Control of a ROV carrying an object

Unoccupied Underwater Vehicles (UUVs) are growing in importance and capabilities. Here, the trajectory control of an UUV carrying an object is investigated, with the consequent changes in system dynamics. For the first time, an Adaptive Model Predictive Control (AMPC) scheme for UUVs is developed, which selects optimal actions at the start of every time step to minimise the trajectory tracking error and prevent excessive changes in the control action over a receding time horizon. Prediction error minimisation is used to identify the linear model of the UUV in real time. The performance of AMPC is compared with existing PID and sliding-mode control (SMC) strategies through simulations. The latter is improved to prevent integral wind-up. While SMC results in best tracking performance, it imposes a strong burden on the motors due to its bang-bang action selection. AMPC presents smoother changes in applied thrust, but higher tracking errors due to non-linear effects and inaccuracies in the on-line system identification process. PID presents best overall performance, but its behaviour is expected to degrade on an actual ROV application due to sensor noise. This study will contribute to the selection of a suitable control scheme for future UUVs performing maintenance tasks autonomously.