Track-and-Complete: Learning Humanoid Skills from a Single Failed Human Video
Track-and-Complete: Learning Humanoid Skills from a Single Failed Human Video
This paper introduces TRACC, a pipeline that learns humanoid skills from failed human video demonstrations. The method imitates the usable portion of the motion trajectory before failure and completes the task based on the inferred outcome. Evaluated on six in-the-wild failed tasks from the Oops! dataset, the approach demonstrates effectiveness for learning from failed attempts when no successful demonstration is available.
The authors propose TRACC, a method that learns humanoid skills from failed human video demonstrations by imitating the usable motion prefix and completing the task based on inferred outcomes, evaluated on six in-the-wild examples from the Oops! dataset.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
n-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.
Open source S4
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 i
Open source S3
Track-and-Complete: Learning Humanoid Skills from a Single Failed Human Video
Open source S1
arXiv:2609.36924v2 Announce Type: replace Abstract: 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
Open source S2
Source：arXiv Robotics — research abstracts · arxiv.org