# HWAM模型联合生成状态与动作，LimX OLI抓取成功率达70.6%

> 原文链接：https://robotics.hellobike.com/papers/2026-10-08-2610-12026
> 频道：papers | 更新日期：2026-10-08 | 标签：auto, arxiv
> 核心摘要：针对人形机器人VLA策略执行偏差问题，HWAM模型将本体感知状态作为显式预测目标，通过三条互补条件路径联合生成参考动作与实现状态。在LimX OLI真机测试中，该模型糖果抓取任务成功率达70.6%，显著优于Fast-WAM基线。

# HWAM模型联合生成状态与动作，LimX OLI抓取成功率达70.6%

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[HWAM: Humanoid World Action Model With Joint State--Action Generation](https://arxiv.org/abs/2610.12026)（arXiv 2610.12026）

## 核心内容

针对人形机器人分层控制中VLA/WAM策略参考动作与实际执行存在差距的问题，研究提出HWAM（Humanoid World Action Model）。该模型将机器人执行后的本体感知状态设为显式预测目标，通过联合生成参考动作与实现状态，直接将执行运动监督纳入动作学习过程，解决了传统方法难以关联动作与物理结果的痛点。

HWAM采用三条互补条件路径训练：Policy路径仅基于当前观测联合去噪状态-动作轨迹以匹配部署条件；前向动力学建模（FDM）基于动作和执行后状态预测未来视觉观测；逆动力学建模（IDM）从视觉转换重构关节轨迹。在LimX OLI人形机器人实机验证中，HWAM在糖果抓取任务成功率达70.6%，大幅超越Fast-WAM的43.3%。

## 关键看点

- **核心机制**：将执行后本体感知状态作为显式预测目标，联合生成参考动作与实现状态，消除策略输出与物理执行的语义鸿沟
- **训练架构**：构建Policy、前向动力学FDM及逆动力学IDM三条互补路径，连接策略参考、实际身体运动与视觉结果
- **真机性能**：在LimX OLI人形机器人糖果抓取任务中成功率达70.6%，较Fast-WAM基线提升27.3个百分点

## 工程与产业观察

HWAM证明了在人形机器人具身智能训练中，显式建模本体状态反馈比单纯依赖视觉预测更能有效弥合Sim-to-Real或Policy-to-Control的执行差距。这种将底层动力学约束融入上层VLA模型的方法，为提升复杂操作任务的鲁棒性提供了可复现的工程范式，尤其适用于对全身平衡与接触力有严格要求的通用人形机器人场景。

## 英文摘要 (Abstract)

Humanoid robots are a promising platform for general-purpose manipulation. Recent Vision-Language-Action (VLA) policies learn actions directly from multimodal observations, while World Action Models (WAMs) further incorporate future visual prediction to improve action generation. However, in hierarchical humanoid systems, VLA and WAM policies output reference actions that are subsequently realized through whole-body control, robot dynamics, balance, and contact. This hierarchy creates an action--execution gap: the reference produced by the policy can differ from the motion realized by the robot. Without explicitly modeling the realized body state, future visual prediction must jointly explain scene evolution and discrepancies between reference actions and executed motion, making it difficult to associate an action with its physical outcome. We propose HWAM, a Humanoid World Action Model with joint state--action generation, which makes the robot's post-execution proprioceptive state an explicit prediction target. By jointly generating reference actions and their realized body states, HWAM directly incorporates supervision of executed motion into action learning. HWAM is trained through three complementary conditional paths. The Policy path jointly denoises state--action trajectories conditioned only on current observations, matching deployment conditions. Forward Dynamics Modeling (FDM) predicts future visual observations conditioned on actions and post-execution states, while Inverse Dynamics Modeling (IDM) reconstructs the joint trajectory from visual transitions. Together, these paths connect policy references, realized body motion, and visual outcomes. HWAM achieves the highest success rate among evaluated baselines on three real-robot tasks on the LimX OLI humanoid. On Candy Picking, HWAM achieves a 70.6% success rate, compared with 43.3% for Fast-WAM.

作者：Yan Yang, Jikun Rong, Minzhao Zhu, Zheyi Zhao, Qirui Hu, Zihan Lan, Weixin Mao, Yinhao Li, Zhen Fu, Hua Chen
:::

## 原始参考来源 (Sources)

- [arXiv 2610.12026：HWAM: Humanoid World Action Model With Joint State--Action Generation](https://arxiv.org/abs/2610.12026)