Metraipolis › archive › dc_7f26329426f7
Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies — arXiv:2609.38537
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38537
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T15:11:32.523Z
- SHA-256 of the archived text
f56640a22233c846fd9018d23253999aa00de8e42f351ab43232a86e8f6d283c- Stable URL of this page
https://metraipolis.com/documento/dc_7f26329426f7
How to cite
Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies — arXiv:2609.38537 — arXiv (en), https://arxiv.org/abs/2609.38537 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f26329426f7 (Metraipolis archive dc_7f26329426f7, sha256 f56640a22233c846fd9018d23253999aa00de8e42f351ab43232a86e8f6d283c)
BibTeX
@misc{dc7f26329426f7,
title = {Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies — arXiv:2609.38537},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38537},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f26329426f7; sha256 f56640a22233c846fd9018d23253999aa00de8e42f351ab43232a86e8f6d283c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38537. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
GPT-6 Astra exhibits a remarkable ability to generate numerical robot actions, extending its role beyond high-level planning. To assess Astra's capabilities as general-purpose embodied policies, we conduct comprehensive evaluations across six domains, examining direct control, cooperation with learned policies, and feedback-driven adaptation. In gripper manipulation, Astra can correct task targets and prepare contact conditions for subsequent policy execution; hybrid control with {\pi}0.5 achieves 48% success on the evaluated RoboDojo subset. In dexterous manipulation, hybrid control achieves 50% success in ten experience-guided DexJoCo trials, while direct in-hand control struggles to coordinate finger contacts. In mobile manipulation, hybrid control reaches 38.7% success on the evaluated RoboCasa365. In navigation, Astra leads our local comparisons, reaching 92% success on RxR instruction following and 82% on HM3D object search, although search incurs substantial detours. In locomotion, dense motion-reference generation remains unreliable: none of five sequential attempts on a single obstacle course reaches the goal, despite improvements in stability and forward progress. In humanoid loco-manipulation, Astra exceeds baseline methods on 13 of 30 HumanoidBench tasks with pretrained whole-body controllers. These findings reveal a gap between useful task decisions and reliable physical control. Inference latency further constrains practical control: across 50 RoboDojo instances per condition, policy-assisted and direct control consume 624.8 million and 1.132 billion tokens. A 30-second locomotion run requires 250 model calls averaging 39.86 seconds each, with physics paused during inference.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.38537 — 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 2026-10-07T14:44:47.351Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).