Improving Low-Cost Teleoperation: Augmenting GELLO with Force
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915397941329920 |
|---|---|
| author | Sujit, Shivakanth Nunziante, Luca Lillrank, Dan Ogawa Dossa, Rousslan Fernand Julien Arulkumaran, Kai |
| author_facet | Sujit, Shivakanth Nunziante, Luca Lillrank, Dan Ogawa Dossa, Rousslan Fernand Julien Arulkumaran, Kai |
| contents | In this work we extend the low-cost GELLO teleoperation system, initially designed for joint position control, with additional force information. Our first extension is to implement force feedback, allowing users to feel resistance when interacting with the environment. Our second extension is to add force information into the data collection process and training of imitation learning models. We validate our additions by implementing these on a GELLO system with a Franka Panda arm as the follower robot, performing a user study, and comparing the performance of policies trained with and without force information on a range of simulated and real dexterous manipulation tasks. Qualitatively, users with robotics experience preferred our controller, and the addition of force inputs improved task success on the majority of tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_13602 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Low-Cost Teleoperation: Augmenting GELLO with Force Sujit, Shivakanth Nunziante, Luca Lillrank, Dan Ogawa Dossa, Rousslan Fernand Julien Arulkumaran, Kai Robotics Human-Computer Interaction Machine Learning In this work we extend the low-cost GELLO teleoperation system, initially designed for joint position control, with additional force information. Our first extension is to implement force feedback, allowing users to feel resistance when interacting with the environment. Our second extension is to add force information into the data collection process and training of imitation learning models. We validate our additions by implementing these on a GELLO system with a Franka Panda arm as the follower robot, performing a user study, and comparing the performance of policies trained with and without force information on a range of simulated and real dexterous manipulation tasks. Qualitatively, users with robotics experience preferred our controller, and the addition of force inputs improved task success on the majority of tasks. |
| title | Improving Low-Cost Teleoperation: Augmenting GELLO with Force |
| topic | Robotics Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2507.13602 |