Proleptic Temporal Ensemble for Improving the Speed of Robot Tasks Generated by 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_ | 1866913735475462144 |
|---|---|
| author | Park, Hyeonjun Lim, Daegyu Kim, Seungyeon Park, Sumin |
| author_facet | Park, Hyeonjun Lim, Daegyu Kim, Seungyeon Park, Sumin |
| contents | Imitation learning, which enables robots to learn behaviors from demonstrations by human, has emerged as a promising solution for generating robot motions in such environments. The imitation learning-based robot motion generation method, however, has the drawback of depending on the demonstrator's task execution speed. This paper presents a novel temporal ensemble approach applied to imitation learning algorithms, allowing for execution of future actions. The proposed method leverages existing demonstration data and pre-trained policies, offering the advantages of requiring no additional computation and being easy to implement. The algorithms performance was validated through real-world experiments involving robotic block color sorting, demonstrating up to 3x increase in task execution speed while maintaining a high success rate compared to the action chunking with transformer method. This study highlights the potential for significantly improving the performance of imitation learning-based policies, which were previously limited by the demonstrator's speed. It is expected to contribute substantially to future advancements in autonomous object manipulation technologies aimed at enhancing productivity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_16981 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Proleptic Temporal Ensemble for Improving the Speed of Robot Tasks Generated by Imitation Learning Park, Hyeonjun Lim, Daegyu Kim, Seungyeon Park, Sumin Robotics Imitation learning, which enables robots to learn behaviors from demonstrations by human, has emerged as a promising solution for generating robot motions in such environments. The imitation learning-based robot motion generation method, however, has the drawback of depending on the demonstrator's task execution speed. This paper presents a novel temporal ensemble approach applied to imitation learning algorithms, allowing for execution of future actions. The proposed method leverages existing demonstration data and pre-trained policies, offering the advantages of requiring no additional computation and being easy to implement. The algorithms performance was validated through real-world experiments involving robotic block color sorting, demonstrating up to 3x increase in task execution speed while maintaining a high success rate compared to the action chunking with transformer method. This study highlights the potential for significantly improving the performance of imitation learning-based policies, which were previously limited by the demonstrator's speed. It is expected to contribute substantially to future advancements in autonomous object manipulation technologies aimed at enhancing productivity. |
| title | Proleptic Temporal Ensemble for Improving the Speed of Robot Tasks Generated by Imitation Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2410.16981 |