TANGO: Full-Body Humanoid Navigation from Berkeley and Princeton

UC Berkeley and Princeton introduced TANGO, a whole-body vision-language-action model that predicts 29-DoF joint actions directly from egocentric RGB, enabling humanoids to navigate cluttered spaces with zero-shot sim-to-real transfer.

2026-09-24 ~ 2026-09-25 · 3 related posts

• TANGO: Sim-Only Trained Whole-Body VLA Gives Humanoids Zero-Shot Navigation on Unitree G1 — chris_j_paxton · 2026-09-24
• TANGO: Whole-Body VLA Maps RGB to 29-DoF Actions for Humanoid Navigation, Trained Fully in Simulation — berkeley_ai · 2026-09-24
• TANGO from UC Berkeley and Princeton brings whole-body AI control to humanoid robot navigation — shahdhruv_ · 2026-09-25