# Verify2Act框架：潜空间验证使机械臂语言操作成功率达83.3%

> 原文链接：https://robotics.hellobike.com/papers/2026-11-20-2611-25243-59175ac7
> 频道：papers | 更新日期：2026-11-20 | 标签：auto, arxiv
> 核心摘要：针对VLM操作规划缺乏物理接地问题，提出Verify2Act模块化验证框架。通过DINOv2潜空间世界模型与双头Critic分离语义提案与物理验证，低成本机械臂在6项任务中成功率达83.3%，较纯VLM提升30个百分点，且消除规划致错。

# Verify2Act框架：潜空间验证使机械臂语言操作成功率达83.3%

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[Verify2Act: Critic-Guided Latent World Models for Verifying Language-Conditioned Manipulation Plans](https://arxiv.org/abs/2611.25243)（arXiv 2611.25243）

## 核心内容

针对视觉语言模型（VLM）生成多步操作计划时缺乏场景变化接地模型、像素级世界模型推理慢且长程漂移的痛点，研究团队提出Verify2Act模块化验证框架。该系统将语义动作提案与潜在物理验证解耦，在低成本机械臂上仅使用数字孪生数据训练世界模型与Critic。实测显示，在6项语言条件操作任务中成功率达83.3%，显著优于无架构改进的潜空间模型（61.7%）、纯VLM（53.3%）及像素扩散模型（46.7%）。

技术上，V2A-WM基于Flow-matching扩展，引入Cross-attention动作接地与因果时序历史窗口，在DINOv2特征空间想象计划；双头Critic在执行前检查想象轨迹的时序一致性与目标满足度。系统实现了执行计划的100%验证覆盖，所有失败均源于底层抓取滑脱而非规划错误。在CALVIN仿真基准中，其五任务链成功率居首，且反思式VLM调用次数仅为像素扩散验证方法的1/30，大幅降低推理开销。

## 关键看点

- **架构创新**：采用V2A-WM潜空间世界模型配合双头Critic，在DINOv2特征空间进行物理验证，实现语义提案与执行校验解耦
- **性能跃升**：低成本机械臂6项语言操作任务成功率83.3%，较纯VLM基线提升30%，较像素扩散世界模型提升36.6%
- **零规划致错**：系统对执行计划实现100%验证覆盖，所有失败案例均为底层抓取或放置滑脱，彻底消除高层规划逻辑错误
- **推理高效**：CALVIN仿真五任务链成功率最优，反思式VLM调用量仅为像素扩散验证方法的1/30，显著降低长程任务算力成本

## 工程与产业观察

该工作验证了“语义提案+潜空间物理验证”范式的有效性，解决了VLM落地具身操作时的幻觉与长程漂移难题。仅依赖数字孪生数据训练即可在真机实现高成功率与零规划致错，为低成本机械臂接入大模型提供了可复现的工程路径，对缓解Sim-to-Real Gap及降低端侧推理负载具有重要参考价值。

## 英文摘要 (Abstract)

Vision-Language Models (VLMs) can propose multi-step manipulation plans, but they have no grounded model of how a scene will change, and the pixel-level world models that could check those plans are slow and drift over long horizons. We present Verify2Act, a modular verification framework that separates semantic action proposal from latent physical verification. A VLM proposes candidate plans, a latent world model (V2A-WM) imagines each of them in the DINOv2 feature space, and a dual-head critic checks the imagined rollouts for temporal consistency and goal satisfaction before anything is executed. V2A-WM extends recent flow-matching world models with cross-attention action grounding and a causal temporal history window. We deploy the full system on a low-cost robot arm, training the world model and critic only on data generated in a digital twin. Across six language-conditioned tasks, Verify2Act reaches 83.3\% task success, compared with 61.7\% for a latent world model without our architectural changes, 53.3\% for the VLM alone, and 46.7\% for a pixel-diffusion world model. It verified every plan it executed and incurred no planning-induced failures: all of its failed episodes were caused by low-level grasp or placement slips. In simulation, Verify2Act obtains the highest five-task chain success on CALVIN among the compared baselines with 30$\times$ fewer reflective VLM calls than pixel-diffusion verification, and the highest success on cluttered nut assembly.

作者：Chrisantus Eze, Christopher Crick
:::

## 原始参考来源 (Sources)

- [arXiv 2611.25243：Verify2Act: Critic-Guided Latent World Models for Verifying Language-Conditioned Manipulation Plans](https://arxiv.org/abs/2611.25243)