论文/arXiv 2610.14997·18 天前

用于实时异步 VLA 执行的屏障约束引导

针对异步VLA动作块边界错位，FreeBar以CBF启发约束进行免训练闭式校正，并在Kinetix、RoboCasa和真实机器人上验证。

AI 整理

• 本体 SDK 与控制
• 具身模型
• 端侧部署

原文链接：Barrier-Constrained Guidance For Real-time Asynchronous VLA Execution（arXiv 2610.14997 · 发布日期：2026-10-10）

Barrier-Constrained Guidance For Real-time Asynchronous VLA Execution

针对异步VLA动作块边界错位，FreeBar以CBF启发约束进行免训练闭式校正，并在Kinetix、RoboCasa和真实机器人上验证。

核心要点

• 异步执行可支持实时预测下一动作块，但会与已提交动作流产生边界错位。
• FreeBar将flow-based VLA的块对齐表述为动作空间屏障引导约束，并闭式求解校正。
• 在Kinetix、RoboCasa和多种真实机器人平台上，平均成功率较朴素异步执行提升10%--15%。
• FreeBar作为通用推理插件，无需训练，并在不同延迟、基础策略和超参数设置下保持鲁棒。

验证范围与局限：验证范围包括Kinetix、RoboCasa、多种真实机器人平台和多个VLA骨干。

英文摘要 (Abstract)

While asynchronous execution enables VLA models to operate in real-time environments by predicting the next chunk during execution, it inevitably introduces boundary misalignment with the committed action stream. Existing delay-aware solutions address this at the prohibitive cost of extensive retraining, architectural modifications, or fixed-prefix inpainting that inflates computation when low latency is vital. To address these problems, we propose FreeBar, a training-free real-time inference plugin that enables robust asynchronous execution with only marginal additional inference cost by casting chunk alignment in flow-based VLAs as barrier-guided action-space constraint. Specifically, FreeBar introduces a lightweight Control Barrier Function (CBF)-inspired consistency constraint between consecutive action chunks and solves the resulting correction in closed form, avoiding costly backpropagation through the VLA action head. By progressively tightening the consistency bound during generation, FreeBar aligns generated chunks with the committed execution stream while preserving early-stage generative and within-chunk future action flexibility,. Across Kinetix, RoboCasa, and diverse real-world robotic platforms with multiple VLA backbones, FreeBar improves success rates over naive asynchronous execution by 10%--15% on average, with larger gains in highly dynamic scenarios. It also preserves real-time computational efficiency, decreasing inference latency per action chunk over 45% than RTC. Additionally, as a universal plugin, FreeBar remains robust across distinct latency environments, base policies, and hyperparameter settings.

作者：Wenbo Yu, Jifan Li, Wenke Xia, Yuchen Li, Yizhuo Zhang, Pei Ren, Zhengping Che, Di hu

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.14997：Barrier-Constrained Guidance For Real-time Asynchronous VLA Execution访问 2026-10-21