Track-and-Complete：从单个失败的人类视频中学习人形机器人技能
Track-and-Complete: Learning Humanoid Skills from a Single Failed Human Video
浏览论文内容
中文总结 AI 辅助
提出TRACC流水线，从单个失败人类视频中提取可用运动前缀并推断任务结果，以在无成功示范时完成人形机器人技能学习，实验验证其有效性。
中文摘要 AI 辅助
从视频中学习人形机器人技能通常需要成功的人类示范，这往往要求定制化的数据收集。尽管失败在机器人学习中传统上仅被视为负面示例，但它们仍能在任务失败前揭示可用的轨迹前缀，以及预期的结果。为了利用失败尝试视频中的这些信息，我们提出了TRACC，一种流水线，它模仿运动轨迹中有用的部分，然后基于推断的任务结果完成任务。可用的运动前缀作为先验知识，直到失败发生，之后任务完成奖励引导策略学习预期的任务目标，而无需成功的任务轨迹。我们在Oops!数据集的六个野外失败人类任务上评估了我们的方法。我们的实验结果证明了在无成功示范可用时，从失败尝试中学习所提出方法的有效性。因此，这些发现确立了失败的人类视频作为人形机器人技能学习的一种可行监督来源。
英文摘要
Learning humanoid skills from videos typically requires a successful human demonstration, which often demands custom data collection. Although failures have traditionally been treated only as negative examples in robot learning, they can still reveal a usable trajectory prefix before the task fails, as well as the intended outcome. To leverage this information from a failed-attempt video, we propose TRACC, a pipeline that imitates the useful portion of the motion trajectory and then completes the task based on the inferred task outcome. The usable motion prefix serves as prior knowledge until the failure occurs, after which the task-completion reward guides the policy to learn the intended task goal without requiring a successful task trajectory. We evaluate our method on six in-the-wild failed human tasks from the Oops! dataset. Our experimental results demonstrate the effectiveness of the proposed approach for learning from failed attempts when no successful demonstration is available. Thus, these findings establish failed human videos as a viable source of supervision for humanoid skill learning.
发表机构
- Yonsei University（延世大学）
机构由 AI 辅助整理，请以论文原文为准。
