The work aims to study the baggage stacking in the cargo hold under the background of air transportation, so as to maximize the utilization of cargo hold space. Considering practical constraints such as baggage posture, volume, weight, non-overlapping requirements, a model for aviation baggage storage was developed. Additionally, a hybrid genetic algorithm combining heuristic techniques with an improved genetic algorithm was designed. Firstly, an extreme points-based heuristic algorithm was employed to optimize the initial population and accelerate the population evolution speed to obtain high-quality initial loading schemes. Then, through the design of hybrid selection and mutation operators, the improved genetic algorithm was used to optimize the multiple feasible schemes, resulting in a loading layout scheme with maximum cargo space utilization rate while minimizing deviation of palletizing center of gravity. Finally, an experiment was conducted with real passenger baggage data collected from an airport self-service baggage check system to visualize the loading scheme. The baggage data in oversized, undersized, and mixed types were selected for experimental testing. The results demonstrated that under the conditions of satisfying various practical constraints of cargo holds, the average space utilization rate of the hybrid genetic algorithm reached 89.71%. This represents an improvement of 9.25% compared to existing cargo hold stacking algorithms, resulting in more scientific and reasonable stacking planning. The proposed algorithm can converge quickly and prevent local optima, showing better adaptability to irregular cargo hold spaces and heterogeneous luggage. It enables rapid and reasonable layout planning for cargo hold stacking.