arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.15134cs.RO
收藏

面向机器人操作的上下文学习：考虑混淆的视觉语言模型

Confusion-Aware In-Context-Learning for Vision-Language Models in Robotic Manipulation

Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）；Shenzhen Bao'an Middle School（深圳宝安中学）

Yayun He, Zuheng Kang, Botao Zhao, Zhouyin Wu, Junqing Peng, Jianzong Wang

备注：
Accepted by the 29th International Conference on Computer Supported Cooperative Work in Design (CSCWD 2026)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出CAICL方法，通过混淆定位与分析提升视觉语言模型在机器人操作中处理混淆场景的能力，实验显示其在VIMA-Bench上成功率达85.5%。

摘要：

视觉语言模型（VLMs）显著提升了机器人操作的泛化能力。然而，基于VLM的系统常因鲁棒性不足而产生不可预测的错误，尤其是在涉及易混淆物体的场景中。本文分析发现，这些失败主要源于VLM内在的捷径学习问题，限制了其区分易混淆特征的能力。为此，我们提出Confusion-Aware In-Context Learning（CAICL），一种增强VLM在机器人操作中处理混淆场景性能的方法。该方法首先进行混淆定位与分析，识别可能的混淆源，然后将此信息作为提示，引导VLM关注最可能引起误识别的特征。在VIMA-Bench上的大量实验表明，CAICL有效解决了捷径学习问题，实现了85.5%的成功率，并在不同泛化程度的任务中表现出良好的稳定性。

英文摘要：

Vision-language models (VLMs) have significantly improved the generalization capabilities of robotic manipulation. However, VLM-based systems often suffer from a lack of robustness, leading to unpredictable errors, particularly in scenarios involving confusable objects. Our preliminary analysis reveals that these failures are mainly caused by shortcut learning problem inherently in VLMs, limiting their ability to accurately distinguish between confusable features. To this end, we propose Confusion-Aware In-Context Learning (CAICL), a method that enhances VLM performance in confusable scenarios for robotic manipulation. The approach begins with confusion localization and analysis, identifying potential sources of confusion. This information is then used as a prompt for the VLM to focus on features most likely to cause misidentification. Extensive experiments on the VIMA-Bench show that CAICL effectively addresses the shortcut learning issue, achieving a 85.5\% success rate and showing good stability across tasks with different degrees of generalization.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑