Safe distance prediction for braking control of bridge cranes considering anti‐swing

Cranes are widely deployed for lifting and moving heavy objects in dynamic environments with human coexistence. Suddenly appeared workers, vehicles, robots can affect the safety of cranes. To avoid possible collisions, cranes must have prediction ability to know how dangerous situation is. In this paper, we address issues bridge based on its online physical states control model. Due swing payload, safe braking distance cannot be a constant value. Therefore, here propose model (MPC)-based anti-swing method non-zero initial states, where new reference trajectory cost function optimization proposed, such that proposed MPC crane follow achieve stable stop state anti-swing. Furthermore, an offline learning mechanism is introduced learn statistical between velocity achieved by using method. way, predict far would require safely without current velocity, which evaluate level obstacle. Experiments both simulated real demonstrate effective