start_tick_0000
initial state before meaningful motion
Real public GR00T WholeBodyControl run inside the MuJoCo-backed G1 showcase, driven by the same staged locomotion script used for the velocity-only cards. This page keeps the full charts, playback, and downloadable artifacts.
NVIDIA GR00T · Lower-body RL locomotion with default upper-body posture
decoupled_wbc
Real public GR00T WholeBodyControl run inside the MuJoCo-backed G1 showcase, driven by the same staged locomotion script used for the velocity-only cards.
run.rrd lazily when the viewer enters the viewport.
decoupled_wbc
decoupled_wbc
assets/robots/unitree_g1/g1_29dof.xml
[2.000, 0.000, 0.000, 0.000, 0.600, 0.000, ...]
Published GR00T WholeBodyControl ONNX checkpoints
models/decoupled-wbc/GR00T-WholeBodyControl-Walk.onnx
runtime.velocity_schedule
[-0.156, 0.021, -0.015, 0.426, -0.147, 0.021, ...]
[-0.367, 0.018, -0.012, 0.678, -0.172, 0.004, ...]
Rerun recording · JSON summary · run log · Proof-pack manifest · configs/showcase/decoupled_wbc_real.toml
Each image overlays the target pose in blue against the actual replayed pose in orange. The checkpoints are selected from the replay trace so you can cross-check startup, motion onset, peak latency, furthest progress, and final state without opening a second report.
initial state before meaningful motion
first floating-base displacement >= 0.05 m (0.051 m)
highest inference latency (0.603 ms)
largest planar displacement from start (3.536 m)
final recorded simulator state