Advances on Affordable Hardware Platforms for Human Demonstration Acquisition in Agricultural Applications
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_ | 1866912424750219264 |
|---|---|
| author | San-Miguel-Tello, Alberto Scarati, Gennaro Hernández, Alejandro Cavero-Vidal, Mario Maroti, Aakash García, Néstor |
| author_facet | San-Miguel-Tello, Alberto Scarati, Gennaro Hernández, Alejandro Cavero-Vidal, Mario Maroti, Aakash García, Néstor |
| contents | This paper presents advances on the Universal Manipulation Interface (UMI), a low-cost hand-held gripper for robot Learning from Demonstration (LfD), for complex in-the-wild scenarios found in agricultural settings. The focus is on improving the acquisition of suitable samples with minimal additional setup. Firstly, idle times and user's cognitive load are reduced through the extraction of individual samples from a continuous demonstration considering task events. Secondly, reliability on the generation of task sample's trajectories is increased through the combination on-board inertial measurements and external visual marker localization usage using Extended Kalman Filtering (EKF). Results are presented for a fruit harvesting task, outperforming the default pipeline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_09494 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advances on Affordable Hardware Platforms for Human Demonstration Acquisition in Agricultural Applications San-Miguel-Tello, Alberto Scarati, Gennaro Hernández, Alejandro Cavero-Vidal, Mario Maroti, Aakash García, Néstor Robotics This paper presents advances on the Universal Manipulation Interface (UMI), a low-cost hand-held gripper for robot Learning from Demonstration (LfD), for complex in-the-wild scenarios found in agricultural settings. The focus is on improving the acquisition of suitable samples with minimal additional setup. Firstly, idle times and user's cognitive load are reduced through the extraction of individual samples from a continuous demonstration considering task events. Secondly, reliability on the generation of task sample's trajectories is increased through the combination on-board inertial measurements and external visual marker localization usage using Extended Kalman Filtering (EKF). Results are presented for a fruit harvesting task, outperforming the default pipeline. |
| title | Advances on Affordable Hardware Platforms for Human Demonstration Acquisition in Agricultural Applications |
| topic | Robotics |
| url | https://arxiv.org/abs/2506.09494 |