In order to find the optimal path for the intelligent inspection robot, the traditional ant colony algorithm was improved. The A* algorithm was used to improve the ant’s path-finding rules, and multiple smooth iterations were performed on the found path, which filled the defects that the traditional A* algorithm easy to fall into a "trap". At the same time, the purpose of smoothing the path and shortening the distance was achieved, the pheromone processing method of ant colony was optimized, and the double pheromone strategy was introduced to get the optimal path. Compared with the traditional ant colony algorithm, the improved algorithm can avoid obstacles accurately, and has a faster and better ability to search for the optimal path.