For the dynamic obstacles in the environment,how to use the global path planning algorithm to solve the optimal path of mobile robot,assuming that the motion range of the dynamic obstacle is known,so the hazard level is an interval number. Define a Pareto probability dominance formula,find out the dominant probability between different interval numbers,which can be used to determine which path is more secure. The traditional NSGA-Ⅱalgorithm is improved,and all solutions are classified into feasible and infeasible solutions according to the constraint function,the non feasible solution set is introduced to store the non feasible solution,guide feasible solutions to evolve better solutions. The environment model is established and simulated with MATLAB software. The simulation results show that for different obstacle environ-ment,this method can be used to plan a safe path,compared with the traditional algorithm,the improved algorithm in solving the dynamic obstacle environment for robot path planning problem is more feasible and effective.