In collaboration with Texas AM (D. Shell) and ASU (S. Saripalli), we develop planning and control algorithms for autonomous underwater vehicles (AUVs) for adaptive four-dimensional sampling with the unique capability to capture data from coupled physical, chemical, and biological processes that occur across space and time-scales. The goal is to advance the state-of-the-art of robotic sampling systems by integrating dynamics-based control (e.g. for docking) with high-level planning and distributed optimization. The system will provide the individual investigator with an easily deployable personal platform for in situ “experiments” through automated sampling to assist in understanding the complex processes affecting water quality.
Upper-confidence bound (UCB) stochastic trajectory optimization for extrema search on a Gaussian Process environmental model