Automation of crane control for block lifting based on deep reinforcement learning

Abstract In shipyards, blocks are controlled by connecting the crane and block with wires during erection. During lifting, if a is not carefully controlled, it will cause damage. Block lifting using operation performed controlling number of wires, hooks, equalizers. Consequently, predicting stable difficult. this study, we proposed control method to determine static equilibrium. Initially, an algorithm for finding initial equilibrium state (IES algorithm) was proposed, followed deep reinforcement learning (DRL)-based lifting. The position, orientation, angular velocity block, hoisting speed were applied as DRL state. input calculated deriving wires. To verify method, comparative studies on application IES carried out, further movement compared. Conclusively, effectively increased safety.