人机必须产生一个大小相等但方向相反的力来保持稳定。目前无人机飞行控制器无法在保持稳定飞行的同时处理这些力。该公司将使用深度强化学习来训练飞行控制器，使其能够在保持稳定飞行的同时处理这些力和相关力。该奖项反映了NSF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 of this Small Business Innovation Research (SBIR) Phase I project is to significantly decrease the cost of environmentally friendly, new home construction. Currently, more than 1/6 of American households spend over half of their income on housing. This project is developing an artificial intelligence (AI)-based autonomous heavy-lift unmanned aerial vehicle (UAV) capable of building homes out of the cheapest, most abundant building material, earth. Such homes, referred to as adobe, are historically expensive due to high labor costs. However, the hhigh precision and versatility of AI-controlled UAVs enable autonomous construction that is cost-competitive and offers significant additional benefits, such as energy efficiency, fire resistance, and soundproofing. This Small Business Innovation Research (SBIR) Phase I project will prototype an autonomous heavy-lift UAV capable of performing the individual tasks necessary to build the walls of a monolithic adobe structure with a novel robotic arm. For example, forming the adobe requires pushing a still-wet wall into the desired shape with a trowel. This force transfers to the UAV which must generate an equal-but-opposite force to maintain stability. No current UAV flight controller can handle these forces while maintaining stable flight. The company will use deep reinforcement learning to train a flight controller that can handle these and related forces while remaining in stable flight.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.