gpt-6VIDEO

NVIDIA studies GPT-6 Astra as a robot pick-and-place policy

In its Astranomy project, NVIDIA tested whether a general-purpose model can serve as a robot policy; GPT-6 Astra set a new SOTA on RoboLab-120, but real-time robot control remains an open challenge.

Jenai Xuning Yang

@xuningyArchived 16 days agoOriginally posted 2026.10.15

Jenai Xuning Yang @xuningyOriginally posted 2026.10.15

Open original on X

Can and should a general-purpose model serve as a robot policy? In Astranomy, we study GPT-6 Astra for general pick-and-place manipulation. Astra sets a new SOTA on RoboLab-120, but real-time robot control remains an open challenge. Full tech report: https://research.nvidia.com/labs/srl/projects/astranomy/

x.com/xuningy/status/2110468153147089292Archived 2026.10.15 10:50