Past, present and future of robotic tunnel inspection

Montero, Roberto; Victores, Juan G.; Martínez, Santiago; Jardón, Alberto; Balaguer, Carlos

doi:10.1016/j.autcon.2015.02.003

Cited by 150 publications

(61 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Cracks are the main factor affecting the service life of a tunnel. Traditional monitoring methods rely on manual crack detection [3], but the process is subjective and operators face very difficult or even dangerous conditions, such as dust conditions, insufficient light or toxic exposure [4]. Another reason is that it's time-consuming and laborious to detect the cracks insufficient light or toxic exposure [4].…”

Section: Motivationmentioning

confidence: 99%

Automatic Tunnel Crack Detection Based on U-Net and a Convolutional Neural Network with Alternately Updated Clique

et al. 2020

Sensors

View full text Add to dashboard Cite

Regular crack inspection of tunnels is essential to guarantee their safe operation. At present, the manual detection method is time-consuming, subjective and even dangerous, while the automatic detection method is relatively inaccurate. Detecting tunnel cracks is a challenging task since cracks are tiny, and there are many noise patterns in the tunnel images. This study proposes a deep learning algorithm based on U-Net and a convolutional neural network with alternately updated clique (CliqueNet), called U-CliqueNet, to separate cracks from background in the tunnel images. A consumer-grade DSC-WX700 camera (SONY, Wuxi, China) was used to collect 200 original images, then cracks are manually marked and divided into sub-images with a resolution of 496 × 496 pixels. A total of 60,000 sub-images were obtained in the dataset of tunnel cracks, among which 50,000 were used for training and 10,000 were used for testing. The proposed framework conducted training and testing on this dataset, the mean pixel accuracy (MPA), mean intersection over union (MIoU), precision and F1-score are 92.25%, 86.96%, 86.32% and 83.40%, respectively. We compared the U-CliqueNet with fully convolutional networks (FCN), U-net, Encoder–decoder network (SegNet) and the multi-scale fusion crack detection (MFCD) algorithm using hypothesis testing, and it’s proved that the MIoU predicted by U-CliqueNet was significantly higher than that of the other four algorithms. The area, length and mean width of cracks can be calculated, and the relative error between the detected mean crack width and the actual mean crack width ranges from −11.20% to 18.57%. The results show that this framework can be used for fast and accurate crack semantic segmentation of tunnel images.

show abstract

Section: Motivationmentioning

confidence: 99%

Automatic Tunnel Crack Detection Based on U-Net and a Convolutional Neural Network with Alternately Updated Clique

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The industrial manipulators are being used in some new scenarios, such as tile placement [5]. Meanwhile, there have been some work on building maintenance, and cleaning, such as for bridge maintenance [6], external wall maintenance, facade windows cleaning [7,8], tunnel inspection [9], additive fabrication [10], etc.…”

Section: Introductionmentioning

confidence: 99%

Toward a framework for robot-inclusive environments

Tan

Elara

Watanabe

2016

Automation in Construction

View full text Add to dashboard Cite

“…These trajectories are typically obtained by using optimization techniques or input shaping. This consists of a sequence of acceleration and deceleration pulses which are generated so that there is no residual swing [16]. However, given that the high requirement of anti-interference for an inspection robot working in a complex environment, those controller studies are open-loop, which is sensitive to external disturbances and parameter variations and, as a result, did not meet system requirements for this robot.…”

Section: Introductionmentioning

confidence: 99%

“…There are several types of robots that have been applied to tunnel inspection [7][8][9]11] Montero et al [16] surveyed most tunnel inspection robots. The main drawback is that the workers are required to be in the same location as the robot and a tunnel must be closed for inspection.…”

Section: Introductionmentioning

confidence: 99%

Hybrid velocity switching and fuzzy logic control scheme for cable tunnel inspection robot

Meng

et al. 2015

IFS

View full text Add to dashboard Cite

Abstract. This paper describes a hybrid anti-swing control scheme of an inspection robot in tunnels for power transmission cables. The hybrid control scheme consists of velocity switching and fuzzy logic control, so that the robot can be operated smoothly without causing excessive swings in acceleration or deceleration motion. In order to ensure control system robustness for greatest movement in the tunnel, fuzzy logic control is used for horizontal anti-swing control. Velocity switching is adopted for incline anti-swing control, in order to obtain sufficient damping as well as a fast response. The stability of the hybrid system has been analyzed. The experimental results present the practicability and effectiveness of the proposed method.

show abstract

Past, present and future of robotic tunnel inspection

Cited by 150 publications

References 64 publications

Automatic Tunnel Crack Detection Based on U-Net and a Convolutional Neural Network with Alternately Updated Clique

Automatic Tunnel Crack Detection Based on U-Net and a Convolutional Neural Network with Alternately Updated Clique

Toward a framework for robot-inclusive environments

Hybrid velocity switching and fuzzy logic control scheme for cable tunnel inspection robot

Contact Info

Product

Resources

About