Metraipolis › archive › dc_42cb2dd8534f

Behavior Graphs: Unsupervised Graph Structures for Interpreting Robot Deployment Data — arXiv:2611.00405

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00405
License (as archived)
CC0-1.0
Archived
2026-11-03T18:56:58.959Z
SHA-256 of the archived text
7d50f5eb753397d24eb2ad117f491320f6297244aefa9ad2bf3086a73f0d19b8
Stable URL of this page
https://metraipolis.com/documento/dc_42cb2dd8534f

How to cite

Behavior Graphs: Unsupervised Graph Structures for Interpreting Robot Deployment Data — arXiv:2611.00405 — arXiv (en), https://arxiv.org/abs/2611.00405 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_42cb2dd8534f (Metraipolis archive dc_42cb2dd8534f, sha256 7d50f5eb753397d24eb2ad117f491320f6297244aefa9ad2bf3086a73f0d19b8)
BibTeX
@misc{dc42cb2dd8534f,
  title = {Behavior Graphs: Unsupervised Graph Structures for Interpreting Robot Deployment Data — arXiv:2611.00405},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00405},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_42cb2dd8534f; sha256 7d50f5eb753397d24eb2ad117f491320f6297244aefa9ad2bf3086a73f0d19b8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00405. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Data flywheels promise continuous improvement via insights from deployment data. Understanding how the deployed model succeeds and fails can steer subsequent data collection towards patching failures and reinforcing successes. However, robot deployments create large volumes of high-dimensional rollout data, which is challenging to understand and confidently ground data collection decisions in. To make deployment data easier to analyze and act on, we propose behavior graphs, which compress policy rollouts into a single interpretable, directed graph. We construct the graphs by learning to identify similar behavior modes across rollouts, connecting the behaviors temporally, and finally linking them to outcomes. In a user study on three real-world tasks, where participants analyzed rollouts to choose a data collection strategy, 16 of 18 preferred behavior graphs to rollout videos, reaching comparable conclusions with 40.3% lower perceived temporal demand and 37.6% lower effort. Beyond interpretability for deployment data, behavior graphs are capable progress predictors: across 43 datasets, they improve the rank correlation between predicted progress and true temporal order by 22.9% and reduce mean absolute error by 53.5% relative to the strongest baseline. As the number of deployed robots grows, behavior graphs lend structure to high-dimensional policy rollouts and make deployment data easier to interpret and reason about.

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/2611.00405 — 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 2026-11-03T18:17:07.701Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).