Online Self-Supervised Learning for Accurate Pick Assembly Operation Optimization
The demand for flexible automation in manufacturing has increased, incorporating vision-guided systems for object grasping. However, a key challenge is in-hand error, where discrepancies between the actual and estimated positions of an object in the robot’s gripper impact not only the grasp but also...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Robotics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-6581/14/1/4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587600805756928 |
|---|---|
| author | Sergio Valdés Marco Ojer Xiao Lin |
| author_facet | Sergio Valdés Marco Ojer Xiao Lin |
| author_sort | Sergio Valdés |
| collection | DOAJ |
| description | The demand for flexible automation in manufacturing has increased, incorporating vision-guided systems for object grasping. However, a key challenge is in-hand error, where discrepancies between the actual and estimated positions of an object in the robot’s gripper impact not only the grasp but also subsequent assembly stages. Corrective strategies used to compensate for misalignment can increase cycle times or rely on pre-labeled datasets, offline training, and validation processes, delaying deployment and limiting adaptability in dynamic industrial environments. Our main contribution is an online self-supervised learning method that automates data collection, training, and evaluation in real time, eliminating the need for offline processes. Building on this, our system collects real-time data during each assembly cycle, using corrective strategies to adjust the data and autonomously labeling them via a self-supervised approach. It then builds and evaluates multiple regression models through an auto machine learning implementation. The system selects the best-performing model to correct the misalignment and dynamically chooses between corrective strategies and the learned model, optimizing the cycle times and improving the performance during the cycle, without halting the production process. Our experiments show a significant reduction in the cycle time while maintaining the performance. |
| format | Article |
| id | doaj-art-d88a6de51346440fa0b8b23bfb914437 |
| institution | Kabale University |
| issn | 2218-6581 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Robotics |
| spelling | doaj-art-d88a6de51346440fa0b8b23bfb9144372025-01-24T13:48:22ZengMDPI AGRobotics2218-65812024-12-01141410.3390/robotics14010004Online Self-Supervised Learning for Accurate Pick Assembly Operation OptimizationSergio Valdés0Marco Ojer1Xiao Lin2Vicomtech Foundation, Basque Research and Technology Alliance (BRTA), 20009 Donostia-San Sebastian, SpainVicomtech Foundation, Basque Research and Technology Alliance (BRTA), 20009 Donostia-San Sebastian, SpainVicomtech Foundation, Basque Research and Technology Alliance (BRTA), 20009 Donostia-San Sebastian, SpainThe demand for flexible automation in manufacturing has increased, incorporating vision-guided systems for object grasping. However, a key challenge is in-hand error, where discrepancies between the actual and estimated positions of an object in the robot’s gripper impact not only the grasp but also subsequent assembly stages. Corrective strategies used to compensate for misalignment can increase cycle times or rely on pre-labeled datasets, offline training, and validation processes, delaying deployment and limiting adaptability in dynamic industrial environments. Our main contribution is an online self-supervised learning method that automates data collection, training, and evaluation in real time, eliminating the need for offline processes. Building on this, our system collects real-time data during each assembly cycle, using corrective strategies to adjust the data and autonomously labeling them via a self-supervised approach. It then builds and evaluates multiple regression models through an auto machine learning implementation. The system selects the best-performing model to correct the misalignment and dynamically chooses between corrective strategies and the learned model, optimizing the cycle times and improving the performance during the cycle, without halting the production process. Our experiments show a significant reduction in the cycle time while maintaining the performance.https://www.mdpi.com/2218-6581/14/1/4self-supervised learningonline learningvision-guided systemspick-and-placein-hand errorpeg-in-hole |
| spellingShingle | Sergio Valdés Marco Ojer Xiao Lin Online Self-Supervised Learning for Accurate Pick Assembly Operation Optimization Robotics self-supervised learning online learning vision-guided systems pick-and-place in-hand error peg-in-hole |
| title | Online Self-Supervised Learning for Accurate Pick Assembly Operation Optimization |
| title_full | Online Self-Supervised Learning for Accurate Pick Assembly Operation Optimization |
| title_fullStr | Online Self-Supervised Learning for Accurate Pick Assembly Operation Optimization |
| title_full_unstemmed | Online Self-Supervised Learning for Accurate Pick Assembly Operation Optimization |
| title_short | Online Self-Supervised Learning for Accurate Pick Assembly Operation Optimization |
| title_sort | online self supervised learning for accurate pick assembly operation optimization |
| topic | self-supervised learning online learning vision-guided systems pick-and-place in-hand error peg-in-hole |
| url | https://www.mdpi.com/2218-6581/14/1/4 |
| work_keys_str_mv | AT sergiovaldes onlineselfsupervisedlearningforaccuratepickassemblyoperationoptimization AT marcoojer onlineselfsupervisedlearningforaccuratepickassemblyoperationoptimization AT xiaolin onlineselfsupervisedlearningforaccuratepickassemblyoperationoptimization |