NRI: Large: Collaborative Research: Fast and Accurate Infrastructure Modeling and Inspection with Low-Flying Robots

该项目的目标是通过开发一种自主机器人检测助手，将人类判断与机器智能相结合，从而改变目前关键基础设施检测方法的效率、保真度和安全性。这项拟议的工作利用小型空中机器人，结合三维成像和最先进的规划、建模和分析技术，开发安全、高效、高精度的结构评估。拟议工作的关键主题是：(1)通过具有3D测绘能力的小型自主空中机器人对大型复杂结构进行快速基础设施建模和分析；(2)身临其境的检查和结构评估，将形状和外观结合成便于检查员进行结构健康评估的综合表示；(3)自适应飞行器运动计划，寻求学习人类检查员的经验，并作为自主检查助理提供便利。拟议的工作是探索人类在从部署飞行机器人到登记数据再到评估的整个周期中的作用。该项目将参与社区的成员聚集在一起，并正在开发课程，以吸引来自机器人和土木工程的本科生和研究生参与拟议的研究。

The goal of this project is to transform the efficiency, fidelity, and safety of current critical infrastructure inspection methods by combining human judgment with machine intelligence through the development of an autonomous robotic inspection assistant. The proposed work utilizes small aerial robots, coupled with three-dimensional imaging and the state-of-the-art in planning, modeling, and analysis to develop safe and efficient, high-precision assessment of structures. The key themes of the proposed work are: (1) rapid infrastructure modeling and analysis of large complex structures via a small autonomous aerial robot with 3D mapping capabilities; (2) immersive inspection and structural assessment to combine shape and appearance into an integrated representation amenable to structural health evaluation by an inspector; and (3) adaptive aerial vehicle motion plans that seek to learn from the experience of human inspectors and facilitate as autonomous inspection assistants. The proposed work is exploring the role of humans in the entire cycle from deployment of flying robots to registering data to the assessment. This project brings together members of participating communities and is developing curriculum to engage undergraduate and graduate students from robotics and civil engineering in the proposed research.