UMI-Underwater：无需水下遥控的学习水下操作
UMI-Underwater: Learning Underwater Manipulation without Underwater Teleoperation
AI总结：
本文提出UMI-Underwater系统，通过自监督数据收集管道自主获取水下抓取示范，并利用基于深度的 affordance 表示将陆地到水下领域差距桥接，提升水下抓取性能和鲁棒性。
摘要：
水下机器人抓取因图像退化、高度变化和收集多样化水下示范成本高而困难。我们介绍了一种系统，(i) 通过自监督数据收集管道自主收集成功的水下抓取示范，(ii) 通过基于深度的 affordance 表示将陆地抓取知识转移到水下，该表示对光照和颜色偏移具有鲁棒性。一个在陆地手持示范上训练的 affordance 模型通过几何对齐在水下零样本部署，然后在水下示范上训练 affordance 条件扩散策略以生成控制动作。在池实验中，我们的方法提高了抓取性能和对背景变化的鲁棒性，并能够泛化到仅在陆地数据中出现的物体，优于仅使用 RGB 的基线。代码、视频和额外结果可在 https://umi-under-water.github.io 上获得。
英文摘要：
Underwater robotic grasping is difficult due to degraded, highly variable imagery and the expense of collecting diverse underwater demonstrations. We introduce a system that (i) autonomously collects successful underwater grasp demonstrations via a self-supervised data collection pipeline and (ii) transfers grasp knowledge from on-land human demonstrations through a depth-based affordance representation that bridges the on-land-to-underwater domain gap and is robust to lighting and color shift. An affordance model trained on on-land handheld demonstrations is deployed underwater zero-shot via geometric alignment, and an affordance-conditioned diffusion policy is then trained on underwater demonstrations to generate control actions. In pool experiments, our approach improves grasping performance and robustness to background shifts, and enables generalization to objects seen only in on-land data, outperforming RGB-only baselines. Code, videos, and additional results are available at https://umi-under-water.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。
