AI Pulse
📄 论文解读

三条腿走路,前腿干活

机器狗终于能听懂人话干活了:三条腿站着,腾出一条前腿当手用。难点在于,会听指令的「世界动作模型」都是照着机械臂练的,直接搬给四条腿的狗水土不服,而且慢。研究者分两步:先把机械臂那套迁移到狗身上,再让学生模型用「边跑边学」的方式蒸馏,把原来要跑很多步的推理压成一步视频加两步动作,快了 14 倍,成功率几乎不掉(77.0% 对 76.7%)。但学生再强也超不过只会模仿的老师,于是第二步用强化学习把老师按任务练强,再把几个慢专家合并成一个快学生,成功率提到 85.0%。他们还在真机 Unitree Go2 Air 上跑了这个快学生。它不是你明天能买到的产品,但「让四足机器人腾一条腿干活、还听得懂指令」这件事,从论文里的仿真走向了真机。

📄 原文摘要(英文)

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.

arXiv 原文

订阅 AI Pulse

每天 08:00 · 12:30 · 18:30 · 23:50 更新