In the process of solving some complex multi-objective optimization problems, Pareto optimal solutions obtained
are vulnerable to the effects of design parameters or environment parameters perturbation. Therefore, the robust solution
is considered and an improved robust multi-objective optimization method is proposed. The method takes advantage of
the expectation and variance of fitness fuction value, which are combined effectively. Then, a specific multi-objective
evolutionary algorithm(MOEA) based on particle swarm optimization(PSO) is proposed. The simulation results show that,
more robust Pareto optimal solutions can be obtained by using the improved method.