A deep learning based automatic surface segmentation algorithm for painting large-size aircraft with 6-DOF robot

Wang, Guolei; Xia, Hua; Xu, Jing; Song, Lei; Chen, Ken

doi:10.1108/aa-03-2019-0037

Cited by 9 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Owing to its high measurement efficiency and noncontact metrology, 3 D scanning has been successfully applied in a wide range of applications, such as robotic bin-picking, localization and automatic assembly (Zhang et al , 2019; Xu et al , 2020; Wang et al , 2020; Lin and Wang, 2021). In these applications, pose estimation plays an important role in the localization stage for the target work-pieces.…”

Section: Introductionmentioning

confidence: 99%

Robust pose estimation for ship block assembly feature based on large-scale scanning

Tang

Chen

Wang

et al. 2023

RIA

View full text Add to dashboard Cite

Purpose Hull block assembly is a vital task in ship construction. It is necessary to obtain the actual poses of the assembly features to guide further block alignment. Traditional methods use single-point measurement, which is time-consuming and may lead to loss of key information. Thus, large-scale scanning is introduced for data acquisition, and this paper aims to provide a precise and robust method for retrieving poses based on point set registration. Design/methodology/approach The main problem of point registration is to find the correct transformation between the model and the scene. In this paper, a vote framework based on a new point pair feature is used to calculate the transformation. First, a special edge indicator for multiplate objects is proposed to determine the edges. Subsequently, pair features with an edge description are noted for every point. Finally, a voting scheme based on agglomerative clustering is implemented to determine the optimal transformation. Findings The proposed method not only improves registration efficiency but also maintains high accuracy compared to several commonly used approaches. In particular, for objects composed of plates, the results of pose estimation are more promising because of the compact pair feature. The multiple ship longitudinal localization experiment validates the effectiveness in real scan applications. Originality/value The proposed edge description performs a better detection for the edges of multiplate objects. The pair feature incorporating the edge indicator is more discriminative than the original template, resulting in better robustness to outliers, noise and occlusions.

show abstract

Section: Introductionmentioning

confidence: 99%

Robust pose estimation for ship block assembly feature based on large-scale scanning

Tang

Chen

Wang

et al. 2023

RIA

View full text Add to dashboard Cite

show abstract

“…Over the recent years, several studies have focused on the engineering applications of artificial intelligence: Wang et al applied deep learning method to estimate the grasping pose of SCARA robot (Wang et al , 2020); Feng et al used deep neural network to establish a welding inspection framework using multisource sensing images (Feng et al , 2020). Wang et al developed a deep-learning-based automatic surface segmentation algorithm for painting large aircraft with robots (Wang et al , 2019). The above studies provided strong solutions to the existing problems in the visual guidance of robots, thereby boosting its industrial applications.…”

Section: Introductionmentioning

confidence: 99%

A novel robotic 6DOF pose measurement strategy for large-size casts based on stereo vision

Wan

Liu

et al. 2022

View full text Add to dashboard Cite

Purpose This paper aims to study six degrees-of-freedom (6DOF) pose measurement of reflective metal casts by machine vision, analyze the problems existing in the positioning of metal casts by stereo vision sensor in unstructured environment and put forward the visual positioning and grasping strategy that can be used in industrial robot cell. Design/methodology/approach A multikeypoints detection network Binocular Attention Hourglass Net is constructed, which can complete the two-dimensional positioning of the left and right cameras of the stereo vision system at the same time and provide reconstruction information for three-dimensional pose measurement. Generate adversarial networks is introduced to enhance the image of local feature area of object surface, and the three-dimensional pose measurement of object is completed by combining RANSAC ellipse fitting algorithm and triangulation method. Findings The proposed method realizes the high-precision 6DOF positioning and grasping of reflective metal casts by industrial robots; it has been applied in many fields and solves the problem of difficult visual measurement of reflective casts. The experimental results show that the system exhibits superior recognition performance, which meets the requirements of the grasping task. Research limitations/implications Because of the chosen research approach, the research results may lack generalizability. The proposed method is more suitable for objects with plane positioning features. Originality/value This paper realizes the 6DOF pose measurement of reflective casts by vision system, and solves the problem of positioning and grasping such objects by industrial robot.

show abstract

“…Considering the large-size, complex-shaped and thin-walled workpieces, in this application, the robot manufacturing system is more suitable than computer numerical control machine tools because of the high flexibility and broad working range (Gao et al , 2016; Pan and Zhang, 2008). At the same time, because of these characteristics, robotic systems are also widely used in other areas of the aerospace applications, such as the painting of large aircraft (Wang et al , 2019) and on-orbit servicing missions (Liu et al , 2019). Although there are already some robot chamfering tools and strategies in existing research studies, these methods can rarely be applied due to the difficulties of processing special-shaped thin-walled parts.…”

Section: Introductionmentioning

confidence: 99%

A robot chamfering system for special-shaped and thin-walled workpieces

et al. 2021

View full text Add to dashboard Cite

Purpose This paper aims to propose a robotic automation system for processing special-shaped thin-walled workpieces, which includes a measurement part and a processing part. Design/methodology/approach In the measurement part, to efficiently and accurately realize the three-dimensional camera hand-eye calibration based on a large amount of measurement data, this paper improves the traditional probabilistic method. To solve the problem of time-consuming in the extraction of point cloud features, this paper proposes a point cloud feature extraction method based on seed points. In the processing part, the authors design a new type of chamfering tool. During the process, the robot adopts admittance control to perform compensation according to the feedback of four sensors mounted on the tool. Findings Experiments show that the proposed system can make the tool smoothly fit the chamfered edge during processing and the machined chamfer meets the processing requirements of 0.5 × 0.5 to 0.9 × 0.9 mm2. Practical implications The proposed design and approach can be applied on many types of special-shaped thin-walled parts. This will give a new solution for the automation integration problem in aerospace manufacturing. Originality/value A novel robotic automation system for processing special-shaped thin-walled workpieces is proposed and a new type of chamfering tool is designed. Furthermore, a more accurate probabilistic hand-eye calibration method and a more efficient point cloud extraction method are proposed, which are suitable for this system when comparing with the traditional methods.

show abstract

A deep learning based automatic surface segmentation algorithm for painting large-size aircraft with 6-DOF robot

Cited by 9 publications

References 15 publications

Robust pose estimation for ship block assembly feature based on large-scale scanning

Robust pose estimation for ship block assembly feature based on large-scale scanning

A novel robotic 6DOF pose measurement strategy for large-size casts based on stereo vision

A robot chamfering system for special-shaped and thin-walled workpieces

Contact Info

Product

Resources

About