# SPEAR：用于 VLM 引导机器人操作的带自适应奖励的选择性偏好获取

> 原文链接：https://robotics.hellobike.com/papers/2026-10-15-2610-21621
> 频道：papers | 更新日期：2026-10-15 | 标签：arxiv, cs.RO
> 核心摘要：SPEAR通过可区分性查询选择和自适应奖励转换，提升VLM偏好标注效率，并在操控基准与真实硬件上验证。

# SPEAR：用于 VLM 引导机器人操作的带自适应奖励的选择性偏好获取

::: v-pre
> 原文链接：[SPEAR: Selective Preference Elicitation with Adaptive Rewards for VLM-Guided Robotic Manipulation](https://arxiv.org/abs/2610.21621)（arXiv 2610.21621 · 发布日期：2026-10-15）

**SPEAR: Selective Preference Elicitation with Adaptive Rewards for VLM-Guided Robotic Manipulation**

SPEAR通过可区分性查询选择和自适应奖励转换，提升VLM偏好标注效率，并在操控基准与真实硬件上验证。

## 核心要点

- VLM可自动为机器人操作偏好标注，但推理成本高，且常在视觉困难比较中选择弃答。
- SPEAR以可区分性感知查询选择降低弃答，并用自适应奖励转换先引导探索再偏好细化。
- 在操控基准上，SPEAR平均成功率达88.9%，较基线高23.3个百分点。
- 在接触丰富任务中，SPEAR显著减少弃答和训练耗时，并可在真实硬件上全在线学习。

**验证范围与局限**：验证范围包括操控基准以及真实硬件上的三个 Mobile ALOHA 操作任务。

## 英文摘要 (Abstract)

Recent Vision-Language Models (VLMs) enable automated preference labeling for robotic manipulation, yet their deployment remains impractical since each query incurs substantial inference cost, while VLMs frequently abstain on visually challenging comparisons. We propose SPEAR, a framework that transforms VLMs into efficient preference oracles via two synergistic mechanisms. First, we design distinguishability-aware query selection to reduce abstention rates by targeting only informative and distinguishable comparisons. Second, we deploy an adaptive reward transition that bootstraps exploration with VLM-synthesized guidance before preference-based refinement. Experiments on the manipulation benchmarks demonstrate that SPEAR achieves 88.9% average success, outperforming baselines by 23.3 percentage points, while significantly reducing abstention and wall-clock training time on contact-rich tasks. SPEAR learns three Mobile ALOHA manipulation tasks fully online on real hardware, demonstrating end-to-end real-world applicability. By addressing query efficiency and exploration challenges, SPEAR establishes VLMs as practical preference oracles for scalable robot learning without manual reward engineering.

作者：Zewen Wu, Ruizhe Liu, Pei Zhou, Feng Chen, Yanchao Yang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.21621：SPEAR: Selective Preference Elicitation with Adaptive Rewards for VLM-Guided Robotic Manipulation](https://arxiv.org/abs/2610.21621)