Heave reduction of payload through crane control based on deep reinforcement learning using dual offshore cranes
Jun-Hyeok Bae, Ju-Hwan Cha, Sol Ha
Abstract
Abstract Offshore operation causes the dynamic motion of offshore cranes and payload by the ocean environment. The motion of the payload lowers the safety and efficiency of the work, which may increase the working time or cause accidents. Therefore, we design a control method for the crane using artificial intelligence to minimize the heave motion of the payload. Herein, reinforcement learning (RL), which calculates actions according to states, is applied. Furthermore, the deep deterministic policy gradient (DDPG) algorithm is used because the actions need to be determined in a continuous state. In the DDPG algorithm, the state is defined as the motion of the crane and speed of the wire rope, and the action is defined as the speed of the wire rope. In addition, the reward is calculated using the motion of the payload. In this study, the heave motion of the payload was reduced by developing an agent suitable for adjusting the length of the wire rope. The heave motion of the payload was compared in between the non-learning condition of the RL-based control and proportional integral differential (PID) control; and an average payload reduction rate of 30% was observed under RL-based control. The RL-based control performed better than the PID control under learned conditions.