Abstract: The equipment of UHV converter station is complex, the electromagnetic environment is special, the construction period of the infrastructure stage is long, and there are many concealed engineering acceptance projects, especially in high-altitude areas, involving more underground, ground and high-altitude operations, and the efficiency of manual operation is greatly reduced. In view of the low efficiency and potential safety hazards of traditional manual inspection, this paper uses power robots to study the intelligent inspection path scheme to provide a new way to solve this problem, but path planning in complex environments is still a technical difficulty. In this paper, a method for the inspection path planning of electric power robots based on the improved bat algorithm is proposed, which dynamically optimizes the inspection path by establishing the underground, ground and high-altitude three-dimensional environment models and the characteristic databases of the three construction stages of civil engineering, electrical and commissioning. Simulation results show that the proposed method can effectively avoid obstacles, reduce energy consumption and improve efficiency, and improve the coverage efficiency of key equipment compared with bat algorithm, neural network, particle swarm and linear programming, etc.KG-0.5mm, which provides theoretical support for the intelligent inspection of UHV converter station.