This paper aims to present a method of combining artificial potential field with ant colony algorithm to solve the problems of slow convergence speed and easy to fall into local optimum in path planning of palletizing robot. Firstly, the initial pheromone was distributed unevenly according to the joint forces of different nodes in the artificial potential field, to solve the invalid path search caused by the lack of pheromone in the initial stage of ant colony algorithm. Secondly, the joint force of the robot hand in the next node was introduced in the design of heuristic function to solve the problem that the ant colony algorithm was easy to fall into local optimum. Finally, the strategy of pheromone updating was improved. After each iteration, the increment of pheromone was updated in proportion to the length of the search path, and the maximum and minimum values were set to solve the problem that the pheromone on the path was so large at the later stage of the iteration that the ant colony algorithm fell into the local optimum. The improved algorithm improved the convergence speed by about 51% and the shortest path by about 10%. Compared with other improved ant colony algorithm, it also improved the comprehensive performance to a certain extent. The improved ant colony algorithm converges faster and finds shorter optimal path.