Design of in-pipe robot based on inertial positioning and visual detection

Song, Hua; Ge, Kunshan; Qu, Di; Wu, Huapu; Yang, Jing

doi:10.1177/1687814016667679

Cited by 21 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the robot moves in the curved pipe, the length and width of the robot must satisfy geometric conditions. 17 We found that the maximum length of the robot is related to the relative shape configurations, as indicated in Figure 17. We investigated four typical conditions, let R be the radius of the elbow curvature, D is the diameter of the pipe and d e be the span angle of the curve section.…”

Section: Posture B In the Elbowmentioning

confidence: 79%

Design and analysis of a novel active screw-drive pipe robot

Tang

Lyu

et al. 2018

Advances in Mechanical Engineering

View full text Add to dashboard Cite

This study proposes a novel active screw-drive in-pipe robot that can adapt the circular-type and square-type pipe structure. The pipe robot is composed of four driving units and a wall-pressing suspension mechanism. Each driving unit contains a motor, a transmission train, and an electromagnetic brake, which is for switching the motion transmission route. DC motors drive the helical wheels, and the incline angle of the helical wheels can be adjusted by using the electromagnetic brake. The wheels of the driving unit exhibit rolling and steering motion. Thus, the robot is capable of translation movements, rotation movements, and screw motions with respect to the axis of the pipe according to the different positions of the helical wheels. The robot can avoid obstacles by using the rotation and screw modes. Moreover, the wallpressing mechanism is analyzed and modified, and a criteria for entering a reduction pipe reducer are derived for the double scissor-like suspension mechanism. We also analyze the robot motion in curved pipes in two typical postures. The simulation experiments reveal the relationship between the translation and rotation motion of the robot and indicates that the steering angle of the wheels can be regarded as a regulator to adjust the movement speed of the robot aside from tuning the posture of the robot. Elbow experiments are conducted to verify the effectiveness of the motion strategy. The robot can be adapted for both circular and square tube pipes without any change in its structure due to the special configuration.

show abstract

Section: Posture B In the Elbowmentioning

confidence: 79%

Design and analysis of a novel active screw-drive pipe robot

Tang

Lyu

et al. 2018

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…This problem is not new and some solutions have been brought to an incipient market. Works as those in [1,2] propose the creation of a map of the pipe set navigating among it with odometry and inertial units [3]. Obstacle avoidance in a crowded 3D world of pipes becomes of great interest when planning a flight; in [4], some contributions are made in this direction although the accuracy of object is deficient to be a reliable technology.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Detection of Pipes in Industrial Environments

Guerra¹,

Palacín²,

Wang³

et al. 2020

Industrial Robotics - New Paradigms

View full text Add to dashboard Cite

Robust perception is generally produced through complex multimodal perception pipelines, but these kinds of methods are unsuitable for autonomous UAV deployment, given the restriction found on the platforms. This chapter describes developments and experimental results produced to develop new deep learning (DL) solutions for industrial perception problems. An earlier solution combining camera, LiDAR, GPS, and IMU sensors to produce high rate, accurate, robust detection, and positioning of pipes in industrial environments is to be replaced by a single camera computationally lightweight convolutional neural network (CNN) perception technique. In order to develop DL solutions, large image datasets with ground truth labels are required, so the previous multimodal technique is modified to be used to capture and label datasets. The labeling method developed automatically computes the labels when possible for the images captured with the UAV platform. To validate the automated dataset generator, a dataset is produced and used to train a lightweight AlexNet-based full convolutional network (FCN). To produce a comparison point, a weakened version of the multimodal approach-without using prior data-is evaluated with the same DL-based metrics.

show abstract

“…Through force analysis and calculation, its maximum climbing angle is larger than 35°. The robot has good passing ability through the pipelines with bends [20]. Obstacle avoidance is not considered in previous researches.…”

Section: Introductionmentioning

confidence: 99%

Design of a new steerable in-pipe inspection robot and its robust control in presence of pipeline flow

Tourajizadeh

Sedigh

Boomeri

et al. 2020

JMES

View full text Add to dashboard Cite

Robust multivariable control of an in-pipe inspection robot with variable pitch rate is performed in this paper which moves through the pipelines while fluid is flowing. Most of the traditional inpipe robots have two challenges which make difficulty for investigating the pipe line. The necessity of blocking the flow and difficulty toward bypassing the probable obstacles in the pipes. Here a new mechanism of inpipe robot is proposed which can bypass the obstacles as a result of its mechanism modification and also is able to work in presence of flow by the aid of its designed robust controlled. To meet this goal, the proper mechanism is designed and its related model is derived. Afterwards a nonlinear robust controller is designed and implemented on the proposed robot based on Sliding Mode Control (SMC). The efficiency of the designed robot for bypassing the obstacles and also the robustness of its corresponding controller in presence of flow are investigated by the aid of MATLAB simulation. These simulations are validated by modeling the system in ADAMS and comparing the response of the proposed SMC and Feedback Linearization (FL). It is proved that the designed robot is able to move with controllable velocity through full pipelines while the designed controller can successfully cancel the fluid flow disturbances with a good accuracy of order 10-2.

show abstract

Design of in-pipe robot based on inertial positioning and visual detection

Cited by 21 publications

References 25 publications

Design and analysis of a novel active screw-drive pipe robot

Design and analysis of a novel active screw-drive pipe robot

Deep Learning-Based Detection of Pipes in Industrial Environments

Design of a new steerable in-pipe inspection robot and its robust control in presence of pipeline flow

Contact Info

Product

Resources

About