# VAMPS：基于采样式规划的视觉与运动策略

> 原文链接：https://robotics.hellobike.com/papers/2026-10-04-2610-05331
> 频道：papers | 更新日期：2026-10-04 | 标签：arxiv, cs.RO
> 核心摘要：VAMPS用MPPI无人工示教生成监督，训练本体感知和视觉运动策略，并在仿真迁移与真机任务上验证。

# VAMPS：基于采样式规划的视觉与运动策略

::: v-pre
> 原文链接：[VAMPS: Visual and Motor Policies from Sampling-Based Planning](https://arxiv.org/abs/2610.05331)（arXiv 2610.05331 · 发布日期：2026-10-04）

**VAMPS: Visual and Motor Policies from Sampling-Based Planning**

VAMPS用MPPI无人工示教生成监督，训练本体感知和视觉运动策略，并在仿真迁移与真机任务上验证。

## 核心要点

- 学习物理机器人策略面临采集成本高、策略探索可能不安全的问题。
- 框架用MPPI训练可复用策略，支持仿真迭代训练和真机数据离线训练两种模式。
- 本体感知策略中，策略热启动MPPI，终端价值与IQL critic辅助规划和更新。
- 实验显示迭代细化优于冻结MPPI数据一次训练，并演示抓放与力感知擦白板。

**验证范围与局限**：验证范围包括仿真训练后迁移到Unitree Go2的运动策略，以及Flexiv Rizon 10S上的真机视觉运动任务。

## 英文摘要 (Abstract)

Learning robot policies directly on physical systems remains difficult because data collection is costly and policy exploration can be unsafe. We introduce Visual and Motor Policies from Sampling-Based Planning (VAMPS), a framework that uses Model Predictive Path Integral (MPPI) control to train reusable policies without human demonstrations. VAMPS supports two training modes. For one-step proprioceptive policies, it operates iteratively in simulation: the policy warm-starts MPPI, and the refined trajectories provide new supervision as the policy changes. A learned terminal value improves short-horizon planning, while an Implicit Q-Learning (IQL) critic guides the policy update. Iterative refinement outperforms training once on frozen MPPI data, and we transfer the learned locomotion policy to a Unitree Go2. For visuomotor policies, VAMPS operates directly from real-robot data. MPPI uses task-specific state estimates to plan and execute trajectories while recording RGB and sensor observations on a Flexiv Rizon 10S. Action Chunking with Transformers predicts action chunks, reducing the effective prediction horizon, and is trained offline on this fixed dataset. We demonstrate visuomotor pick-and-place and force-aware whiteboard erasing. In the latter task, the policy additionally observes the measured $6$-D wrench and desired normal force. These results show that VAMPS can learn policies either in simulation followed by hardware transfer or directly from autonomously collected real-robot data.

作者：Mohamed Yassine Kabouri, Pietro Noah Crestaz, Quang-Nam Nguyen, Qilong Cheng, Ludovic Righetti, Nicolas Mansard
:::

## 原始参考来源 (Sources)

- [arXiv 2610.05331：VAMPS: Visual and Motor Policies from Sampling-Based Planning](https://arxiv.org/abs/2610.05331)