论文/arXiv 2610.08150·22 天前

ViDAL：面向 Vision-Language-Action 模型的视觉动态扎根动作潜在空间

ViDAL通过将连续动作潜变量与未来场景视觉动态对齐，改进VLA动作表示，并在LIBERO、RoboTwin 2.0和真实机器人上验证。

AI 整理

• 具身模型

Franka FR3

原文链接：ViDAL: A Visual Dynamics-Grounded Action Latent Space for Vision-Language-Action Models（arXiv 2610.08150 · 发布日期：2026-10-06）

ViDAL: A Visual Dynamics-Grounded Action Latent Space for Vision-Language-Action Models

ViDAL通过将连续动作潜变量与未来场景视觉动态对齐，改进VLA动作表示，并在LIBERO、RoboTwin 2.0和真实机器人上验证。

核心要点

• 现有动作表示主要建模动作轨迹，对动作引发的视觉动态考虑有限。
• ViDAL训练Action VAE重构动作片段，并使潜变量对齐未来场景动态。
• 该Action VAE可作为插件动作接口兼容多种VLA架构，并支持可选未来视频预测。
• ViDAL在LIBERO达98.1%平均成功率，并提升RoboTwin 2.0及真实平台成功率。

验证范围与局限：验证范围包括LIBERO、RoboTwin 2.0的50个双臂任务，以及真实单臂Franka和双臂ARX平台。

英文摘要 (Abstract)

Vision-Language-Action (VLA) models have become a central paradigm for robot policy learning, which predict actions in three forms: raw action chunks, discrete action tokens, or continuous action latents. However, existing action representations primarily model action trajectories, with limited consideration of the visual dynamics induced by these actions. We introduce ViDAL, a Visual Dynamics-grounded Action Latent Space that anchors continuous action latents in the future visual dynamics of the scene. Specifically, ViDAL learns action latent space by training an Action Variational Autoencoder (Action VAE) to reconstruct action chunks while aligning its latent with future scene dynamics. When integrated into downstream robot policies, the proposed Action VAE serves as a plug-in action interface compatible with multiple VLA architectures and enables optional future-video prediction as an additional capability. Empirically, ViDAL outperforms competitive baselines on LIBERO with 98.1% average success, improves a multi-task $π_{0.5}$ policy on RoboTwin 2.0 from 54.3% to 65.5% (Clean) and from 33.2% to 43.1% (Random) success rates over 50 dual-arm tasks, and yields 20.0% and 23.4% absolute success-rate gains on real-world single-arm Franka and dual-arm ARX robot platforms.

作者：Yuan Xu, Yixiang Chen, Qisen Ma, Jiabing Yang, Peiyan Li, Kai Wang, Jianhua Yang, Jianlou Si, Jun Huang, Jing Liu

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.08150：ViDAL: A Visual Dynamics-Grounded Action Latent Space for Vision-Language-Action Models访问 2026-10-21