---
title: "πR²: Reactive Real-time Flow Policies — Enabling High-Frequency Closed-Loop Replanning for Generalist Manipulation Policies"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.26055v1"
permalink: "https://feed.astralor.com/items/itm_83b67ae1bd309a434b1c0072"
published: "2026-07-28T17:59:31.000Z"
score: 78
channel: "ai"
tags: ["GR00T N1.7","reactive real-time control","diffusion forcing","robot manipulation","flow policy"]
---

# πR²: Reactive Real-time Flow Policies — Enabling High-Frequency Closed-Loop Replanning for Generalist Manipulation Policies

## AI commentary

> The highlight of this work is its clever use of diffusion forcing's noise schedule to achieve condition decoupling, allowing large models to maintain expressiveness while gaining real-time responsiveness. It is particularly valuable for researchers and engineers working on robot manipulation policies and real-time control systems, offering a drop-in improvement that could accelerate the deployment of generalist policies in dynamic environments.

## At a glance

Generalist manipulation policies often take the form of action-chunking flow policies built on large pretrained backbones, but they execute open-loop and cannot react to mid-execution sensory input, with replanning limited by latency. This paper proposes πR², leveraging the per-position noise schedule of diffusion forcing to split conditioning into a fast channel (proprioception) and an asynchronously updated slow channel (vision-language features), plus a latency-adaptive flow schedule. Applied to GR00T-N1.7 on an xArm6+XHand platform, πR² achieves roughly 4x faster closed-loop replanning (~25Hz), improving success rates by 23% in simulation and 30% in the real world over the strongest baseline.

## Key points

- Proposes splitting conditioning into a fast channel (proprioception) and a slow channel (vision-language features), enabling the policy to react instantly within a chunk while tolerating stale vision. 
- Designs a latency-adaptive flow schedule that treats in-flight actions as inpainting conditioning, emitting actions in one denoising step per call, allowing one model to adapt to varying hardware latency. 
- Fine-tuned from a pretrained GR00T-N1.7 policy on xArm6+XHand, achieves closed-loop replanning at ~25Hz and significantly boosts success rates. 

## Full text

Generalist manipulation policies increasingly take the form of action-chunking flow policies built on large pretrained backbones. Such chunks run open-loop, so the policy cannot react to sensory input arriving mid-execution, sacrificing \emph{reactivity}. Replanning more often would restore it, but the perception-to-action pipeline (a large backbone plus multiple denoising steps) is too slow: this \emph{latency} forbids frequent replanning and leaves committed actions stale, making such policies ill-suited for dynamic, closed-loop control. We present $π\mathbf{R}^2$, which makes these policies reactive and real-time while retaining large backbones, expressive multi-modal policies, and multi-action prediction. Built on the per-position noise schedule of diffusion forcing, $π\mathbf{R}^2$ contributes two ideas. First, it splits conditioning into a fast channel (proprioception, fresh every tick) and an asynchronously updated slow channel (vision-language features), so the policy reacts to proprioception within a chunk while tolerating stale vision. Second, a latency-adaptive flow schedule treats in-flight actions as inpainting conditioning and emits actions in one denoising step per call, letting one trained model adapt to varying hardware latency. Requiring minimal modification to existing architectures, $π\mathbf{R}^2$ can be finetuned from a pretrained policy: applied to GR00T-N1.7 on a real xArm6+XHand platform, it replans closed-loop roughly $4\times$ faster than the base policy (~$25$Hz on an A5000 GPU), acting on a fresh observation every $40$ms. Across simulation and real-world manipulation tasks, $π\mathbf{R}^2$ improves the success rate by up to $23\%$ in simulation and $30\%$ in the real world over the strongest baseline. Project page: https://pi-r2-flow.github.io/

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_83b67ae1bd309a434b1c0072