Current substation inspection robot path planning algorithms are subject to problems of weak planning and adaptability. Based on the system structure of a UHV substation inspection robot, a path planning method for a substation is proposed, one which combines an ant colony optimization algorithm and an artificial potential field algorithm. The traditional one-way search of an ant colony algorithm is improved to two-way search, the synthetic direction of artificial potential field force is added to the heuristic factor, and the transition probability is improved. The grid method is used to construct the simulation environment of a UHV substation. This demonstrates the superiority of the proposed planning method. The simulation results show that the improved algorithm can significantly improve the number of iterations and the minimum path. The 20×20 grid environment converges to the optimal path of length 26 in 15 iterations, and the 30×30 grid environment converges to the optimal path of length 43 in 70 iterations. This work is supported by the Science and Technology Project of the Headquarters of State Grid Corporation of China (No. 521203190009).