Metraipolis › archive › dc_f9866bcae21d
Can Astra Solve RoboMME without Breaking the Bank? — arXiv:2611.06184
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06184
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:30:39.432Z
- SHA-256 of the archived text
cfc305f0c5a456a0d49bb3c6afd64e787dd34afa5d3c8b7bd2a4c3e28f0c3862- Stable URL of this page
https://metraipolis.com/documento/dc_f9866bcae21d
How to cite
Can Astra Solve RoboMME without Breaking the Bank? — arXiv:2611.06184 — arXiv (en), https://arxiv.org/abs/2611.06184 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f9866bcae21d (Metraipolis archive dc_f9866bcae21d, sha256 cfc305f0c5a456a0d49bb3c6afd64e787dd34afa5d3c8b7bd2a4c3e28f0c3862)
BibTeX
@misc{dcf9866bcae21d,
title = {Can Astra Solve RoboMME without Breaking the Bank? — arXiv:2611.06184},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06184},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f9866bcae21d; sha256 cfc305f0c5a456a0d49bb3c6afd64e787dd34afa5d3c8b7bd2a4c3e28f0c3862},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06184. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Robotic manipulation often requires remembering information that is no longer visible, such as an object's location before occlusion or the order of a demonstrated action sequence. A large vision-language planner can read this history, but calling it before every action chunk is slow and costly. We present a three-tier system for the RoboMME benchmark. GPT-6 Astra (System 2) selects a grounded subtask from stored visual history, a $\pi_{0.5}$ vision-language-action policy (System 1) executes it, and a fine-tuned Qwen3-VL-4B monitor (System 1.5) checks after each action chunk whether the subtask is finished. The instruction is kept until the monitor reports completion or a task-specific event occurs, while the policy keeps acting on new observations. On RoboMME, the system succeeds in 79.13% of episodes with an average of 3.63 Astra calls and 80.84 seconds per episode. This is 34.62 points above the best published non-oracle baseline and 4.95 points below GroundSG+Oracle, which gives the low-level policy ground-truth subgoals.
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/2611.06184 — 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 2026-11-05T18:20:03.986Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).