robotics
A Few Corrections Teach the Reason for Failure
OopsieRecover infers semantic intent from corrective demonstrations, then steers robot policies with spatial costs across new scenes.
Summary
OopsieRecover infers semantic intent from corrective demonstrations, then steers robot policies with spatial costs across new scenes.
Instead of binding a correction to the exact observation in which it appeared, the framework uses abduction to infer why the original behavior was undesirable. It encodes that knowledge as dense spatial representations and conditional costs. Across six manipulation tasks and variations in objects, poses, scenes and related tasks, the authors report that a handful of demonstrations can transfer corrections without fresh data for every variation. The result remains confined to the paper’s tasks and vision-language-action models.
Why it matters
OopsieRecover infers semantic intent from corrective demonstrations, then steers robot policies with spatial costs across new scenes.
Limits and context
No additional limitation was separately recorded.
Key claims
OopsieRecover infers semantic intent from corrective demonstrations, then steers robot policies with spatial costs across new scenes.
Evidence: source-2026-11-06-005
Sources
- arXiv preprint 2611.08462, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.