WEVO: World Model-Enabled VLA Optimization for Whole-Body Loco-Manipulation
Organizations: Amazon · Stanford University · The University of Texas at Austin
Abstract
Reinforcement learning (RL) can improve vision-language-action (VLA) policies beyond imitation, but humanoid exploration is unsafe and simulator RL can exploit residual sim-to-real gaps. We present WEVO, a teleoperation-free framework for post-training a whole-body humanoid VLA in an action-conditioned video world model (WM). Simulated manipulation and locomotion play data improve contact-dynamics and viewpoint-change prediction. A VLA trained on synthetic demonstrations collects 20 autonomous real robot rollouts per task to align the WM with deployment observations. The VLA, whole-body controller (WBC), and video WM then form a closed-loop RL environment with dense progress rewards. Across three real robot tasks, play data improves every evaluated WM metric and downstream policy success; video WM RL raises mean success from 23.3% to 75.0%, compared with 48.3% for real robot RL. We therefore leverage the complementary strengths of both environments: simulation provides policy initialization and broad coverage, while the video WM offers a deployment-aligned environment for policy improvement. Project website: https://qianzhong-chen.github.io/wevo.github.io/.
Figures & tables
| Task | Variant | PSNR | iPSNR | SSIM | LPIPS | FID |
|---|---|---|---|---|---|---|
| PNP | Base | 20.22 | 15.12 | 0.75 | 0.24 | 32.61 |
| Play | 21.46 | 16.71 | 0.77 | 0.23 | 30.97 | |
| PTP | Base | 18.38 | 14.96 | 0.70 | 0.29 | 33.08 |
| Play | 19.08 | 15.86 | 0.71 | 0.28 | 31.97 | |
| Basket | Base | 17.70 | 13.06 | 0.67 | 0.30 | 37.54 |
| Play | 18.55 | 14.07 | 0.68 | 0.29 | 37.42 |
| Baselines Method PNP PTP Basket BC 40% 20% 10% Real RL 60% 45% 40% Sim RL 30% 0% 0% VLAW 45% 20% 35% WMPO 55% 30% 35% | RL Algorithms Method PNP PTP Basket AWR 75% 70% 70% ReinFlow 60% 50% 45% DICE-RL 85% 75% 65% Ablations Sparse 65% 40% 30% Offline 70% 55% 50% w/o Play 70% 65% 55% |
Humanoid Loco-Manipulation
Humanoid loco-manipulation studies how robots coordinate walking, balance, and whole-body interaction to move and handle objects.
See all 99 papers