Variable-Speed Teaching-Playback as Real-World Data Augmentation for Imitation Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910928691265536 |
|---|---|
| author | Masuya, Nozomu Sato, Hiroshi Yamane, Koki Kusume, Takuya Sakaino, Sho Tsuji, Toshiaki |
| author_facet | Masuya, Nozomu Sato, Hiroshi Yamane, Koki Kusume, Takuya Sakaino, Sho Tsuji, Toshiaki |
| contents | Because imitation learning relies on human demonstrations in hard-to-simulate settings, the inclusion of force control in this method has resulted in a shortage of training data, even with a simple change in speed. Although the field of data augmentation has addressed the lack of data, conventional methods of data augmentation for robot manipulation are limited to simulation-based methods or downsampling for position control. This paper proposes a novel method of data augmentation that is applicable to force control and preserves the advantages of real-world datasets. We applied teaching-playback at variable speeds as real-world data augmentation to increase both the quantity and quality of environmental reactions at variable speeds. An experiment was conducted on bilateral control-based imitation learning using a method of imitation learning equipped with position-force control. We evaluated the effect of real-world data augmentation on two tasks, pick-and-place and wiping, at variable speeds, each from two human demonstrations at fixed speed. The results showed a maximum 55% increase in success rate from a simple change in speed of real-world reactions and improved accuracy along the duration/frequency command by gathering environmental reactions at variable speeds. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03252 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Variable-Speed Teaching-Playback as Real-World Data Augmentation for Imitation Learning Masuya, Nozomu Sato, Hiroshi Yamane, Koki Kusume, Takuya Sakaino, Sho Tsuji, Toshiaki Robotics Machine Learning Because imitation learning relies on human demonstrations in hard-to-simulate settings, the inclusion of force control in this method has resulted in a shortage of training data, even with a simple change in speed. Although the field of data augmentation has addressed the lack of data, conventional methods of data augmentation for robot manipulation are limited to simulation-based methods or downsampling for position control. This paper proposes a novel method of data augmentation that is applicable to force control and preserves the advantages of real-world datasets. We applied teaching-playback at variable speeds as real-world data augmentation to increase both the quantity and quality of environmental reactions at variable speeds. An experiment was conducted on bilateral control-based imitation learning using a method of imitation learning equipped with position-force control. We evaluated the effect of real-world data augmentation on two tasks, pick-and-place and wiping, at variable speeds, each from two human demonstrations at fixed speed. The results showed a maximum 55% increase in success rate from a simple change in speed of real-world reactions and improved accuracy along the duration/frequency command by gathering environmental reactions at variable speeds. |
| title | Variable-Speed Teaching-Playback as Real-World Data Augmentation for Imitation Learning |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2412.03252 |