Reinforcement Learning Allows Underwater Robots To Locate And Track Objects Underwater

A team of researchers from the Institut de Ciències del Mar (ICM-CSIC) in Barcelona, the Monterey Bay Aquarium Research Institute (MBARI) in California, the Universitat Politècnica de Catalunya (UPC) and the Universitat de Girona (UdG) have proven for the first time that reinforcement learning can be used to allow autonomous vehicles and underwater robots to locate and track marine objects and animals. This type of learning allows a neural network to be trained to optimize a specific task, which would be difficult to achieve otherwise. This will enable the study of ecological phenomena such as migration or movement of species in a more efficient way.