A flexible 3D vision system based on structured light for in-line product inspection

Skotheim, Øystein; Nygaard, Jens Olav; Thielemann, Jens T.; Vollset, Thor

doi:10.1117/12.766230

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome these limitations of visual perception, it is often combined with motion estimation (Klein and Drummond, 2004) or tactile sensing (Allen, 1988;Ilonen et al, 2013). Skotheim et al (2008) use functional feature detection for low-level industrial manipulation. Although the literature provides these powerful techniques, any single technique is insufficient to overcome the challenges of flexible factory environments.…”

Section: Visual Perception For Manipulationmentioning

confidence: 99%

Multi-scale assembly with robot teams

Dogar

Knepper

Spielberg

et al. 2015

The International Journal of Robotics Research

View full text Add to dashboard Cite

We present algorithms and experiments for multi-scale assembly of complex structures by multi-robot teams. We focus on tasks where successful completion requires multiple types of assembly operations with a range of precision requirements. We develop a hierarchical planning approach to multi-scale perception in support of multi-scale manipulation, in which the resolution of the perception operation is * Corresponding author; e-mail: mdogar@csail.mit.edu 1 The first three authors contributed equally to this paper. This paper is a revision of Dogar et al. (2014) matched with the required resolution for the manipulation operation. We demonstrate these techniques in the context of a multi-step task where robots assemble large box-like objects, inspired by the assembly of an airplane wing. The robots begin by transporting a wing panel, a coarse manipulation operation that requires a wide field of view, and gradually shift to narrower field of view but more accurate sensors for part alignment and fastener insertion. Within this framework we also provide for failure detection and recovery: upon losing track of a feature, the robots retract to using wider field of view systems to re-localize. Finally, we contribute collaborative manipulation algorithms for assembling complex large objects. First, the team of robots coordinates to transport large assembly parts which are too 2 heavy for a single robot to carry. Second, the fasteners and parts are co-localized for robust insertion and fastening. We implement these ideas using four KUKA youBot robots and present experiments where our robots successfully complete all 80 of the attempted fastener insertion operations.

show abstract

Section: Visual Perception For Manipulationmentioning

confidence: 99%

Multi-scale assembly with robot teams

Dogar

Knepper

Spielberg

et al. 2015

The International Journal of Robotics Research

View full text Add to dashboard Cite

show abstract

“…Some prior investigations into the practical scopes and accuracy of digitizers have been reported in the literature, in particular, investigations into the performance of a single digitizer through a measurement process. Valkenburg and McIvor, 25 Rocchini et al 26 and Skotheim et al 27 accomplished a measuring process on planar surfaces using a structured light system and maintained the average error of measurement as the result of study. Similarly, the accuracy of different laser systems is reported in the works of Thompson et al 28 and Son et al 29 Other researchers attempted to compare two or more different scanning systems, for example, Iuliano and Minetola, 30 where a standard structured light scanner with a laser scanner was compared.…”

Section: Introductionmentioning

confidence: 99%

An investigation on measurement accuracy of digitizing methods in turbine blade reverse engineering

Mahboubkhah

Aliakbari

Burvill

2016

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

Measurement and quality control of turbine blades is critical to the successful operation of power plants. It has a key role in manufacturing and reverse engineering. Novel technologies continue to be developed to measure parts with complex geometries, such as turbine blades. Digitizing techniques, using both contact and noncontact methods, are used. Selecting the most appropriate digitizing method for a turbine blade requires consideration of the measuring performance of the alternative methods, including criteria such as accuracy, speed and cost. This study seeks to evaluate the practical accuracy and efficiency of various contact and noncontact digitizing methods through measurement and associated quality control of a complex part, that is, a turbine blade airfoil. Four popular technologies, using distinct underlying measurement methods, were chosen to measure a Frame 5 gas turbine blade, namely, a touch trigger probe mounted on a Zeiss coordinate measuring machine, a touch scanning probe and a spot laser probe separately mounted on Renishaw coordinate measuring machine and a linear laser system from ZScanner. The measured point cloud resulting from each method was then used to reconstruct three-dimensional computer-aided design models of the blade. The accuracy of each measuring system was evaluated against the original blade. The evaluation incorporated a comparative study of design parameters derived from the point cloud and reconstructed surfaces associated with each measurement method. The maximum error of point clouds were 2123, 2530 and 2173 mm for the ZScanner linear laser, Renishaw spot laser and Renishaw touch scan, respectively. These measured errors indicated higher accuracy from linear laser method than spot laser scanning and touch scanning methods. Furthermore, the achieved standard deviations of 42, 170 and 269 mm for point clouds of ZScanner linear laser, Renishaw spot laser and Renishaw touch scan, respectively, showed that the manufacturer reported that information cannot be always reliable.

show abstract

“…Compared to the stereovision sensor, the structured light vision sensor is much lighter and smaller, has a lower cost and more flexibility, and avoids the socalled correspondence problem [4][5][6][7][8][9]. Since the early 1970s [10] there has been active research on shape reconstruction and object recognition by projecting structured light stripes onto objects, especially for flexible visual inspection systems guided by industrial robots [11,12]. A structured light vision sensor can inspect the spatial edge easily but not the spatial circle, because feature points on the spatial edge can be conveniently located on the structured light plane modulated by the measured surfaces, so their 3D coordinates can be inspected easily with the mathematical model of a structured light vision sensor.…”

Section: Introductionmentioning

confidence: 99%

A two-step method for spatial circle orientation with a structured light vision sensor and error analysis

Xue

2010

Meas. Sci. Technol.

View full text Add to dashboard Cite

A novel two-step method for spatial circle orientation with a structured light vision sensor is proposed for a 3D flexible visual inspection system guided by an industrial robot. Firstly the z coordinate of a spatial circle center is estimated, secondly the x and y coordinates are estimated with the center orientation relative to the camera optic center, and then its radius is computed. Simultaneously, the x, y and z coordinate orientation errors are analyzed in detail. It shows that the method is feasible and valid, and the orientation accuracy for the spatial circle exceeds 0.15 mm by experiment. It eliminates the bottleneck of the traditional orientation method with a stereovision sensor, and greatly expands the application of the structured light visual inspection system.

show abstract

A flexible 3D vision system based on structured light for in-line product inspection

Cited by 4 publications

References 0 publications

Multi-scale assembly with robot teams

Multi-scale assembly with robot teams

An investigation on measurement accuracy of digitizing methods in turbine blade reverse engineering

A two-step method for spatial circle orientation with a structured light vision sensor and error analysis

Contact Info

Product

Resources

About