视觉-语言-动作模型的对比表示正则化
Contrastive Representation Regularization for Vision-Language-Action Models
AI总结：
提出机器人状态感知对比损失（RS-CL），通过对比学习对齐VLM表示与机器人本体感受状态，提升VLA模型在机器人操作任务中的性能。
摘要：
视觉-语言-动作（VLA）模型通过利用预训练视觉-语言模型（VLM）的丰富表示，在机器人操作中展现了强大的能力。然而，它们的表示可以说仍然次优，缺乏对控制动作和本体感受信息等机器人信号的敏感性。为了解决这个问题，我们引入了机器人状态感知对比损失（RS-CL），一种简单有效的VLA模型表示正则化方法，旨在弥合VLM表示与机器人信号之间的差距。特别地，RS-CL通过使用状态之间的相对距离作为软监督，使表示更紧密地对齐机器人的本体感受状态。作为原始动作预测目标的补充，RS-CL增强了控制相关表示学习，同时轻量级且与标准VLA训练流程完全兼容。我们的实验结果表明，RS-CL显著提升了最先进VLA模型的性能；它将先前技术在RoboCasa-Kitchen基准上的性能提升至69.7%，达到最先进水平，并在具有挑战性的真实机器人操作任务中将成功率从45.0%提升至58.3%。
英文摘要：
Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs). However, their representations arguably remain suboptimal, lacking sensitivity to robotic signals such as control actions and proprioceptive information. To address the issue, we introduce Robot State-aware Contrastive Loss (RS-CL), a simple and effective representation regularization for VLA models, designed to bridge the gap between VLM representations and robotic signals. In particular, RS-CL aligns the representations more closely with the robot's proprioceptive states by using relative distances between the states as soft supervision. Complementing the original action prediction objective, RS-CL enhances control-relevant representation learning, while being lightweight and fully compatible with standard VLA training pipelines. Our empirical results demonstrate that RS-CL substantially improves the performance of state-of-the-art VLA models; it pushes the prior art to 69.7% achieving the state-of-the-art performance on the RoboCasa-Kitchen benchmark, and boosts success rates from 45.0% to 58.3% on challenging real-robot manipulation tasks.
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。
