Recent Trends in the Research of Industrial Robots and Future Outlook

Domae, Yukiyasu

doi:10.20965/jrm.2019.p0057

Cited by 18 publications

(8 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, relevant works in the precision agriculture field have been proposed in recent years to support autonomous navigation [ 4 , 5 ], harvesting [ 6 ], and spraying [ 7 ]. Intelligent DL-based behaviors are also desired for visual-based robotic surgery to detect and segment instruments [ 8 , 9 ], and in many industrial robotic tasks [ 10 , 11 ]. Nonetheless, to fill the gap between robot and human perception, multisensory approaches have recently been studied and evolved in novel robotic platforms, combining visual data with vocal interfaces [ 12 , 13 ], or tactile sensors [ 14 , 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Instance Segmentation and Visual Servoing to Play Jenga with a Cost-Effective Robotic System

Marchionna

Pugliese

Martini

et al. 2023

Sensors

View full text Add to dashboard Cite

The game of Jenga is a benchmark used for developing innovative manipulation solutions for complex tasks. Indeed, it encourages the study of novel robotics methods to successfully extract blocks from a tower. A Jenga game involves many traits of complex industrial and surgical manipulation tasks, requiring a multi-step strategy, the combination of visual and tactile data, and the highly precise motion of a robotic arm to perform a single block extraction. In this work, we propose a novel, cost-effective architecture for playing Jenga with e.Do, a 6DOF anthropomorphic manipulator manufactured by Comau, a standard depth camera, and an inexpensive monodirectional force sensor. Our solution focuses on a visual-based control strategy to accurately align the end-effector with the desired block, enabling block extraction by pushing. To this aim, we trained an instance segmentation deep learning model on a synthetic custom dataset to segment each piece of the Jenga tower, allowing for visual tracking of the desired block’s pose during the motion of the manipulator. We integrated the visual-based strategy with a 1D force sensor to detect whether the block could be safely removed by identifying a force threshold value. Our experimentation shows that our low-cost solution allows e.DO to precisely reach removable blocks and perform up to 14 consecutive extractions in a row.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Second, all of these steps are based on the combination of real-time visual and tactile data processing and the highly precise motion of the end-effector for a single block extraction. According to this, it can be surely compared to real-world industrial [ 11 ], surgical [ 24 ], and agricultural [ 25 , 26 ] manipulation tasks.…”

Section: Introductionmentioning

confidence: 99%

Deep Instance Segmentation and Visual Servoing to Play Jenga with a Cost-Effective Robotic System

Marchionna

Pugliese

Martini

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Nowadays, with the rapid development of industrial robot technology, [1][2][3] palletizing manipulators have become a hot spot of application and are used in automobile production, material handling, glasssubstrate sorting. [4][5][6][7][8][9] For example, a multi-degree of freedom serial mechanism-based glass palletizing manipulator was designed in Cui 10 and Wang 11 which can absorb glass through a pneumatic sucker. In YASKAWA, 12 a large liquid crystal glass substrate handling robot with four degrees of freedom (DOF) was designed by YASKAWA, which can be suitable for glass substrate handling.…”

Section: Introductionmentioning

confidence: 99%

Multi-link mechanism-inspired palletizing manipulator: Design, optimization and experimental results

Chen

Huang

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

The precision of trajectory tracking and stable operation with sorting merchandise are the main challenges for palletizing manipulators in different working conditions, especially in sorting glass-substrate. To ensure the adaptability of the manipulator under different working conditions, including operational efficiency, motion space, and control accuracy, the structural optimization and the motion control methods of the manipulator should be considered. In this paper, the structure optimization and tracking control of the manipulator for sorting glass substrates are studied. Firstly, considering the optimization factors including stroke speed ratio k, transmission angle [Formula: see text] and the sum of link-rod lengths l of the crank rocker mechanism, a structural optimization method based on genetic algorithm is applied to enhance the flexible maneuverability. Furthermore, a feedforward-feedback iterative learning control (ILC) algorithm is adopted to the high accuracy of position tracking. Finally, experimental results verify the feasibility of structural optimization and tracking control, which can be effective applied in practical engineering.

show abstract

“…According to the International Federation of Robotics, the global installations of industrial robot arms were ~380,000 units in 2020, with ~3.0 million operational stocks of industrial robot arms [1]. With an increase in the number of robots in manufacturing scenes, new intelligent control paradigms for robot collaboration and their future applications are discussed [2,3]. Robot arms are used in several applications including the production of electricity, electronics, food, and chemicals.…”

Section: Introductionmentioning

confidence: 99%

Efficient Cable Path Optimization Based on Critical Robot Poses for Industrial Robot Arms

et al. 2022

View full text Add to dashboard Cite

Although industrial robotic arms are equipped with external cables to supply electricity, gases or other materials, cable path design is a difficult and demanding task. Herein, an efficient optimization method is proposed for automating cable path design under the assumption that the robot motion path is known. The contribution of this study was to reduce the considerable computation time required for the optimization, which was a concern in our previous work. The previous method represented candidates for cable paths as a set of parameter vectors (PVs) that included cable length and guide configurations, and then selected the optimal PV that satisfies stress constraints and provided the shortest cable path. The proposed method extracted critical poses, i.e., several static robot poses that are prone to applying stress to the cable, from the joint angle time series of the motion path, and then performed attachment and motion tests. The cable geometry for the static critical poses was simulated in the attachment test, while the geometry for dynamic robot motion was simulated in the motion test in an ascending order of the cable length among the PV candidates. Experimental results showed that the computation time for cable path optimization could be significantly reduced.

show abstract

Recent Trends in the Research of Industrial Robots and Future Outlook

Cited by 18 publications

References 41 publications

Deep Instance Segmentation and Visual Servoing to Play Jenga with a Cost-Effective Robotic System

Deep Instance Segmentation and Visual Servoing to Play Jenga with a Cost-Effective Robotic System

Multi-link mechanism-inspired palletizing manipulator: Design, optimization and experimental results

Efficient Cable Path Optimization Based on Critical Robot Poses for Industrial Robot Arms

Contact Info

Product

Resources

About