CrowdAI announced today that it won an AFWERX Small Business Innovation and Research (SBIR) Phase II award from the U.S. Air Force (AF). The project will explore CrowdAI’s artificial intelligence (AI) capabilities to improve building maintenance at AF bases across the country. CrowdAI specializes in pairing deep learning and computer vision (CV)—the automated exploitation of imagery and video.
There are over fifty Air Force bases in the contiguous U.S. and even more overseas. With hundreds of structures on each base—offices, workshops, hangars, homes—keeping track of their state of repair in real-time is next to impossible. Currently, AF civil engineers, who are responsible for base upkeep, rely on manual surveying and reporting to understand the condition of each building, a slow and resource-intensive process. These surveys also create an enormous amount of data that is hard to digitize and track, such as written reports. However, with the explosive growth of remote imaging platforms, both government and commercial, AI-powered computer vision has the potential to transform this data collection, saving time and resources.
In 2019, CrowdAI worked with the Air Force Civil Engineer Center (AFCEC) to use its deep learning algorithms to analyze satellite imagery to detect damage to AF buildings in the U.S. as part of a corresponding Phase I SBIR award. The positive results of this test, as well as new availability of geospatial video, led CrowdAI to pursue the Phase II award to further develop this capability.
“We’re very excited to take our initial results to the next level,” Devaki Raj, CEO of CrowdAI, said of the project. “Assessing the current status of a building is just the first step: using AI to examine something like a roof, for example, the Air Force can start identifying problems before they even occur. Scaling preventative maintenance like this has the potential to save an enormous amount of time and resources.”
CrowdAI won the 2018 Hyperspace Challenge pitch competition, proposing their deep learning technology as a solution to this problem for AFCEC. This Phase II award will allow for rapid deployment and testing of CrowdAI’s solution by AF end-users.
Established in 2017 by the Secretary of the Air Force and reporting to the Vice Chief of Staff of the Air Force, AFWERX is a catalyst for agile Air Force engagement across industry, academia and non-traditional contributors to create transformative opportunities and foster an Air Force culture of innovation. The ultimate aim is to solve problems and enhance the effectiveness of the Air Force.
The Air Force Research Lab (AFRL) and AFWERX have partnered to streamline the SBIR process in an attempt to speed up the experience, broaden the pool of potential applicants, and decrease bureaucratic overhead. Beginning in SBIR 18.2, and now in 20.1, the Air Force has begun offering 'Special' SBIR topics that are faster, leaner and open to a broader range of innovations.
The Air Force Civil Engineer Center, located at Joint Base San Antonio-Lackland, Texas, is a 1,900-person primary subordinate unit of the Air Force Installation and Mission Support Center, Air Force Materiel Command. The center is responsible for providing responsive, flexible full-spectrum installation engineering services. The center's missions include facility investment planning, design and construction, operations support, real property management, energy support, environmental compliance and restoration, and audit assertions, acquisition and program management. Conducting operations at more than 75 locations worldwide, the center oversees the annual execution of more than $11 billion in contracts, manages $7 billion in housing and $5 billion in Enhanced Use Lease portfolios, and indirectly controls $49 billion in contract vehicles.