20.000 fotografies sota el mar

Conèixer una posició sota l'aigua és una tasca molt complexa que no estava del tot resolta. Ara, investigadors de la Universitat de Girona han trobat una solució al problema a partir de la interpretació d'imatges del fons del mar. Aquesta tècnica, a més, ha obert noves possibilitats a biòlegs i geòlegs que estudien els fons marins

Autonomous underwater vehicle control using reinforcement learning policy search methods

Autonomous underwater vehicles (AUV) represent a challenging control problem with complex, noisy, dynamics. Nowadays, not only the continuous scientific advances in underwater robotics but the increasing number of subsea missions and its complexity ask for an automatization of submarine processes. This paper proposes a high-level control system for solving the action selection problem of an autonomous robot. The system is characterized by the use of reinforcement learning direct policy search methods (RLDPS) for learning the internal state/action mapping of some behaviors. We demonstrate its feasibility with simulated experiments using the model of our underwater robot URIS in a target following task