Here is the code for the MASCOT project. We are intersted in improving how we sample with AUVs. We utilise onboard statistical model to improve real time descicions on where and when to sample.
GOOGLE: Long-Horizon Informative Path Planning with Obstacles and Time Constraints
MAFIA: Spatially varying anisotropy for Gaussian random fields in three-dimensional space
GRANADE: Finding large salinity gradients in water fronts.
CALMSEA: Locating high densities of zooplankton or Chlorophyll A
The code is implemented on LAUVs from OceanScan and used in several field tests in Portugal and Norway.
Ge, Y., Olaisen, A.J.H., Eidsvik, J., Jain, R.P. and Johansen, T.A., (2022). Long-Horizon Informative Path Planning with Obstacles and Time Constraints. IFAC-PapersOnLine, 55(31), pp.124-129. Paper
Ge, Y., Eidsvik, J., and Mo-Bjørkelund, T. (2023), 3-D adaptive AUV sampling for classification of water masses. IEEE Journal of Oceanic Engineering. Paper
Berild M.O., and Fuglstad, G-A. (2023). Spatially varying anisotropy for Gaussian random fields in three-dimensional space. Spatial Statistics. Paper
Berild, M.O., Ge, Y., Eidsvik, J., Fuglstad, G.A. and Ellingsen, I. (2024). Efficient 3D real-time adaptive AUV sampling of a river plume front. Frontiers in Marine Science. Paper
