外观
论文arXiv 2610.1583317 天前
P-BFM：通过无监督强化学习实现人形机器人控制的感知式行为基础模型
P-BFM将人形控制分解为地形无关意图与地形条件实现，并在复杂地形和Unitree G1零样本迁移中验证。
宇树 G1原文链接：P-BFM: Perceptive Behavioral Foundation Models for Humanoid Control via Unsupervised Reinforcement Learning（arXiv 2610.15833 · 发布日期：2026-10-11）
P-BFM: Perceptive Behavioral Foundation Models for Humanoid Control via Unsupervised Reinforcement Learning
P-BFM将人形控制分解为地形无关意图与地形条件实现，并在复杂地形和Unitree G1零样本迁移中验证。
核心要点
- 现实控制中，同一意图在不同地形下可能需要根本不同动作。
- 前向-后向表示在无地形信息下，将参考、目标和奖励映射到共享意图。
- 感知策略按周围地形实现意图，ERI分离全局运输与行为意图。
- 在挑战地形上优于强基线，冻结策略还支持多种控制任务。
验证范围与局限：验证包括挑战性地形，并零样本迁移到一台搭载机载深度感知的Unitree G1。
英文摘要 (Abstract)
Behavioral foundation models (BFMs) provide humanoids with reusable repertoires of whole-body behaviors; in real-world humanoid control, the same behavioral intent may require fundamentally different motions under different terrain constraints. Covering such variation with terrain-matched demonstrations requires enumerating a combinatorial space of behaviors and terrain geometries. We introduce P-BFM, a perceptive behavioral foundation model that factorizes humanoid control into terrain-invariant intent and terrain-conditioned realization. A forward-backward representation maps motion references, target states, and reward functions into a shared intent space without terrain information, while a perceptive policy learns how to realize each intent under the surrounding terrain geometry. We further identify a complementary limitation of purely latent control: behavioral latents can preserve local motion patterns while losing precise global progress. We therefore introduce Explicit Root Instructions (ERI), which separates global transport (e.g., heading and planar velocity) from behavioral intent, while leaving local whole-body adaptation to the perceptive policy. This decomposition leads to a characteristic capability absent from conventional BFMs: one fixed intent induces different, terrain-appropriate behaviors, including changes in step height, stride, posture, foothold placement, and contacts, without terrain-specific demonstrations. Across challenging terrains, P-BFM improves motion fidelity, root-control precision, and perturbation recovery over strong baselines. A single frozen policy further supports motion tracking, goal reaching, reward inference, teleoperation, and terrain-aware recovery, and transfers zero-shot to a Unitree G1 using onboard depth sensing.
作者：Xue Wang, Yitang Li, Yiming Zhang, Siqin Wang, Junhan Sun, Zhihao Liu, Yaojie Shen, Jingbo Yuan, Hao Zhao, Qingdu Li
来源
本页事实对应的公开页面，以原文为准。