robotics
One Demonstration Wrote the Planner’s World
PDDL-ART generated symbolic domains and problems from one expert demonstration, then corrected them through syntax, semantics and execution.
Summary
PDDL-ART generated symbolic domains and problems from one expert demonstration, then corrected them through syntax, semantics and execution.
Across engine-maintenance and household tasks, the VLM-based system reported 93.3 percent average success versus 78.3 percent for its planner baseline. Tool-grounded predicate checks helped with relations not visible in a single frame; performance still depends on the demonstration and available high-level actions.
Why it matters
PDDL-ART generated symbolic domains and problems from one expert demonstration, then corrected them through syntax, semantics and execution.
Limits and context
- Tool-grounded predicate checks helped with relations not visible in a single frame; performance still depends on the demonstration and available high-level actions.
Key claims
PDDL-ART generated symbolic domains and problems from one expert demonstration, then corrected them through syntax, semantics and execution.
Qualification: Tool-grounded predicate checks helped with relations not visible in a single frame; performance still depends on the demonstration and available high-level actions.
Evidence: source-2026-08-19-017
Sources
- arXiv preprint 2608.17146arXiv · primary research
Corrections
No corrections have been recorded for this story.