Metraipolis › archive › dc_7e2f225fe16e

Robotic Data Inoculation — arXiv:2610.39054

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39054
License (as archived)
CC0-1.0
Archived
2026-11-01T02:44:19.724Z
SHA-256 of the archived text
95a99d6edd65e131b241f79bfe86f03ea54be081dfbeed59dbf6f1b70789b942
Stable URL of this page
https://metraipolis.com/documento/dc_7e2f225fe16e

How to cite

Robotic Data Inoculation — arXiv:2610.39054 — arXiv (en), https://arxiv.org/abs/2610.39054 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e2f225fe16e (Metraipolis archive dc_7e2f225fe16e, sha256 95a99d6edd65e131b241f79bfe86f03ea54be081dfbeed59dbf6f1b70789b942)
BibTeX
@misc{dc7e2f225fe16e,
  title = {Robotic Data Inoculation — arXiv:2610.39054},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39054},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e2f225fe16e; sha256 95a99d6edd65e131b241f79bfe86f03ea54be081dfbeed59dbf6f1b70789b942},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39054. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern robot learning systems feed on high-quality demonstration data, and their performance hinges on coverage. Without good coverage, small errors compound and the policy can quickly go into out-of-distribution states from which it cannot recover. Yet there is no principled way of collecting high-coverage data, and data collection often relies on heuristic instructions to human operators. Purely online reinforcement learning (RL) explores at the cost of safety and sample efficiency, while DAgger-style interventions require the policy to fail by chance before a human can correct it. In this paper, we ask instead whether we can modify how the robot behaves during data collection to collect more useful data. We propose Data Inoculation (DI), a shared-control framework in which a human provide closed-loop teleoperation commands while a residual policy perturbs these commands. The residual policy is trained online, on the growing dataset, with the same reward-maximizing objective later used for policy extraction, so its perturbations steer data collection toward the deviations a policy trained on the data would make. These perturbations expose the robot to a wider range of states, while the human's continuous corrections provide recovery demonstrations, "inoculating" the dataset against the learner's future mistakes while the human remains in control. On three challenging real-world robotic tasks, DI consistently improves or matches the success rate of policies trained with both behavioral cloning and offline RL, showing DI as an effective data collection strategy for improving downstream policy performance.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.39054 — 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 2026-11-01T02:16:58.645Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).