外观
论文arXiv 2610.1200720 天前
REACT框架：滚动去噪与双解耦提升VLA模型实时反应性
本文由 AI 根据公开内容整理，可能有误，请以原文为准：REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models（arXiv 2610.12007）
核心内容
针对Flow-based视觉-语言-动作（VLA）模型在分块控制中面临的长时程平滑性与高频重规划反应性之间的根本矛盾，研究团队提出REACT框架。该方法旨在不牺牲长horizon上下文的前提下增强模型反应能力，在RoboTwin 2.0仿真基准及涵盖双臂操作、动态控制的真实机器人任务中验证有效，相比频繁重规划和异步基线，显著提高了任务成功率并降低了反应延迟，同时生成更平滑的运动轨迹。
技术上，REACT采用滚动去噪机制维护持久动作缓冲区，利用交错flow时间步，每步基于最新观测对全horizon去噪，执行最干净动作块并将部分优化后的未来块前移、尾部追加新噪声，使每个执行块经多次观测精炼。为支持实时控制，引入双解耦架构分离感知、VLM编码、DiT去噪与动作执行模块，突破算力约束实现高频观测更新与动作流式传输，解决了传统VLA模型在物理交互中的滞后与不连续问题。
关键看点
- 滚动去噪机制：维护持久动作缓冲与交错时间步，每步基于最新观测精炼全horizon，执行块经多次迭代优化，兼顾长程上下文与瞬时反应性
- 双解耦系统架构：将感知、VLM编码、DiT去噪与执行四模块解耦，支持高频观测更新与动作流式传输，解决算力约束下的实时控制瓶颈
- 性能验证指标：在RoboTwin 2.0仿真及真机双臂/动态任务中，相比频繁重规划与异步基线，显著提升任务成功率并降低反应延迟，轨迹更平滑
工程与产业观察
REACT为Flow-based VLA落地提供了关键工程范式：通过算法层面的滚动推理与系统层面的流水线解耦，有效弥合了生成式策略模型与高频物理控制间的鸿沟。该方案证明了在不增加模型参数量的前提下，仅靠推理架构优化即可大幅提升具身智能体的动态响应能力，对VLA模型的端侧实时部署具有重要参考价值。
英文摘要 (Abstract)
Flow-based vision-language-action (VLA) models generate action chunks for temporally coherent robot motion, but chunked control creates a fundamental closed-loop trade-off: long chunks provide smooth execution, whereas frequent replanning improves reactivity at the cost of action discontinuities. We introduce REACT, a rolling-denoising framework that makes flow-based VLAs more reactive while preserving long-horizon context. Instead of regenerating entire action chunks from scratch, REACT maintains a persistent action buffer with staggered flow timesteps. At each control step, the full horizon is denoised using the latest observation, the cleanest action block is executed, partially refined future blocks are shifted forward, and fresh noise is appended to the tail. As a result, each executed action block is refined across multiple recent observations before deployment. To support real-time control, we further introduce dual decoupling, which separates sensing, VLM encoding, DiT denoising, and action execution, enabling high-frequency observation updates and action streaming under practical compute constraints. Across the RoboTwin 2.0 simulation benchmark and real-world tasks spanning bimanual manipulation and dynamic control on multiple robot platforms, REACT improves task success and reduces reaction latency while producing smoother trajectories than frequent-replanning and asynchronous baselines.
作者：Houlong Xiong, Zhenqi Qiu, Zechen Wang, Suohang Zhang, Yiyu Ren, Wanting Xu, Hongfei Niu, Chengyang He, Ge Sun, Ran Cheng, Qian Zhu
来源
本页事实对应的公开页面，以原文为准。