robotics
The Planner Chooses Reachable States Before Exact Actions
ID-WM separates high-level reachability from low-level inverse dynamics and reports a 135 percent gain over single-level world-model control.
Summary
ID-WM separates high-level reachability from low-level inverse dynamics and reports a 135 percent gain over single-level world-model control.
Long-horizon world-model planning accumulates errors when one model must choose distant goals and exact actions at once. ID-WM divides the problem: a high-level model samples feasible state transitions, while a low-level world model solves the inverse dynamics needed to realize each transition. That lets the system assemble new plans from short behavioral segments without committing early to rigid macro-actions. Across three navigation and manipulation suites, the authors report a 38.5 percent improvement over policy and diffusion-based planners and a 135 percent gain over single-level world-model model-predictive control in complex unseen configurations. The scope is the tested suites; physical deployment and safety are not established by the abstract.
Why it matters
ID-WM separates high-level reachability from low-level inverse dynamics and reports a 135 percent gain over single-level world-model control.
Limits and context
- The scope is the tested suites; physical deployment and safety are not established by the abstract.
Key claims
ID-WM separates high-level reachability from low-level inverse dynamics and reports a 135 percent gain over single-level world-model control.
Qualification: The scope is the tested suites; physical deployment and safety are not established by the abstract.
Evidence: source-2026-11-02-006
Sources
- arXiv preprint 2610.42146, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.