Local Stochastic Prediction for UUV/USV Environmental Awareness

This project delivers a system to assess local uncertainties and track the evolution of the maritime environment around unmanned platforms at sea. The system uses Navy ocean forecasts for initial environmental guesses and outlooks and implements a Reduced Order Model (ROM) derived from Dynamically Orthogonal (DO) solutions to deliver a local uncertainty picture (for the next 24-48 hours). The ROM-DO solutions target the variables of relevance for UUV/SUV missions planning and execution. These solutions use a set of dynamic modes from which the reduced order estimates for the parameters and variables of interest are computed. They are then integrated with the local data, using a non-intrusive filter, to deliver an updated local forecast for the next 12-24 hours. These new fields are then used to compute marginal and conditional probability distributions of pre-loaded dynamical functions/modes that are sent to the forward deployed platforms. The probabilities are then integrated in dedicated payloads with platforms sensor data in real-time to locally reconstruct and update the most likely environments for the next 1-12 hours. These solutions can be used for path optimization and environmental adaptation/adaptive sampling.