Mirage：利用 Cross-Painting 实现跨本体零样本策略迁移
Mirage: Cross-Embodiment Zero-Shot Policy Transfer with Cross-Painting
AI总结：
本文提出 Mirage，通过实时 cross-painting 将目标机器人外观替换为源机器人，实现视觉操作策略在不同机械臂与夹爪间的零样本迁移。
摘要：
复用已采集数据并在不同机器人之间迁移已训练策略的能力，有望减轻额外数据采集和训练的负担。尽管预训练加微调、协同训练等现有方法展现出良好前景，但它们无法泛化到训练期间未见过的机器人。本文聚焦具有相似工作空间和二指夹爪的常见机械臂，研究零样本迁移的可行性。通过在 8 个操作任务上的仿真研究，我们发现：在考虑前向动力学后，基于状态的笛卡尔控制策略能够成功零样本迁移到目标机器人。为解决基于视觉的策略所面临的机器人外观差异问题，我们提出 Mirage；该方法在执行过程中实时使用“cross-painting”——遮蔽未见过的目标机器人，并补绘已见过的源机器人——使策略看起来像是训练时的源机器人正在执行任务。Mirage 适用于第一人称和第三人称相机视角，也适用于同时接收状态与图像作为输入、或仅接收图像作为输入的策略。尽管方法简单，我们大量的仿真和物理实验有力表明，Mirage 能够在不同机械臂和夹爪之间成功实现零样本迁移，并在拾取、堆叠和装配等多种操作任务上仅有极小的性能下降，显著优于通用策略。项目网站：https://robot-mirage.github.io/
英文摘要：
The ability to reuse collected data and transfer trained policies between robots could alleviate the burden of additional data collection and training. While existing approaches such as pretraining plus finetuning and co-training show promise, they do not generalize to robots unseen in training. Focusing on common robot arms with similar workspaces and 2-jaw grippers, we investigate the feasibility of zero-shot transfer. Through simulation studies on 8 manipulation tasks, we find that state-based Cartesian control policies can successfully zero-shot transfer to a target robot after accounting for forward dynamics. To address robot visual disparities for vision-based policies, we introduce Mirage, which uses "cross-painting"--masking out the unseen target robot and inpainting the seen source robot--during execution in real time so that it appears to the policy as if the trained source robot were performing the task. Mirage applies to both first-person and third-person camera views and policies that take in both states and images as inputs or only images as inputs. Despite its simplicity, our extensive simulation and physical experiments provide strong evidence that Mirage can successfully zero-shot transfer between different robot arms and grippers with only minimal performance degradation on a variety of manipulation tasks such as picking, stacking, and assembly, significantly outperforming a generalist policy. Project website: https://robot-mirage.github.io/
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。
