Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.18481 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910919078969344 |
|---|---|
| author | Proesmans, Remko Lips, Thomas wyffels, Francis |
| author_facet | Proesmans, Remko Lips, Thomas wyffels, Francis |
| contents | Learning from demonstrations is a powerful paradigm for robot manipulation, but its effectiveness hinges on both the quantity and quality of the collected data. In this work, we present a case study of how instrumentation, i.e. integration of sensors, can improve the quality of demonstrations and automate data collection. We instrument a squeeze bottle with a pressure sensor to learn a liquid dispensing task, enabling automated data collection via a PI controller. Transformer-based policies trained on automated demonstrations outperform those trained on human data in 78% of cases. Our findings indicate that instrumentation not only facilitates scalable data collection but also leads to better-performing policies, highlighting its potential in the pursuit of generalist robotic agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18481 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Instrumentation for Better Demonstrations: A Case Study Proesmans, Remko Lips, Thomas wyffels, Francis Robotics Learning from demonstrations is a powerful paradigm for robot manipulation, but its effectiveness hinges on both the quantity and quality of the collected data. In this work, we present a case study of how instrumentation, i.e. integration of sensors, can improve the quality of demonstrations and automate data collection. We instrument a squeeze bottle with a pressure sensor to learn a liquid dispensing task, enabling automated data collection via a PI controller. Transformer-based policies trained on automated demonstrations outperform those trained on human data in 78% of cases. Our findings indicate that instrumentation not only facilitates scalable data collection but also leads to better-performing policies, highlighting its potential in the pursuit of generalist robotic agents. |
| title | Instrumentation for Better Demonstrations: A Case Study |
| topic | Robotics |
| url | https://arxiv.org/abs/2504.18481 |