Search Results (25)

This paper presents an intelligent robotic system for in-pipe inspection that integrates a novel mechanical design, deep learning-based defect detection, and high-fidelity simulation for real-time validation. Unlike existing solutions, the proposed system combines a Mecanum wheel-based mobile platform with a modular arm and advanced pan-tilt camera, enabling navigation and inspection of pipes ranging from 100 mm to 500 mm in diameter. A comprehensive dataset of 53,486 images, including 27,000 annotated defect instances across six critical classes, was used to train a YOLOv11-based detection framework. The model achieved high accuracy with a precision of 0.9, recall of 0.8, mAP@0.5 of 0.9, and mAP@0.5:0.95 of 0.6, outperforming previous YOLO versions, SSD, RCNN, and DinoV2 by 26% in mAP. Real-time testing on a Raspberry Pi Camera 3 Wide IR module validated the robust detection under realistic conditions. This work contributes a mechanically adaptable robot, an optimized deep learning inspection framework, and an integrated simulation-to-deployment workflow, providing a scalable and autonomous solution for industrial pipeline inspection. Full article

Pipeline transportation of oil and gas is widespread. To improve inspection and maintenance, a pipeline inspection robot was developed in our study. We employed a threaded nut mechanism with a preload spring and diameter-adjustment methods. A torque output formula was derived. At maximum (340 mm) and minimum (260 mm) diameters, angles α and β were given. A pipeline obstacle model was established with a maximum crossing height of 7.5 mm. Simulation and experiments showed that the robot could cross up to 7.8 mm, performed well, and operated stably, which met our expectations. Full article

Miniature robots in small-diameter pipelines require efficient and reliable environmental perception for autonomous navigation. In this paper, a tiny machine learning (TinyML)-based resource-efficient pipe feature recognition method is proposed for miniature robots to identify key pipeline features such as elbows, joints, and turns. The method leverages a custom five-layer convolutional neural network (CNN) optimized for deployment on a robot with limited computational and memory resources. Trained on a custom dataset of 4629 images collected under diverse conditions, the model achieved an accuracy of 97.1%. With a peak RAM usage of 195.1 kB, flash usage of 427.9 kB, and an inference time of 1693 ms, the method demonstrates high computational efficiency while ensuring stable performance under challenging conditions through a sliding window smoothing strategy. These results highlight the feasibility of deploying advanced machine learning models on resource-constrained devices, providing a cost-effective solution for autonomous in-pipe exploration and inspection. Full article

The estimation of robot pose and pipe diameter is an essential task for reliable in-line inspection (ILI) operations and the accurate assessment of pipeline attributes. This paper addresses the problem of robot pose and pipe diameter estimation for natural gas pipelines based on 3D time-of-flight (ToF) sensors. To tackle this challenge, we model the problem as a non-linear least-squares optimization that fits 3D ToF sensor measurements in its local coordinates to an elliptic cylindrical model of the pipe inner surface. We identify and prove that the canonical ellipse-based estimation method (C-EPD), which uses a canonical residual function, suffers from bias in diameter estimation due to its asymmetry to depth errors. To overcome this limitation, we propose the robust and unbiased estimation of pose and diameter (RU-EPD) approach, which employs a novel error-based residual function. The proposed function is symmetric to depth errors, effectively reducing estimation bias. Extensive numerical simulations and prototype pipeline experiments demonstrate that RU-EPD outperforms C-EPD, achieving an at least six times lower estimation bias and a 2.5 times smaller estimation error range in pipe diameter and about a 2 times smaller estimation error range in pose estimation. Full article

Ondol is a heating system unique to Korean homes that increases indoor temperatures by supplying hot water through pipes embedded in floor slabs. Known for its comfort and sustained heating advantages, ondol has garnered international interest in countries requiring efficient heating solutions. Given the inherent challenges faced during installation and operation, timely inspection of ondol is crucial due to difficulties in detecting and locating defects in buried concrete pipes, often leading to costly rework and removal. However, specialized inspection systems tailored to ondol pipes remain underexplored. Therefore, this paper proposes a robotic inspection system capable of assessing the conditions of ondol pipelines. We analyze the characteristics of ondol piping to establish system requirements and develop a prototype of a compact capsule-shaped inspection robot tailored for ondol pipe inspection. Subsequent laboratory testing validates system performance and usability, confirming field applications through curvature maneuverability and image reception quality tests. This study aims to motivate advancements in ondol-specific system implementation and performance validation, potentially contributing to the smartification of ondol maintenance practices. Full article

This paper introduces an autonomous robot designed for in-pipe structural health monitoring of oil/gas pipelines. This system employs a 3D Optical Laser Scanning Technical Vision System (TVS) to continuously scan the internal surface of the pipeline. This paper elaborates on the mathematical methodology of 3D laser surface scanning based on dynamic triangulation. This paper presents the mathematical framework governing the combined kinematics of the Mobile Robot (MR) and TVS. It discusses the custom design of the MR, adjusting it to use of robustized mathematics, and incorporating a laser scanner produced using a 3D printer. Both experimental and theoretical approaches are utilized to illustrate the formation of point clouds during surface scanning. This paper details the application of the simple and robust mathematical algorithm RANSAC for the preliminary processing of the measured point clouds. Furthermore, it contributes two distinct and simplified criteria for detecting defects in pipelines, specifically tailored for computer processing. In conclusion, this paper assesses the effectiveness of the proposed mathematical and physical method through experimental tests conducted under varying light conditions. Full article

This paper describes the development of an in-pipe inspection robot system designed for large-diameter water pipes. The robot is equipped with a Magnetic Flux Leakage (MFL) sensor module. The robot system is intended for pipes with diameters ranging from 900 mm to 1200 mm. The structure of the in-pipe inspection robot consists of the front and rear driving parts, with the inspection module located centrally. The robot is powered by 22 motors, including eight wheels with motors positioned at both the bottom and the top for propulsion. To ensure that the robot’s center aligns with that of the pipeline during operation, lifting units have been incorporated. The robot is equipped with cameras and LiDAR sensors at the front and rear to monitor the internal environment of the pipeline. Pipeline inspection is conducted using the MFL inspection modules, and the robot’s driving mechanism is designed to execute spiral maneuvers while maintaining contact with the pipeline surface during rotation. The in-pipe inspection robot is configured with wireless communication modules and batteries, allowing for wireless operation. Following its development, the inspection robot underwent driving experiments in actual pipelines to validate its performance. The field test bed used for these experiments is approximately 1 km in length. Results from the driving experiments on the field test bed confirmed the robot’s ability to navigate various curvatures and obstacles within the pipeline. It is posited that the use of the developed in-pipe inspection robot can reduce economic costs and enhance the safety of inspectors when examining aging pipes. Full article

Soft fiber-reinforced actuators have demonstrated significant potential across various robotics applications. However, the actuation motion in these actuators is typically limited to a single type of motion behavior, such as bending, extending, and twisting. Additionally, a combination of bending with twisting and extending with twisting can occur in fiber-reinforced actuators. This paper presents two novel hybrid actuators in which shape memory alloy (SMA) wires are used as reinforcement for pneumatic actuation, and upon electrical activation, they create a twisting motion. As a result, the hybrid soft SMA-reinforced actuators can select between twisting and bending, as well as twisting and extending. In pneumatic mode, a bending angle of 40° and a longitudinal strain of 20% were achieved for the bending/twisting and extending/twisting actuators, respectively. When the SMA wires are electrically activated by the Joule effect, the actuators achieved more than 90% of the maximum twisting angle (24°) in almost 2 s. Passive recovery, facilitated by the elastic response of the soft chamber, took approximately 10 s. The double-helical reinforcement by SMA wires not only enables twisting in both directions but also serves as an active recovery mechanism to more rapidly return the finger to the initial position (within 2 s). The resulting pneumatic–electric-driven soft actuators enhance dexterity and versatility, making them suitable for applications in walking robots, in-pipe crawling robots, and in-hand manipulation. Full article

The in-pipe robot is the most commonly used technique in offshore pipelines. The use of rubber sealing discs is important for in-pipe robots to ensure that the robots are moved by fluid pressures inside offshore pipelines. This paper focuses on the measuring and modeling of the wax–oil gel-breaking process at the soft frictional area between sealing discs and the pipe wall. In this study, a detailed characterization of the gel-scraping process and in situ probing portable microscopy are performed. Two contributions are made in this study. First, a direct observation of wax–oil deposition breaking is employed to detect the minute changes at the in-pipe robot. Second, we find that a simple function is possible to describe the relationship between the wax contents and dewaxing efficiency, in which the debris material removal ratio (DRR) is discussed. Thus, the gel deposition-breaking phenomena are quite different under the influence of rubber sealing discs. This result is further confirmed by the real contact ratio measurements. It is important to research the sealing disc further and apply it more in the petroleum industry, especially in in-pipe robots for deepwater pipeline systems. Full article

Pipelines are embedded in industrial sites and residential environments, and maintaining these pipes is crucial to prevent leakage. Given that most pipelines are buried, the development of robots capable of exploring their interiors is essential. In this work, we introduce a novel in-pipe robot utilizing Continuously Variable Transmission (CVT) mechanisms for navigating various pipes, including vertical and curved pipes. The robot comprises one air motor, three CVT mechanisms, and six wheels at the end of six slider-crank mechanisms, including three active and three idler ones. The slider crank and spring mechanism generate a wall press force through the wheel to prevent slipping inside the pipe. This capability allows the robot to climb vertical pipes and adapt to various pipe diameters. Moreover, by combining CVT mechanisms, whose speed ratios between the driver and driven pulleys are passively adjusted by the position of the slider, the robot achieves independent and continuous speed control for each wheel. This enables it to navigate pipes with various geometries, such as straight–curved–straight pipes, using only one motor. Since active control of each wheel is not needed, the complexities of the robot controller can be significantly reduced. To validate the proposed mechanism, MATLAB simulations were conducted, and in-pipe driving experiments were executed. Both simulation and experimental results have shown that the robot can effectively navigate curved pipes with a maximum speed of 17.5 mm/s and a maximum traction force of 56.84 N. Full article

The peristaltic in-pipe robot incorporates multiple actuators, and achieving precise cooperative control among these actuators poses significant complexity. To address these issues, the Theory of Inventive Problem Solving (TRIZ) is applied to identify and resolve physical and technical conflicts in the creative design process of peristaltic in-pipe robots. By highlighting the insights on and technical guidance offered by TRIZ’s inventive principles, this paper examines the method for realizing a single-motor-driven peristaltic in-pipe robot from a transmission perspective. By employing a combination of connecting rods, cam mechanisms, and gear systems, a one-DOF peristaltic in-pipe robot was devised. Subsequently, a prototype was constructed, and successful bidirectional motion tests were conducted within pipes. The findings highlight the efficacy of the TRIZ-based design approach in innovatively designing one-DOF in-pipe robots and the unnecessary employment of complex multi-drive cooperative control in peristaltic in-pipe robots. Full article

Incidents to pipes cause damage in water distribution systems (WDS) and access to all parts of the WDS is a challenging task. In this paper, we propose an integrated wireless robotic system for in-pipe missions that includes an agile, maneuverable, and size-adaptable (9-in to 22-in) in-pipe robot, “SmartCrawler”, with 1.56 m/s maximum speed. We develop a two-phase motion control algorithm that enables reliable motion in straight and rotation in non-straight configurations of in-service WDS. We also propose a bi-directional wireless sensor module based on active radio frequency identification (RFID) working in 434 MHz carrier frequency and 120 kbps for up to 5 sensor measurements to enable wireless underground communication with the burial depth of 1.5 m. The integration of the proposed wireless sensor module and the two-phase motion controller demonstrates promising results for wireless control of the in-pipe robot and multi-parameter sensor transmission for in-pipe missions. Full article

The twisted bundled-tube locomotive device is an elongated soft robot that moves inside a pipe in a helical bending motion. This motion mimics the behavior of microorganisms called spirochetes. This device is inexpensive and easy to miniaturize because of its simple structure, which consists of three inflatable tubes twisted together. It can move in pipes of various diameters without a change in design. Therefore, it has a high capacity for water pipe inspection. However, it has not yet been shown to pass through step parts wherein the diameter of the pipes decreases. In this study, we developed a device that was deformed into a tapered shape by changing the pitch of the spirals at each location. The prototype device was able to move from a pipe with an inside diameter of 52.9 mm to a pipe with an inside diameter of 21.6 mm for horizontally fixed pipes, and from a pipe with an inside diameter of 41.6 mm to a pipe with an inside diameter of 21.6 mm for vertically fixed pipes. Full article

In-pipe inspection robots have proven useful in examining the inside of pipes without affecting their structure, therefore, the interest in researching these robots has constantly increased over time. There are many different types of inspection robots, but the most commonly used are the wall pressed type. This paper proposes a review of the wall pressed type inspection robots in terms of adapting mechanisms. By adapting mechanism is meant a simple linkage or a combination of linkages, with an active or passive force generation system used to adapt the robot to variations in pipe diameter. The characteristics of the different adaptation mechanisms are compared and analyzed regarding the type of linkages used, how the pressure force on the pipe wall is obtained, and the possibility of ensuring the movement through inclined or vertical pipes with elbows and branches. Full article

This paper aims to present the design and prototype of an inspection robot that can perform both horizontal and vertical locomotion in ferromagnetic pipelines. The proposed robot applies to a range from 5-inch (127 mm) diameter pipes to flat plates. The train-like robot is mainly composed of three sealed modules with omnidirectional driving wheels for longitudinal and transverse movements. Permanent magnets were designed to provide sufficient magnetic adhesion between the robot and the ferromagnetic surface of the pipes. The internal condition of the pipe can be monitored visually through cameras and sensors. Specific experimental conditions have been carried out to validate the robot’s capabilities, including maximum speed, payload capacity, and vertical climbing distance. The experimental results also show that the robot is capable of passing through a straight pipe and elbow fitting in both upward and downward directions. Full article