In order to realize the parameterization and intellectualization of cabin layout, a multi-objective optimization model including the objective of logistics intensity between cabins, the objective of adjacent intensity and the objective of fixed position was established according to the characteristics of the optimization design of ship cabin layout. Based on the establishment of the mathematical model, the improved genetic algorithm based on the reverse learning optimization population generation method was used to solve the model. By expanding the search range of the solution, it can jump out of the local optimum and guide the population to find the global optimum. Finally, the simulation experiment was carried out by using the established optimization model and the improved genetic algorithm, and more reasonable results are obtained, which verify the feasibility and effectiveness of the proposed method.