# 用于样本高效模型预测控制的 Hybrid Feedback Sampling

> 原文链接：https://robotics.hellobike.com/papers/2026-08-19-2608-19443
> 频道：papers | 更新日期：2026-08-19 | 标签：arxiv, cs.RO
> 核心摘要：针对高维和开环不稳定系统中采样式MPC样本效率差的问题，提出FS-MPC，并在接触丰富及真实人形机器人任务上验证。

# 用于样本高效模型预测控制的 Hybrid Feedback Sampling

::: v-pre
> 原文链接：[Hybrid Feedback Sampling for Sample-Efficient Model Predictive Control](https://arxiv.org/abs/2608.19443)（arXiv 2608.19443 · 发布日期：2026-08-19）

**Hybrid Feedback Sampling for Sample-Efficient Model Predictive Control**

针对高维和开环不稳定系统中采样式MPC样本效率差的问题，提出FS-MPC，并在接触丰富及真实人形机器人任务上验证。

## 核心要点

- 采样式MPC在高维、开环不稳定系统中所需样本随时域指数增长，易效率低且数值不稳。
- FS-MPC用优化反馈策略实现最优采样提议分布，并以混合采样平衡局部与全局搜索。
- 理论分析表明，混合采样比标准MPPI收敛更快，且比标准反馈采样最优性更好。
- 在类人移动操作和灵巧操作等接触丰富任务中，FS-MPC处理了标准采样法困难的动态不稳定任务。

**验证范围与局限**：验证范围包括接触丰富控制任务，以及真实世界人形机器人行走和操作任务。

## 英文摘要 (Abstract)

Thanks to its parallelizability and flexibility, sampling-based Model Predictive Control (MPC) has become widely popular for controlling real-world robotic systems. However, for high-dimensional and open-loop unstable dynamical systems, the required number of samples to improve the control sequence will grow exponentially with the horizon, leading to poor sample efficiency and numerical instability. This paper investigates the instability of shooting methods in sampling-based MPC and shows that the optimal sampling proposal distribution can be realized by sampling with an optimized feedback policy. We refer to this algorithm as Feedback Sampling MPC (FS-MPC). FS-MPC involves a hybrid sampling design which balances local and global search based on the system stability and the available computation budget. Our theoretical analysis shows that our hybrid sampling approach achieves faster convergence than standard MPPI and better optimality than standard feedback sampling. Empirically, in diverse contact-rich control tasks like humanoid loco-manipulation and dexterous manipulation, we show that FS-MPC successfully tackles dynamically unstable tasks where standard sample-based approaches struggle, and strictly outperforms feedback policies alone. Finally, we validate our method on humanoid robot locomotion and manipulation tasks in the real world.

作者：Chaoyi Pan, Zeji Yi, John Z. Zhang, Zachary R. Manchester, Guannan Qu, Guanya Shi
:::

## 原始参考来源 (Sources)

- [arXiv 2608.19443：Hybrid Feedback Sampling for Sample-Efficient Model Predictive Control](https://arxiv.org/abs/2608.19443)