---
title: "TOPS: Reshaping Flow Source and Transport for Multi-Task Robot Manipulation"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.36694v1"
permalink: "https://feed.astralor.com/items/itm_47755bc626ebca7a6423795a"
published: "2026-10-27T06:11:55.000Z"
score: 59
channel: "tech"
tags: ["推理效率","多模态","TOPS","Reshaping Flow Source","Transport","Multi-Task Robot Manipulation","Flow-based","Gaussian"]
---

# TOPS: Reshaping Flow Source and Transport for Multi-Task Robot Manipulation

## 速览

Flow-based policies for language-conditioned multi-task manipulation commonly share a single $\textit{Gaussian}$ source prior and a common linear transport path across tasks. However, reliably executing multiple tasks w…

## 关键点

- Flow-based policies for language-conditioned multi-task manipulation commonly share a single $\textit{Gaussian}$ source prior and a common linear transport path across tasks.
- However, reliably executing multiple tasks with distinct motion requirements remains challenging for a shared policy.
- We introduce $\textbf{TOPS}$ ($\textbf{T}$ask-$\textbf{O}$riented $\textbf{P}$riors and $\textbf{S}$chedules), which adapts the flow source prior and interpolation schedule to each task without modifying the network arc…

## 全文

Flow-based policies for language-conditioned multi-task manipulation commonly share a single $\textit{Gaussian}$ source prior and a common linear transport path across tasks. However, reliably executing multiple tasks with distinct motion requirements remains challenging for a shared policy. We introduce $\textbf{TOPS}$ ($\textbf{T}$ask-$\textbf{O}$riented $\textbf{P}$riors and $\textbf{S}$chedules), which adapts the flow source prior and interpolation schedule to each task without modifying the network architecture. TOPS first constructs multimodal task sources from reverse-mapped expert action sequences, allowing language instructions to select where generation begins. Guided by source-target covariance mismatch, it then slows the transition toward expert actions early in denoising and accelerates it later along directions requiring expansion. Under a $\textit{Gaussian}$ endpoint model, our analysis shows that this schedule adjustment can lower an upper bound on velocity-prediction risk. Experiments on LIBERO, LIBERO-Plus, and CALVIN demonstrate improved performance across in-distribution, perturbation and cross-environment settings, alongside better data efficiency. Using one integration step, TOPS raises LIBERO-10 success from $53.44\%$ to $69.67\%$ compared with ten-step Standard Flow Matching (FM), while reducing inference time to approximately one-sixth of the baseline. TOPS also yields consistent gains when transferred to the large-scale flow-based $π_{0.5}$ policy across all four evaluated settings. Real-world experiments further demonstrate improved task success, including an increase from $20\%$ with standard FM to $80\%$ with TOPS on the upper-drawer opening task.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_47755bc626ebca7a6423795a