Adaptive Sampling of Ocean Processes Using an AUV with a Gaussian Proxy Model
Gunhild Elisabeth Berget
We aim to exploit compact spatial models on board an autonomous underwater vehicle (AUV) for tracking of suspended material plumes. By explointing in-situ measurements from sensors, the AUV is able to assimilate and adapt the mission in real-time, exploiting all information available. The spatial model is built using Guassian process approximations and an objective function for path planning is suggested to maximize the value of the collected information. The model is tested in simulation as well as in a real application.