Visual Movement Prediction for Stable Grasp Point Detection
C. Schwan, W. Schenck, in: L. Iliadis, P.P. Angelov, C. Jayne, E. Pimenidis (Eds.), Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference. Proceedings of the EANN 2020, Springer International Publishing, Cham, 2020, pp. 70–81.
Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Konferenzbeitrag
| Veröffentlicht
| Englisch
Autor*in
Schwan, Constanze;
Schenck, Wolfram
![](https://www.hsbi.de/publikationsserver/images/icon_orcid.png)
![FH Bielefeld](/publikationsserver/images/fh_icon.png)
![](https://www.hsbi.de/publikationsserver/images/icon_orcid.png)
Herausgeber*in
Iliadis, Lazaros;
Angelov, Plamen Parvanov;
Jayne, Chrisina;
Pimenidis, Elias
Abstract
Robotic grasping of unknown objects in cluttered scenes is already well established, mainly based on advances in Deep Learning methods. A major drawback is the need for a big amount of real-world training data. Furthermore these networks are not interpretable in a sense that it is not clear why certain grasp attempts fail. To make the process of robotic grasping traceable and simplify the overall model we suggest to divide the complex task of robotic grasping into three simpler tasks to find stable grasp points. The first task is to find all grasp points where the gripper can be lowered onto the table without colliding with the object. The second task is to determine for the grasp points and gripper parameters from the first step how the object moves while the gripper is closed. Finally in the third step for all grasp points from the second step it is predicted whether the object slips out of the gripper during lifting. By this simplification it is possible to understand for each grasp point why it is stable and - just as important - why others are unstable or not feasible. In this study we focus on the second task, the prediction of the physical interaction between gripper and object while the gripper is closed. We investigate different Convolutional Neural Network (CNN) architectures and identify the architecture(s) that predict the physical interactions in image space best. We perform the experiments for training data generation in the robot and physics simulator V-REP.
Erscheinungsjahr
Titel des Konferenzbandes
Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference. Proceedings of the EANN 2020
Seite
70-81
Konferenz
21st EANN (Engineering Applications of Neural Networks) 2020 Conference
Konferenzort
Halkidiki, Greece
Konferenzdatum
2020-06-05 – 2020-06-07
ISBN
ISSN
eISSN
FH-PUB-ID
Zitieren
Schwan, Constanze ; Schenck, Wolfram: Visual Movement Prediction for Stable Grasp Point Detection. In: Iliadis, L. ; Angelov, P. P. ; Jayne, C. ; Pimenidis, E. (Hrsg.): Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference. Proceedings of the EANN 2020, Proceedings of the International Neural Networks Society. Cham : Springer International Publishing, 2020, S. 70–81
Schwan C, Schenck W. Visual Movement Prediction for Stable Grasp Point Detection. In: Iliadis L, Angelov PP, Jayne C, Pimenidis E, eds. Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference. Proceedings of the EANN 2020. Proceedings of the International Neural Networks Society. Cham: Springer International Publishing; 2020:70-81. doi:10.1007/978-3-030-48791-1_5
Schwan, C., & Schenck, W. (2020). Visual Movement Prediction for Stable Grasp Point Detection. In L. Iliadis, P. P. Angelov, C. Jayne, & E. Pimenidis (Eds.), Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference. Proceedings of the EANN 2020 (pp. 70–81). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-030-48791-1_5
@inproceedings{Schwan_Schenck_2020, place={Cham}, series={Proceedings of the International Neural Networks Society}, title={Visual Movement Prediction for Stable Grasp Point Detection}, DOI={10.1007/978-3-030-48791-1_5}, booktitle={Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference. Proceedings of the EANN 2020}, publisher={Springer International Publishing}, author={Schwan, Constanze and Schenck, Wolfram}, editor={Iliadis, Lazaros and Angelov, Plamen Parvanov and Jayne, Chrisina and Pimenidis, EliasEditors}, year={2020}, pages={70–81}, collection={Proceedings of the International Neural Networks Society} }
Schwan, Constanze, and Wolfram Schenck. “Visual Movement Prediction for Stable Grasp Point Detection.” In Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference. Proceedings of the EANN 2020, edited by Lazaros Iliadis, Plamen Parvanov Angelov, Chrisina Jayne, and Elias Pimenidis, 70–81. Proceedings of the International Neural Networks Society. Cham: Springer International Publishing, 2020. https://doi.org/10.1007/978-3-030-48791-1_5.
C. Schwan and W. Schenck, “Visual Movement Prediction for Stable Grasp Point Detection,” in Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference. Proceedings of the EANN 2020, Halkidiki, Greece, 2020, pp. 70–81.
Schwan, Constanze, and Wolfram Schenck. “Visual Movement Prediction for Stable Grasp Point Detection.” Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference. Proceedings of the EANN 2020, edited by Lazaros Iliadis et al., Springer International Publishing, 2020, pp. 70–81, doi:10.1007/978-3-030-48791-1_5.