Imperfection for Precision: Upcycling Imperfect Data for High-Precision Robotic Manipulation

2026-09-22

AI Summary

为解决高精度机器人操作中高质量数据收集成本高的问题，提出ε4P方法，通过利用低精度目标任务数据和高精度不匹配任务数据提升模型性能。

Abstract

Training vision-language-action (VLA) models for high-precision manipulation typically requires task-specific, high-quality data (e.g., teleoperation), which is slow and expensive to collect. To reduce this burden without compromising manipulation precision, we propose $\varepsilon$4P (Imperfection for Precision), a simple yet effective method that "upcycles" two otherwise discarded data sources: (1) low-precision data from the target task and (2) high-precision data from mismatched tasks. Rather than naively mixing these imperfect data sources throughout co-training, $\varepsilon$4P controls where each source contributes along the flow-matching trajectory. Specifically, low-precision, target-task data is used at high noise to preserve high-level task context and high-precision, task-mismatched data is used at low noise to transfer low-level action precision. Through real-robot experiments on both sub-millimeter, high-precision tasks and coarse-grained tasks, we demonstrate that the proposed method (1) effectively leverages additional imperfect data to improve policy performance by up to 31.7 percentage points, and (2) can replace an equal amount of task-specific, high-quality data with an average performance drop of only 4.2 percentage points. Overall, $\varepsilon$4P points toward a scalable paradigm for high-precision manipulation, in which heterogeneous, imperfect data can be systematically repurposed to reduce reliance on costly task-specific, high-quality data. More details are available at https://varepsilon4p.github.io/.

Problem

• high-precision manipulation
• vision-language-action models
• task-specific data
• high-quality data

Innovation

• Imperfection for Precision
• upcycling imperfect data
• high-precision manipulation
• flow-matching trajectory
• low-precision and high-precision data