外观
论文arXiv 2610.0533124 天前
VAMPS：基于采样式规划的视觉与运动策略
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。
宇树 Go2原文链接：VAMPS: Visual and Motor Policies from Sampling-Based Planning（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
来源
本页事实对应的公开页面，以原文为准。