NEEDLEWORK：带验证局部缝合的机器人数据离线改写
NEEDLEWORK: Offline Rewriting of Robot Data with Verified Local Stitches
浏览论文内容
中文总结 AI 辅助
NEEDLE是一种离线数据增强算法，通过在高维机器人演示中添加强验证的动作桥接，绕过次优路径并利用失败轨迹，在真实任务上将成功率平均提升21个百分点。
中文摘要 AI 辅助
机器人演示即使在单个回合效率低下或未成功时，也可能包含有用的行为。轨迹缝合提供了一种将这些行为组合成改进训练数据的方法，但在高维机器人数据中识别有用的连接并验证其可行性是困难的，因为许多先前方法依赖于低维状态表示。我们引入了NEEDLE，一种离线数据集增强算法，通过在高维机器人演示的已记录观测之间添加简短、经过验证的动作桥接来解决这些挑战。首先，NEEDLE识别并创建绕过次优绕行、扩大动作覆盖范围并将失败轨迹添加到原始数据集的连接，仅使用RGB图像、本体感觉和回合级结果，无需新的环境交互或特权对象状态。接下来，我们提出一种采样技术，将已接受的桥接纳入策略训练，而无需合成中间图像或丢弃原始演示，使策略能够学习替代动作，同时保留原始数据集的覆盖范围。在真实机器人任务上，NEEDLE将每个任务上最强基线的成功率平均提高了21个百分点。视频和补充材料见此https URL。
英文摘要
Robot demonstrations may contain useful behavior even when individual episodes are inefficient or unsuccessful. Trajectory stitching offers a way to compose these behaviors into improved training data, but identifying useful connections and verifying their feasibility is difficult in high-dimensional robot data, where many prior methods rely on low-dimensional state representations. We introduce NEEDLE, an offline dataset-augmentation algorithm that addresses these challenges by adding short, verified action bridges between recorded observations in high-dimensional robot demonstrations. First, NEEDLE identifies and creates connections that bypass suboptimal detours, broaden action coverage, and augment the original dataset with failed trajectories, using only RGB images, proprioception, and episode-level outcomes, without new environment interaction or privileged object state. Next, we present a sampling technique that incorporates accepted bridges into policy training without synthesizing intermediate images or discarding the original demonstrations, allowing policies to learn alternative actions while retaining the original dataset's coverage. On real-robot tasks, NEEDLE improves success rate over the strongest baseline on each task by an average of 21 percentage points. Videos and supplementary materials are on https://needle-work.github.io/.
发表机构
- Stanford University（斯坦福大学）
- NVIDIA（英伟达）
机构由 AI 辅助整理，请以论文原文为准。
