CPS: Small: Long-term navigation of mobile CPS sensor nodes in dynamic fluid environment

Our oceans play a vital role in everything from coastal safety and national security to the economy and public health. Yet, large parts of the ocean remain difficult to explore and monitor. This project is focused on developing smarter and more reliable tools to help us better understand and navigate these vast underwater environments. Using new advances in robotics and artificial intelligence, the research team is working to improve small, cost-effective underwater robots that can travel long distances and operate on their own, even in areas where GPS and human control are unavailable. These mobile sensor platforms will be able to collect valuable information about the ocean in real time, adapt to changing conditions, and work together as a team — all without needing constant guidance. The project not only advances technology but also plays an important role in educating the next generation of scientists and engineers. The ability to monitor and survey oceans persistently and cost effectively on a large scale is of great significance to coastal safety, homeland security, national economy and public health. The proposed research addresses critical issues in transforming modern computing technologies for solving pressing problems of marine science. Recent decades marked a phenomenal transformation in our ocean exploration and perception approaches due to the progress in robotic computing platforms such as autonomous underwater vehicles (AUV). This research aims at enhancing the resilience and versatility of cyber-physical systems (CPS), consisting of mobile sensor platforms and ocean dynamics simulation, as our gateway to better explore and understand the harsh underwater environments. This project proposes research that will improve the long-term autonomy and intelligence of cost-effective mobile robots in previously under-explored ocean regions. Using Artificial Intelligence (AI) and Machine Learning (ML) techniques will enable mobile sensor networks with intelligent distributed sensing capabilities while ensuring their scalability and survivability within highly unpredictable dynamical environments. The developed strategies allow AUVs to localize themselves much more accurately in the oceans when GPS is not available. This project will also have a direct aim at training the next generation of engineers and computers scientists with expertise in naval architecture and marine sciences. In addition to the technical advances in CPS and AI used for ocean sampling, distributed sensing, and networking anticipated above, this project provides an application focus that will be of interest to researchers and students working in electrical, mechanical, and naval engineering, as well as computer, ocean, and biological sciences. 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.