外观
论文arXiv 2609.123471 个月前
DWMP：利用双世界模型实现人形机器人障碍穿越
针对人形机器人依靠本体与视觉穿越杂乱障碍场的问题，DWMP融合双世界模型表征，并在仿真和Unitree G1真机验证。
宇树 G1原文链接：DWMP: Leveraging Dual World Models for Humanoid Obstacle Traversal（arXiv 2609.12347 · 发布日期：2026-09-11）
DWMP: Leveraging Dual World Models for Humanoid Obstacle Traversal
针对人形机器人依靠本体与视觉穿越杂乱障碍场的问题，DWMP融合双世界模型表征，并在仿真和Unitree G1真机验证。
核心要点
- 现有方法通常未显式考虑本体观测与自我中心视觉观测的不同特性。
- DWMP用Koopman动力学世界模型提取近似线性的本体时序特征。
- RSSM视觉世界模型将自我中心深度观测压缩为保留障碍几何的随机状态。
- 仿真和Unitree G1实验显示，DWMP较基线提升障碍穿越性能。
验证范围与局限：验证范围为仿真和一台Unitree G1人形机器人上的随机障碍布局穿越。
英文摘要 (Abstract)
Humanoid robots must traverse cluttered obstacle fields using onboard proprioceptive and visual observations, yet existing methods usually process multimodal observations without explicitly considering their different characteristics: proprioceptive observations are low-dimensional but governed by highly nonlinear robot dynamics, while egocentric visual observations are high-dimensional, noisy, and redundant. We propose DWMP (Dual World Model Policy), a framework that provides the actor with separate but complementary world-model representations for humanoid obstacle traversal. A Koopman-based dynamics world model lifts proprioceptive observations into a latent space where their temporal evolution is approximately linear, making the dynamics features easier for the actor to learn from. An RSSM-based visual world model compresses egocentric depth observations into compact stochastic states while preserving obstacle-related geometry. The student policy receives the fused latent representation for action generation, combining linearized proprioceptive dynamics with compressed visual perception. Experiments in simulation and on a Unitree G1 humanoid robot show that DWMP improves obstacle traversal performance over baselines and supports real-world deployment under randomized obstacle layouts.
作者：Rong Jin, Jianming Ma, Yue Gao
来源
本页事实对应的公开页面，以原文为准。