BRITE Pivot: Towards Intelligent Health Monitoring, Inspection, and Reconnaissance of Critical Infrastructure using Autonomous Robots

This Boosting Research Ideas for Transformative and Equitable Advances in Engineering (BRITE) project will advance the ability of autonomous machines to inspect critical infrastructure with minimal human assistance through novel research in areas of machine learning, optimization, and computer vision. This objective will be achieved through a mentored and rigorous program comprised of classroom learning and focused research tasks intended to advance the ability for a small unmanned aerial vehicle (UAV or “drone”) to remotely and autonomously inspect a new, unknown, and cluttered infrastructure environment to find a potential threat using computer vision.

By educating and training a group of civil engineering researchers in cutting-edge theory and methods of machine learning, optimization, and computer vision, this project will enable future research in a wide range of exciting and societally transformative topics related to autonomous infrastructure and smart cities.

Without autonomous inspection, monitoring, and reconnaissance solutions, engineers are bottlenecked by humans in the loop. This research addresses the critical gap by exploring means for aerial robots to autonomously navigate in, model, and inspect cluttered urban environments. Computer vision, machine learning, and artificial intelligence will be used to improve reconnaissance of infrastructure before and after natural and/or man-made hazards.

The potential for machines to autonomously and intelligently contribute to the safety and functionality of our society will not only improve the economics of monitoring society’s infrastructure, but it will also improve the quality of life for its residents by helping to maintain a more functional and safe society.

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.