robotics
The Failed Plan Repairs the Training Scene
SCOPE turns planner execution errors into feedback for correcting hallucinated scene graphs before they enter long-horizon robot datasets.
Summary
SCOPE turns planner execution errors into feedback for correcting hallucinated scene graphs before they enter long-horizon robot datasets.
Automatically generated task-and-motion-planning data can be repetitive or physically unsolvable when a language model invents inconsistent scene graphs. SCOPE measures scenario diversity while running a planner against each generated scene. Execution failures feed a retroactive correction loop that repairs logical and physical inconsistencies before the example is accepted. In the reported comparison, an LLM fine-tuned on SCOPE data achieved a 12.33-point absolute success-rate gain over a counterpart trained on data from the DELTA PDDL-based generator. This evaluates the authors' generation pipeline, planners and downstream tasks; it does not establish that every corrected scene is physically complete or that synthetic planning data transfers to every robot.
Why it matters
SCOPE turns planner execution errors into feedback for correcting hallucinated scene graphs before they enter long-horizon robot datasets.
Limits and context
- This evaluates the authors' generation pipeline, planners and downstream tasks; it does not establish that every corrected scene is physically complete or that synthetic planning data transfers to every robot.
Key claims
SCOPE turns planner execution errors into feedback for correcting hallucinated scene graphs before they enter long-horizon robot datasets.
Qualification: This evaluates the authors' generation pipeline, planners and downstream tasks; it does not establish that every corrected scene is physically complete or that synthetic planning data transfers to every robot.
Evidence: source-2026-10-25-007
Sources
- arXiv preprint 2610.31518, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.