Physics-Based Self-Supervised Grasp Pose Detection
Current industrial robotic manipulators have made their lack of flexibility evident. The systems must know beforehand the piece and its position. To address this issue, contemporary approaches typically employ learning-based techniques, which rely on extensive amounts of data. To obtain vast data, a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/13/1/12 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588054975479808 |
|---|---|
| author | Jon Ander Ruiz Ander Iriondo Elena Lazkano Ander Ansuategi Iñaki Maurtua |
| author_facet | Jon Ander Ruiz Ander Iriondo Elena Lazkano Ander Ansuategi Iñaki Maurtua |
| author_sort | Jon Ander Ruiz |
| collection | DOAJ |
| description | Current industrial robotic manipulators have made their lack of flexibility evident. The systems must know beforehand the piece and its position. To address this issue, contemporary approaches typically employ learning-based techniques, which rely on extensive amounts of data. To obtain vast data, an often sought tool is an extensive grasp dataset. This work introduces our Physics-Based Self-Supervised Grasp Pose Detection (PBSS-GPD) pipeline for model-based grasping point detection, which is useful for generating grasp pose datasets. Given a gripper-object pair, it samples grasping pose candidates using a modified version of GPD (implementing inner-grasps, CAD support…) and quantifies their quality using the MuJoCo physics engine and a grasp quality metric that takes into account the pose of the object over time. The system is optimized to run on CPU in headless-parallelized mode, with the option of running in a graphical interface or headless and storing videos of the process. The system has been validated obtaining grasping poses for a subset of Egad! objects using the Franka Panda two-finger gripper, compared with state-of-the-art grasp generation pipelines and tested in a real scenario. While our system achieves similar accuracy compared to a contemporary approach, 84% on the real-world validation, it has proven to be effective at generating grasps with good centering 18 times faster than the compared system. |
| format | Article |
| id | doaj-art-4c25d050757a4ad98f43f8d418fc083b |
| institution | Kabale University |
| issn | 2075-1702 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj-art-4c25d050757a4ad98f43f8d418fc083b2025-01-24T13:39:07ZengMDPI AGMachines2075-17022024-12-011311210.3390/machines13010012Physics-Based Self-Supervised Grasp Pose DetectionJon Ander Ruiz0Ander Iriondo1Elena Lazkano2Ander Ansuategi3Iñaki Maurtua4Department of Autonomous and Intelligent Systems, Tekniker—Basque Research and Technology Alliance (BRTA), Iñaki Goenaga 5, 20600 Eibar, Gipuzkoa, SpainDepartment of Autonomous and Intelligent Systems, Tekniker—Basque Research and Technology Alliance (BRTA), Iñaki Goenaga 5, 20600 Eibar, Gipuzkoa, SpainRobotics and Autonomous Systems Group (RSAIT), Department of Computer Science and Artificial Intelligence, University of the Basque Country (UPV/EHU), 20018 Donostia-San Sebastián, Gipuzkoa, SpainDepartment of Autonomous and Intelligent Systems, Tekniker—Basque Research and Technology Alliance (BRTA), Iñaki Goenaga 5, 20600 Eibar, Gipuzkoa, SpainDepartment of Autonomous and Intelligent Systems, Tekniker—Basque Research and Technology Alliance (BRTA), Iñaki Goenaga 5, 20600 Eibar, Gipuzkoa, SpainCurrent industrial robotic manipulators have made their lack of flexibility evident. The systems must know beforehand the piece and its position. To address this issue, contemporary approaches typically employ learning-based techniques, which rely on extensive amounts of data. To obtain vast data, an often sought tool is an extensive grasp dataset. This work introduces our Physics-Based Self-Supervised Grasp Pose Detection (PBSS-GPD) pipeline for model-based grasping point detection, which is useful for generating grasp pose datasets. Given a gripper-object pair, it samples grasping pose candidates using a modified version of GPD (implementing inner-grasps, CAD support…) and quantifies their quality using the MuJoCo physics engine and a grasp quality metric that takes into account the pose of the object over time. The system is optimized to run on CPU in headless-parallelized mode, with the option of running in a graphical interface or headless and storing videos of the process. The system has been validated obtaining grasping poses for a subset of Egad! objects using the Franka Panda two-finger gripper, compared with state-of-the-art grasp generation pipelines and tested in a real scenario. While our system achieves similar accuracy compared to a contemporary approach, 84% on the real-world validation, it has proven to be effective at generating grasps with good centering 18 times faster than the compared system.https://www.mdpi.com/2075-1702/13/1/12graspingrobot learningintelligent robotssimulationautonomous robots |
| spellingShingle | Jon Ander Ruiz Ander Iriondo Elena Lazkano Ander Ansuategi Iñaki Maurtua Physics-Based Self-Supervised Grasp Pose Detection Machines grasping robot learning intelligent robots simulation autonomous robots |
| title | Physics-Based Self-Supervised Grasp Pose Detection |
| title_full | Physics-Based Self-Supervised Grasp Pose Detection |
| title_fullStr | Physics-Based Self-Supervised Grasp Pose Detection |
| title_full_unstemmed | Physics-Based Self-Supervised Grasp Pose Detection |
| title_short | Physics-Based Self-Supervised Grasp Pose Detection |
| title_sort | physics based self supervised grasp pose detection |
| topic | grasping robot learning intelligent robots simulation autonomous robots |
| url | https://www.mdpi.com/2075-1702/13/1/12 |
| work_keys_str_mv | AT jonanderruiz physicsbasedselfsupervisedgraspposedetection AT andeririondo physicsbasedselfsupervisedgraspposedetection AT elenalazkano physicsbasedselfsupervisedgraspposedetection AT anderansuategi physicsbasedselfsupervisedgraspposedetection AT inakimaurtua physicsbasedselfsupervisedgraspposedetection |