WAM-Policy:以在策略蒸餾實現四足行走操作的世界動作模型
WAM-Policy: World Action Models with On-Policy Distillation for Quadrupedal Loco-Manipulation
WAM-Policy透過兩階段流程,將世界動作模型轉化為可依語言指令執行四足行走操作的策略。在包含10項模擬任務的QLM-Bench上,遷移策略得分77.0%,OPSD學生模型得分76.7%,取樣速度快14倍;加入任務專屬RL及M-OPD後,得分升至85.0%。研究亦將OPSD學生模型部署於實體Unitree Go2 Air。
Published on Nov 18
Authors:
,
,
,
,
Abstract
Arm-free quadrupeds can perform loco-manipulation, walking on three legs while manipulating with a front leg, yet no existing policy for it follows language instructions. World action models (WAMs) have emerged as effective language-conditioned manipulation policies, but are pretrained for robot arms and sample slowly. WAM-Policy turns one WAM into a quadrupedal loco-manipulation policy via two stages. The first, Cross-Morphology Policy Adaptation and Acceleration, adapts the arm-centric WAM to quadrupeds and distills the transferred policy into a student with one video and two action steps by on-policy self-distillation (OPSD). This student, however, is bounded by its teacher, which only imitates demonstrations. The second stage, Task-Specific Improvement and Merging, therefore tunes the teacher by reinforcement learning (RL) and merges the slow specialists into one few-step student by multi-teacher on-policy distillation (M-OPD). On QLM-Bench, ten simulated tasks with 1,000 demonstrations synthesized without teleoperation, the transferred policy reaches 77.0%, and the OPSD student keeps 76.7% while sampling 14 times faster. Task-specific RL and M-OPD lift it to 85.0%. We also deploy the OPSD student on a real Unitree Go2 Air. WAM-Policy thus achieves a stronger quadrupedal policy at a fraction of the inference cost.
View arXiv page View PDF Project page GitHub 2 Add to collection
Get this paper in your agent:
hf papers read 2611.24011
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.24011 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.24011 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.24011 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co