Cargo hold clearing operation is a crucial part of the bulk carrier discharge process. Traditionally, this task is performed using manually operated clearing machines to gather residual cargo for removal by grabs. However, this method is both inefficient and risky. This paper introduces an improved hybrid A* algorithm for full-coverage path planning in cargo hold clearing robots, establishing a foundation stacking of material for autonomous operations. First, a genetic algorithm-based approach is proposed to optimize the distribution and location of material piling spots for the robots. This method creates a detailed cargo hold environment model and determines the optimal placement of material piling spots using genetic algorithms. Second, an improved hybrid A* path planning algorithm is presented, tailored to the unique characteristics of cargo hold clearing operation. This algorithm considers the kinematic constraints of the robots, operational distance limits, and the boundaries of the clearing area, enabling efficient path planning for multiple material piling spots and achieving full coverage for the clearing robots. Experimental results show that this method achieves full coverage and efficient path planning within cargo holds. The genetic algorithm’s optimized material piling spot distribution increases bucket overlap efficiency by 365.8%, while the improved path planning algorithm boosts planning efficiency by 92.8%, ensuring the effectiveness of subsequent cargo hold clearing operations.