arXiv · 2611.22367
FailureGen: Scalable Robot Failure Data Generation with World Models
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Akul Santhosh, Chaitra Sathe, Aastha Jhunjhunwala. 2026-11-17. FailureGen: Scalable Robot Failure Data Generation with World Models. https://searcharxiv.com/abs/2611.22367
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.