#LocoManipulation (4)

VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation

VIRAL is a visual sim-to-real framework from NVIDIA GEAR and CMU: a privileged RL teacher masters long-horizon loco-manipulation with a delta action space, staged rewards, and reference state initialization, then a student policy using only RGB is distilled at scale on 64 GPUs via a DAgger-BC mixture, with dexterous-hand SysID, camera extrinsics alignment, and four-axis visual randomization. Deployed zero-shot on a Unitree G1, it succeeds on 54 of 59 real trials at 20.2 s per cycle — faster than expert teleoperation — and generalizes across nine environment variations. Ablations show compute scale is a passing grade, not an accelerator; code, models, and the full reward table are open-sourced.