# Evo-World：一种通过光流监督进行未来运动预测的轻量级 VLA 模型

> 原文链接：https://robotics.hellobike.com/papers/2026-10-09-2610-12936
> 频道：papers | 更新日期：2026-10-09 | 标签：arxiv, cs.RO
> 核心摘要：Evo-World用光流监督的未来运动预测增强轻量级VLA，并在仿真基准和AgileX真机操控上验证效果。

# Evo-World：一种通过光流监督进行未来运动预测的轻量级 VLA 模型

::: v-pre
> 原文链接：[Evo-World: A Lightweight Vision-Language-Action Model with Future Motion Prediction via Optical-Flow Supervision](https://arxiv.org/abs/2610.12936)（arXiv 2610.12936 · 发布日期：2026-10-09）

**Evo-World: A Lightweight Vision-Language-Action Model with Future Motion Prediction via Optical-Flow Supervision**

Evo-World用光流监督的未来运动预测增强轻量级VLA，并在仿真基准和AgileX真机操控上验证效果。

## 核心要点

- 动机是仅用动作监督不显式鼓励场景演化预期，未来图像预测又混合静态外观。
- 方法以光流监督加入未来运动预测，提供聚焦运动的任务相关预测信号。
- 在Meta-World MT50上成功率91.1%，较非预测基线相对提升13.0%。
- 在AgileX单臂和双臂任务上优于所评估基线，并具更低显存和更高推理效率。

**验证范围与局限**：验证范围为仿真基准、Meta-World MT50，以及AgileX真机单臂和双臂操控任务。

## 英文摘要 (Abstract)

Vision-language-action (VLA) models provide a unified framework for visual understanding, language grounding, and robot control, yet anticipating how the scene will evolve beyond the current observation can provide additional information for control. Action supervision alone does not explicitly encourage such anticipation, while future-image prediction entangles task-relevant motion with largely static appearance. To address these limitations, we introduce Evo-World, a lightweight VLA model that augments policy learning with future motion prediction through optical-flow supervision, thereby providing a task-relevant predictive signal focused on motion rather than appearance. We further design the training procedure to preserve these predictive representations during policy learning, regulating representation diversity while decoupling representation learning from action optimization. Across simulation benchmarks, Evo-World demonstrates strong performance, achieving a tier-averaged success rate of 91.1% on Meta-World MT50 , with a 13.0% relative improvement over the non-predictive baseline. On real-world AgileX robots, Evo-World outperforms the evaluated baselines across single-arm and bimanual manipulation tasks while using only 0.87B parameters and delivering lower GPU memory usage and higher inference efficiency. These results demonstrate that future motion prediction through optical-flow supervision provides an effective and lightweight approach to enhancing the predictive capabilities of VLA models.

作者：Zile Zhong, Yuxin Du, Tao Lin, Haoxiao Wang, Wei Dai, Binhua Zuo, Bo Zhao
:::

## 原始参考来源 (Sources)

- [arXiv 2610.12936：Evo-World: A Lightweight Vision-Language-Action Model with Future Motion Prediction via Optical-Flow Supervision](https://arxiv.org/abs/2610.12936)