Metraipolis › archive › dc_3551f8ff7cc7
BlenDAgger: Blended Shared Control for Interactive Imitation Learning — arXiv:2609.37599
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37599
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:33:01.167Z
- SHA-256 of the archived text
266b3bf96a260f91fb2166c19ef9e9835777c9e6e0cbe2bb015f5680620060b6- Stable URL of this page
https://metraipolis.com/documento/dc_3551f8ff7cc7
How to cite
BlenDAgger: Blended Shared Control for Interactive Imitation Learning — arXiv:2609.37599 — arXiv (en), https://arxiv.org/abs/2609.37599 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3551f8ff7cc7 (Metraipolis archive dc_3551f8ff7cc7, sha256 266b3bf96a260f91fb2166c19ef9e9835777c9e6e0cbe2bb015f5680620060b6)
BibTeX
@misc{dc3551f8ff7cc7,
title = {BlenDAgger: Blended Shared Control for Interactive Imitation Learning — arXiv:2609.37599},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37599},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3551f8ff7cc7; sha256 266b3bf96a260f91fb2166c19ef9e9835777c9e6e0cbe2bb015f5680620060b6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37599. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Robot policies are frequently trained from human corrections, yet teleoperating a robot to provide corrections is burdensome, and human demonstrators are not always optimal. We propose Blended DAgger (BlenDAgger), an approach for collecting data to train imitation learning policies by using shared control to blend the policy's and demonstrator's actions during interventions. By blending human and policy actions, we aim to improve the autonomous performance of manipulation policies. We validate our approach across five manipulation tasks, two in the real world and three in simulation. Our approach achieves higher autonomous performance by 30 or more percentage points on two real-world tasks compared to a typical human-gated correction approach (HG-DAgger). We also investigate the advantages of BlenDAgger that allow for higher autonomous performance, finding that BlenDAgger results in 57% smoother transitions between policy control and human interventions, and 14% higher trajectory similarity to the training data. In a user study (n=14) on two real-world tasks, we find that BlenDAgger results in faster data collection (BF=13.32), and we do not find a difference in subjective perceptions. These results show that blended shared control leads to higher autonomous performance compared to typical methods for fine-tuning robot policies from fully teleoperated interventions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG). Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.37599 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T16:59:48.563Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).