SCC-CIVIC-FA Track A: Targeted Micro-retrofits based on Building Envelope Scans using Drones, GPR, and Deep Neural Networks

Addressing a critical issue in New York City, this project targets the impending shortage of building inspection staff and the rising labor costs, especially with the implementation of Local Law 97. Traditional data collection for roof moisture reports in the building science and roofing consultancy industry is time-consuming, costly, and poses safety risks. This project’s technology offers a transformative solution that is cost-effective, labor-efficient, non-invasive, and scalable. It enables building inspection practitioners to perform more inspections than traditional methods, significantly reducing time and cost. Partnering with roofing consultants, community solar organizations, local school boards, and the municipal government, this project is particularly beneficial for groups with limited funding and large building portfolios, aiding in devising cost-effective compliance plans for climate legislation like Local Law 97. Also, the social science arm of this project investigates the barriers to the adoption of this technology and provides strategies to overcome them. The efforts will be continued after the CIVIC project through an NYU-based startup focused on commercializing the technology developed and refined throughout the project. Overall, this project increases efficiency, reduces costs, and improves safety in the building inspection process, potentially impacting the industry significantly and contributing to the broader goal of improving building maintenance and energy efficiency all over the nation. This project focuses on the development and deployment of an autonomous robotic data collection platform equipped with advanced sensors, including ground penetrating radar, LiDAR, GPS, visual cameras, and thermal cameras. It also utilizes drones to capture thermal and RGB data of building envelopes. These technologies enable the detection of moisture, thermal anomalies, and other building envelope issues without invasive procedures, minimizing the need for physical visits by engineers. The collected data is sent to cloud-based servers, where AI-powered software analyzes the information using deep learning and robot perception techniques to generate detailed reports on the moisture levels and overall condition. Combining drone-based data collection, advanced sensor technologies, and AI analysis enhances the accuracy, efficiency, and comprehensiveness of building envelope inspections. This project's scope involves piloting the technology on large roofs with complex obstructions and obstacles, particularly in New York City. This real-world testing enables system refinement and optimization for different building types and contexts. By improving building inspections with such an integrated approach, this project improves the effectiveness, cost-efficiency, and safety of the process, addressing critical building envelope issues and supporting sustainable building practices. The CIVIC Innovation Challenge is a collaboration with Department of Energy, Department of Homeland Security, and the National Science Foundation. 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.