TANGO: whole-body VLA model navigates humanoid robots in cluttered spaces from sim data
Anqi Li · hf · 2026-09-09
TANGO is a vision-language-action framework that predicts whole-body joint actions for humanoid robots navigating cluttered indoor environments, trained entirely on simulated data.
More from Embodied
- CosmoH2G: dataset and baseline for transferring hand demos to robot grippers — Hongxiang Zhao · 2026-09-09
- whurley rides CyberCab robotaxi again: 'clean and comfortable,' calls it his next car — whurley · 2026-09-09
- Apple's foldable iPhone named iPhone Duo, $2,000 starting price, October launch — petefang · 2026-09-09
- Hanshow and X-EraLab bring embodied retail robots to nearly 70,000 stores worldwide — 量子位 · 2026-09-09
- Hyper3D WorldGen turns a single photo into a fully editable 3D scene — dr_cintas · 2026-09-09
- GE-Act 2.0: scaling a world-action model for zero-shot robot manipulation — agibot-world · 2026-09-09