← 研踪 PaperTrailCVF · CVPR 2026:cvf:5cd98792408b4a2916afd93456bd9330 · 记录 #1
Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer
Xue, HaoruHe, TairanWang, ZiBen, QingweiXiao, WenliLuo, ZhengyiDa, XingyeCastañeda, FernandoShi, GuanyaSastry, ShankarFan, LinxiZhu, Yuke 来源日期(仅到年份) 2026
来源记录日期 2026
雷达观测 2026-11-05 04:01
摘要
Recent progress in GPU-accelerated, photorealistic simulation has opened a scalable data-generation path for robot learning, where massive physics and visual randomization allow policies to generalize beyond curated environments. Building on these advances, we develop a teacher-student-bootstrap learning framework for vision-based humanoid loco-manipulation, using articulated-object interaction as a representative high-difficulty benchmark. Our approach introduces a staged-reset exploration strategy that stabilizes long-horizon privileged-policy training, and a GRPO-based fine-tuning procedure designed to mitigate partial observability and improve closed-loop consistency in sim-to-real RL. Trained entirely on synthetic simulation data, the resulting policy achieves robust zero-shot performance across diverse articulated objects--including multiple door types--and outperforms human teleoperators by up to 31.7% in task completion time under the same whole-body control stack. This represents the first humanoid sim-to-real policy capable of diverse articulated loco-manipulation from pure RGB perception.
论文发现出处
这些页面提供论文线索,不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer
Recent progress in GPU-accelerated, photorealistic simulation has opened a scalable data-generation path for robot learning, where massive physics and visual randomization allow policies to generalize beyond curated environments. Building on these advances, we develop a teacher-student-bootstrap learning framework for vision-based humanoid loco-manipulation, using articulated-object interaction as a representative high-difficulty benchmark. Our approach introduces a staged-reset exploration strategy that stabilizes long-horizon privileged-policy training, and a GRPO-based fine-tuning procedure designed to mitigate partial observability and improve closed-loop consistency in sim-to-real RL. Trained entirely on synthetic simulation data, the resulting policy achieves robust zero-shot performance across diverse articulated objects--including multiple door types--and outperforms human teleoperators by up to 31.7% in task completion time under the same whole-body control stack. This represents the first humanoid sim-to-real policy capable of diverse articulated loco-manipulation from pure RGB perception.
查看此版本解读 →查看此版本原文 ↗