AI & ML
XMimic and XSoma: Learning Humanoid Motion Tracking and Locomotion in Under a Minute
arXiv cs.RO0 views
arXiv:2611.20452v1 Announce Type: new Abstract: We present XMimic and XSoma, which learn humanoid motion tracking and locomotion on rough terrain in under a minute of training. Both follow SuperMimic, which learns a world model of the robot and optimizes the policy with analytic gradients through short rollouts imagined in this model. Existing implementations of this method do not make use of larger GPUs, as every training iteration is a long chain of small GPU operations that run one after another. XMimic and XSoma therefore shorten this chain and run the steps of every iteration at the same time on up to four GPUs. We compile the complete training loop with JAX, including the MuJoCo Warp simulator. For locomotion, XSoma leaves only the dynamics of the robot to the world model and computes everything else exactly, including the terrain height under the feet. It learns with a horizon of one second and without a critic. On four H100 GPUs, XMimic learns to track all 40 LAFAN1 clips with the Unitree G1 in 0.86 minutes, 3.7 times faster than BlinkMimic on one GPU. XSoma reaches the tracking target that Holosoma's tests set for FastSAC in 0.77 minutes, 12.3 times faster than FastSAC on one GPU, while needing only an eighth of its environment steps.
Source:https://arxiv.org/abs/2611.20452PreviousMaking Koopman Control Guarantees Hold on RobotsNextStochastic Self-Distillation for Flow-Based Vision-Language-Action Models
Related posts

GPT-6.2 Astra and Sol: Cheaper, Shorter Answers, and the Fine Print
0dev.to
I had AI read my entire field, Theoretical Astrophysics
0Hacker News
Nvidia Earnings; Office Convergence; OS Wars, AI Edition
0Stratechery
France Is Blaming Iran for the Fridge Cyberattack
0Schneier on Security
Apple iPhone Duo Gets a New Facial Unlock Option With iOS 27.3 Update
0FOSS Bytes
CMM. The cursed language that never really took off.
0dev.to Watercooler