The laying of secondary cables is an important link in the secondary installation construction process of power transformer projects. At present, the laying of secondary cables is still mainly done manually, lacking effective mechanized construction means. Therefore, there are problems such as large workload, complex process, low efficiency, high labor demand and high cost. Based on the application of cable-pulling robot in the laying of secondary cables, aiming at the localization problem of four-wheel cable-pulling robot in cable laying, this paper proposes a localization scheme of correcting inertial navigation posture by observing ArUco marker fixed on the wall of cable trench with camera. This method is to solve the problem that localization methods based on vision and laser sensors and GPS-RTK can’t achieve high precision localization of cable-pulling robot in cable trench environment. And the method is to identify the ArUco markers pre-arranged on the wall of cable trench during the movement of four-wheel cable-pulling robot. And it will select specific frames based on its pose in the camera plane. The pose information of inertial navigation is modified by recognizing ArUco marker to realize the pose correction of four-wheel cable-pulling robot. The experimental results show that the method can enable the four-wheel cable-pulling robot to achieve real-time and accurate localization in the cable trench. This further enhances the intelligence