Unsupervised Motion Retargeting for Human-Robot Imitation
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_ | 1866911773395779584 |
|---|---|
| author | Annabi, Louis Ma, Ziqi Nguyen, Sao Mai |
| author_facet | Annabi, Louis Ma, Ziqi Nguyen, Sao Mai |
| contents | This early-stage research work aims to improve online human-robot imitation by translating sequences of joint positions from the domain of human motions to a domain of motions achievable by a given robot, thus constrained by its embodiment. Leveraging the generalization capabilities of deep learning methods, we address this problem by proposing an encoder-decoder neural network model performing domain-to-domain translation. In order to train such a model, one could use pairs of associated robot and human motions. Though, such paired data is extremely rare in practice, and tedious to collect. Therefore, we turn towards deep learning methods for unpaired domain-to-domain translation, that we adapt in order to perform human-robot imitation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05115 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unsupervised Motion Retargeting for Human-Robot Imitation Annabi, Louis Ma, Ziqi Nguyen, Sao Mai Robotics Artificial Intelligence Machine Learning This early-stage research work aims to improve online human-robot imitation by translating sequences of joint positions from the domain of human motions to a domain of motions achievable by a given robot, thus constrained by its embodiment. Leveraging the generalization capabilities of deep learning methods, we address this problem by proposing an encoder-decoder neural network model performing domain-to-domain translation. In order to train such a model, one could use pairs of associated robot and human motions. Though, such paired data is extremely rare in practice, and tedious to collect. Therefore, we turn towards deep learning methods for unpaired domain-to-domain translation, that we adapt in order to perform human-robot imitation. |
| title | Unsupervised Motion Retargeting for Human-Robot Imitation |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2402.05115 |