Genetic trajectories control planning for teams of quasi-robot ships

This paper considers complex marine operations involving the coordinated motion of several ships. Each ship is controlled by an on-board computer, under captain supervision; so the ship is a quasi-robot ship. A computational procedure, able to embed a priori knowledge, was devised for planning of the ships motion control, to make them follow adequate trajectories. The main idea has been to mimic the typical maneuver when parking a car: turn the wheel to one side, and then to the other side; this may be seen as a partial bang-bang control strategy. In general, this type of maneuver do adapt to the control of non-holonomic vehicles, when a vehicle starts from a certain position and attitude and must arrive to another position and attitude. The paper introduces a genetic procedure for control planning using partial bang-bang control. A complete operation, the case of oil spill over confinement, is described, presenting results of the genetic optimization procedure.