This groundbreaking research was recently published in Science Robotics, a leading journal in the field of robotics. It focuses on the use of underwater robotics to gain valuable in-situ data about the ocean. The study uses reinforcement learning, a concept prevalently used in control and robotics, to teach underwater robots how to optimize their actions in real-time to achieve specific objectives. This research could pave the way for a more detailed understanding of marine ecological phenomena, such as the migration or movement patterns of various marine species.
