Deep Convolutional Neural Network Based Unmanned Surface Vehicle Maneuvering

The level of automated unmanned surface vehicle is always dependent on human interactions. An automated collision avoidance approach is proposed which is based on the visual system in order to improve it. Deep convolutional neural network (CNN) is a popular deep neural network for pattern recognition. Three types of encounter scenes are created and recorded which are used as the CNN training samples. The maneuver operations of these samples are conforming to the COLREGs rules. The CNN can predict the maneuvering operation according to the input scene as crewman after the training of CNN, and the central control system can take measures to avoid collision. Different simulations are taken to testify the validity of this approach.