# LIBERO-PeRM：个性化机器人操作基准测试

> 原文链接：https://robotics.hellobike.com/papers/2026-10-15-2610-22372
> 频道：papers | 更新日期：2026-10-15 | 标签：arxiv, cs.RO
> 核心摘要：提出LIBERO-PeRM，用受控仿真偏好学习基准评测具身智能体的个性化操作，并在五个任务套件上实验。

# LIBERO-PeRM：个性化机器人操作基准测试

::: v-pre
> 原文链接：[LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation](https://arxiv.org/abs/2610.22372)（arXiv 2610.22372 · 发布日期：2026-10-15）

**LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation**

提出LIBERO-PeRM，用受控仿真偏好学习基准评测具身智能体的个性化操作，并在五个任务套件上实验。

## 核心要点

- 通用家用机器人需要个性化，但PeRM缺少区分任务完成与偏好满足的受控基准。
- 基准限定语言可表达、可自动评估且不改变任务目标的偏好，覆盖运动、技能和用户画像选择。
- 流程生成有无偏好的配对演示，构建五个任务套件共312项任务及偏好满足指标。
- 实验显示当前VLA零样本个性化困难，SFT可学习偏好；代码、数据集和演示已开放。

**验证范围与局限**：验证范围为LIBERO仿真中的五个任务套件，偏好泛化、分解和冲突处理仍然困难。

## 英文摘要 (Abstract)

Personalization is essential for general-purpose robots to transition into household environments and achieve true practicality. While general robotic manipulation has been extensively studied, personalized robotic manipulation (PeRM) lacks a controlled benchmark for separating task completion from preference satisfaction. We introduce LIBERO-PeRM, a benchmark for preference learning in embodied agents. LIBERO-PeRM studies five questions: 1) how policies follow preferences in zero-shot settings; 2) how they learn single preferences from demonstrations; 3) how efficiently they acquire preferences as demonstrations increase; 4) how learned preferences generalize across layouts and tasks; and 5) how policies compose preferences and behave under conflicts. We propose a controlled formulation and taxonomy of observable preferences in simulation, covering motion, skill, and user-profile choices. This formulation is restricted to language-expressible preferences that can be instantiated in LIBERO without changing the task goal, evaluated automatically, and reused across tasks. Building on LIBERO, our procedural pipeline generates paired demonstrations with and without preferences. We create five task suites (312 tasks) with high-quality demonstrations, rich metadata, and preference-satisfaction metrics. Experiments show that current VLA policies struggle with zero-shot personalization, while SFT makes preferences learnable. Mixed training achieves better no-preference retention than sequential adaptation and improves performance with contextual prompts compared with preference-only training, but can weaken motion-preference learning; preference generalization, decomposition, and conflict handling remain difficult. The code, datasets, and demos can be found on the project website: https://libero-perm.github.io/.

作者：Zhixu Li, Keqian Tang, Litian Gong, Jingyu Yao, Wenqian Zhang, Tianze Xu, Zehao Wang, Yuping Wang, Junge Zhang, Jiachen Li
:::

## 原始参考来源 (Sources)

- [arXiv 2610.22372：LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation](https://arxiv.org/abs/2610.22372)