A wheeled-leg pipeline robot suitable for operation in small pipes is proposed to address the challenges of detecting the condition of pipelines, such as solution corrosion and crack defects, which cannot be conducted externally due to the pre-buried pipe system embedded in other structures. Inspired by existing pipeline robots, the proposed robot employs a mechanical structure with six wheeled legs arranged in an alternating pattern. To analyze the motion state of the pipeline robot turning in curved pipes, kinematic analysis based on geometry is conducted to figure out the kinematic characteristics of the robot navigating in curved pipes. The relationship between the motion trajectories of each contact wheel and the posture angle of the robot in the pipeline is the focal point. Additionally, a turning method preventing wheel slippage is proposed specifically for this type of robot. Finally, an experiment with the pipeline robot navigating in the curved pipeline is implemented and demonstrates successful passing through curved pipes with an inner diameter of 120 mm as well as a turning radius of 240 mm, with the effectiveness of the kinematic analysis validated.

A pipeline robot suitable for miniature pipeline detection, namely π-II, was proposed in this paper. It features six wheel-leg mobile mechanisms arranged in a staggered manner, with a monocular fisheye camera located at the center of the front end. The proposed robot can be used to capture images during detection in miniature pipes with an inner diameter of 120 mm. To efficiently identify the robot’s status within the pipeline, such as navigating in straight pipes, curved pipes, or T-shaped pipes, it is necessary to recognize and classify these specific pipeline landmarks accurately. For this purpose, the residual network model ResNet18 was employed to learn from the images of various pipeline landmarks captured by the fisheye camera. A detailed analysis of image characteristics of some common pipeline landmarks was provided, and a dataset of approximately 908 images was created in this paper. After modifying the outputs of the network model, the ResNet18 was trained according to the proposed datasets, and the final test results indicate that this modified network has a high accuracy rate in classifying various pipeline landmarks, demonstrating a promising application prospect of image detection technology based on deep learning in miniature pipelines.