Collision Detection for Underwater ROV Manipulator Systems

Sivčev, Satja; Rossi, Matija; Coleman, Joseph; Omerdić, Edin; Dooly, Gerard; Toal, Daniel

doi:10.3390/s18041117

Cited by 32 publications

(24 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the structure parameters designed above, the performance parameters of the single-vane swing cylinder can be obtained through Eqs. (6)(7)(8)(9). Table 3 shows the performance parameters of the single-vane swing cylinder.…”

Section: Itemmentioning

confidence: 99%

“…Underwater hydraulic manipulators are used in subsea Intervention, Repair, and Maintenance (IRM) operations in offshore industries, including oil and gas, marine construction, marine science, naval defence, and Marine Renewable Energy (MRE) [6]. As they are being used in a wide range of applications, underwater hydraulic manipulators are designed for different purposes and can work at any ocean depth with the pressure compensator balancing the tank pressure with the ambient pressure [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DOREP: An Educational Experiment Platform for Robot Control Based on MATLAB and the Real-Time Controller

Liu

Han

et al. 2019

Intelligent Robotics and Applications

View full text Add to dashboard Cite

This paper presents the development of a full ocean depth masterslave hydraulic manipulator system for marine engineering and research in the harsh hadal environment. Three basic modules of the slave arm including a linear cylinder, a single-vane swing cylinder, and a new wrist joint are designed. The electronic system and software are developed then. Laboratory experiments on the single-vane swing cylinder and the new wrist joint were carried out to verify the performance of new joints. Additionally, a 11000 m pressure experiment is conducted, and the results demonstrate that the full ocean depth hydraulic manipulator system works well in the 11000 m environment.

show abstract

Section: Itemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

DOREP: An Educational Experiment Platform for Robot Control Based on MATLAB and the Real-Time Controller

Liu

Han

et al. 2019

Intelligent Robotics and Applications

View full text Add to dashboard Cite

show abstract

“…Meanwhile, in the area of industrial and daily application [ 11 ], the robot mechanism presents a promising prospect. A real-time collision detection algorithm for marine robotic manipulation was presented to be a useful pilot assisting tool for subsea intervention operations [ 12 ]. In addition, Leite et al proposed a new skill-based architecture for MR which is used to overcome the difficulties in current autonomous robot design [ 13 ] to improve robotic performance.…”

Section: Related Workmentioning

confidence: 99%

Pixel-Wise Crack Detection Using Deep Local Pattern Predictor for Robot Application

Wang

2018

Sensors

View full text Add to dashboard Cite

Robotic vision-based crack detection in concrete bridges is an essential task to preserve these assets and their safety. The conventional human visual inspection method is time consuming and cost inefficient. In this paper, we propose a robust algorithm to detect cracks in a pixel-wise manner from real concrete surface images. In practice, crack detection remains challenging in the following aspects: (1) detection performance is disturbed by noises and clutters of environment; and (2) the requirement of high pixel-wise accuracy is difficult to obtain. To address these limitations, three steps are considered in the proposed scheme. First, a local pattern predictor (LPP) is constructed using convolutional neural networks (CNN), which can extract discriminative features of images. Second, each pixel is efficiently classified into crack categories or non-crack categories by LPP, using as context a patch centered on the pixel. Lastly, the output of CNN—i.e., confidence map—is post-processed to obtain the crack areas. We evaluate the proposed algorithm on samples captured from several concrete bridges. The experimental results demonstrate the good performance of the proposed method.

show abstract

“…Recently, several works on remotely operated vehicles (ROVs) have been reported for applications in ocean research [1][2][3][4]. In particular, ROVs have been used for underwater intervention, repair, and maintenance operations in offshore industries, including oil and gas industries, marine structures, marine sciences, naval defense, marine renewable energy, and scientific purposes [5][6][7][8][9]. Within submarine applications, recognition tasks stand out; for example, in [10][11][12] ROVs are employed for tracking mines and are programmed to carry out high-risk tasks, executing algorithms related to prediction, diagnosis, and classification.…”

Section: Introductionmentioning

confidence: 99%

Design and Construction of an ROV for Underwater Exploration

Aguirre-Castro

Inzunza-González

García-Guerrero

et al. 2019

Sensors

View full text Add to dashboard Cite

The design of a remotely operated vehicle (ROV) with a size of 18.41 cm × 29.50 cm × 33.50 cm, and a weight of 15.64 kg, is introduced herein. The main goal is to capture underwater video by remote control communication in real time via Ethernet protocol. The ROV moves under the six brushless motors governed through a smart PID controller (Proportional + Integral + Derivative) and by using pulse-wide modulation with short pulses of 1 μs to improve the stability of the position in relation to the translational, ascent or descent, and rotational movements on three axes to capture images of 800 × 640 pixels on a video graphic array standard. The motion control, 3D position, temperature sensing, and video capture are performed at the same time, exploiting the four cores of the Raspberry Pi 3, using the threading library for parallel computing. In such a way, experimental results show that the video capture stage can process up to 42 frames per second on a Raspberry Pi 3. The remote control of the ROV is executed under a graphical user interface developed in Python, which is suitable for different operating systems, such as GNU/Linux, Windows, Android, and OS X. The proposed ROV can reach up to 100 m underwater, thus solving the issue of divers who can only reach 30 m depth. In addition, the proposed ROV can be useful in underwater applications such as surveillance, operations, maintenance, and measurement.

show abstract

Collision Detection for Underwater ROV Manipulator Systems

Cited by 32 publications

References 34 publications

DOREP: An Educational Experiment Platform for Robot Control Based on MATLAB and the Real-Time Controller

DOREP: An Educational Experiment Platform for Robot Control Based on MATLAB and the Real-Time Controller

Pixel-Wise Crack Detection Using Deep Local Pattern Predictor for Robot Application

Design and Construction of an ROV for Underwater Exploration

Contact Info

Product

Resources

About