用视觉对比提升机器人政策的泛化能力，无需修改模型。
Policy Contrastive Decoding for Robotic Foundation Models
- 通过对比原始图像与遮挡物体后的图像，引导机器人关注关键视觉线索。
- 在仿真中提升性能8.9%，真实场景下提升108%。
- 无需微调，可适配多种机器人策略，适合部署优化场景。
机器人基础模型（通用机器人策略）具有实现灵活、通用和灵巧机器人系统的巨大潜力。尽管取得进展，我们的实验发现现有机器人策略容易从预训练轨迹中学习到虚假关联，损害其在训练数据之外的泛化能力。为此，我们提出一种新的策略对比解码（PCD）方法，通过对比原始视觉输入与物体遮挡后输入所生成的动作概率分布，引导机器人策略关注与物体相关的视觉线索。作为一项无需训练的方法，PCD可作为插件直接用于改进各类机器人策略，无需微调或访问模型权重。我们在三种开源机器人策略上进行了广泛实验，包括自回归策略 OpenVLA 和基于扩散的策略 Octo 与 $π_0$。仿真与真实环境中的结果均证明了 PCD 的灵活性与有效性：在仿真环境中使最先进的策略 $π_0$ 提升 8.9%，在真实环境中提升 108%。代码与演示已公开：https://koorye.github.io/PCD。
原文摘要 · Abstract (English)
Robotic foundation models, or generalist robot policies, hold immense potential to enable flexible, general-purpose and dexterous robotic systems. Despite their advancements, our empirical experiments reveal that existing robot policies are prone to learning spurious correlations from pre-training trajectories, adversely affecting their generalization capabilities beyond the training data. To tackle this, we propose a novel Policy Contrastive Decoding (PCD) approach, which redirects the robot policy's focus toward object-relevant visual clues by contrasting action probability distributions derived from original and object-masked visual inputs. As a training-free method, our PCD can be used as a plugin to improve different types of robot policies without needing to finetune or access model weights. We conduct extensive experiments on top of three open-source robot policies, including the autoregressive policy OpenVLA and the diffusion-based policies Octo and $π_0$. The obtained results in both simulation and real-world environments prove PCD's flexibility and effectiveness, e.g., PCD enhances the state-of-the-art policy $π_0$ by 8.9% in the simulation environment and by 108% in the real-world environment. Code and demos are publicly available at: https://koorye.github.io/PCD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。