Human-Robot Copilot for Data-Efficient Imitation Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910102897819648 |
|---|---|
| author | Yan, Rui Gongye, Zaitian Paulsen, Lars Cheng, Xuxin Wang, Xiaolong |
| author_facet | Yan, Rui Gongye, Zaitian Paulsen, Lars Cheng, Xuxin Wang, Xiaolong |
| contents | Collecting human demonstrations via teleoperation is a common approach for teaching robots task-specific skills. However, when only a limited number of demonstrations are available, policies are prone to entering out-of-distribution (OOD) states due to compounding errors or environmental stochasticity. Existing interactive imitation learning or human-in-the-loop methods try to address this issue by following the Human-Gated DAgger (HG-DAgger) paradigm, an approach that augments demonstrations through selective human intervention during policy execution. Nevertheless, these approaches struggle to balance dexterity and generality: they either provide fine-grained corrections but are limited to specific kinematic structures, or achieve generality at the cost of precise control. To overcome this limitation, we propose the Human-Robot Copilot framework that can leverage a scaling factor for dexterous teleoperation while maintaining compatibility with a wide range of industrial and research manipulators. Experimental results demonstrate that our framework achieves higher performance with the same number of demonstration trajectories. Moreover, since corrective interventions are required only intermittently, the overall data collection process is more efficient and less time-consuming. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03613 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Human-Robot Copilot for Data-Efficient Imitation Learning Yan, Rui Gongye, Zaitian Paulsen, Lars Cheng, Xuxin Wang, Xiaolong Robotics Collecting human demonstrations via teleoperation is a common approach for teaching robots task-specific skills. However, when only a limited number of demonstrations are available, policies are prone to entering out-of-distribution (OOD) states due to compounding errors or environmental stochasticity. Existing interactive imitation learning or human-in-the-loop methods try to address this issue by following the Human-Gated DAgger (HG-DAgger) paradigm, an approach that augments demonstrations through selective human intervention during policy execution. Nevertheless, these approaches struggle to balance dexterity and generality: they either provide fine-grained corrections but are limited to specific kinematic structures, or achieve generality at the cost of precise control. To overcome this limitation, we propose the Human-Robot Copilot framework that can leverage a scaling factor for dexterous teleoperation while maintaining compatibility with a wide range of industrial and research manipulators. Experimental results demonstrate that our framework achieves higher performance with the same number of demonstration trajectories. Moreover, since corrective interventions are required only intermittently, the overall data collection process is more efficient and less time-consuming. |
| title | Human-Robot Copilot for Data-Efficient Imitation Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2604.03613 |