arXiv cs.AI· Akul Santhosh, Chaitra Sathe, Aastha Jhunjhunwala·· 4 小时前AI 评分31
FailureGen:用世界模型可扩展生成机器人失败数据
FailureGen: Scalable Robot Failure Data Generation with World Models
AI 导读
FailureGen 通过复用已记录失败中的动作轨迹,生成带时序事件标注的合成视频,用于扩充机器人失败数据。方法基于微调的 Cosmos 世界模型,将失败片段运动迁移到成功执行场景中,并经过标注与质量过滤。在初步对比中,用真实与生成数据训练的检测器平均精度达 0.51(仅真实数据为 0.41),并在 36 个失败区间中检出 33 个(仅真实数据为 28 个)。
正文 · 原文
Abstract:Robot failures are difficult to collect at scale, limiting the range of failure scenarios represented in robot learning datasets. We present FailureGen, a method for generating synthetic videos with temporal event annotations by reusing action trajectories from recorded failures. The method comprises four stages: (1) fine-tuning an action-conditioned Cosmos world model on successful and failed real executions; (2) annotating source recordings to identify failure-associated donor segments and compatible successful hosts; (3) transferring donor motion into host contexts, with optional spatial offsets, to generate continuous video rollouts; and (4) annotating and filtering the generated samples according to observed events and visual quality. We study two implementations with different tasks and robot configurations, with visual failure detection serving as one downstream application. In a preliminary comparison, a detector trained on real and generated data achieves an average precision of 0.51, compared with 0.41 using real data alone, and detects 33 of 36 failure intervals, compared with 28 of 36. By reusing observed failures in additional contexts, FailureGen expands the data available for studying robot failures and developing downstream learning methods.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.22367 [cs.RO] |
| (or arXiv:2611.22367v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22367 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Akul Santhosh [view email]
[v1]
Tue, 17 Nov 2026 08:21:16 UTC (13,180 KB)
来源:arXiv cs.AI · arxiv.org