In order to realize the optimization of the robot path under the dynamic complex environment, on the basis of the establishment of the grid map model, aiming at the disadvantage of the traditional genetic algorithm, one is to make the path more smooth by improving the fitness function, and the second is to combine the improved genetic algorithm with the Morphin algorithm, so that the robot can effectively avoid the obstacle in real time. The simulation results show that by combining the improved genetic algorithm and the Morphin algorithm, the robot can quickly and safely reach the target point along a short and smooth optimal path.