H-WM: Robotic Task and Motion Planning Guided by Hierarchical World Model
COMPILED NOTES
Hierarchical world model jointly predicting logical and visual state transitions — mitigates error accumulation in TAMP
H-WM: Hierarchical World Model for TAMP
Key Claims
- Two-level world model — high-level logical (symbolic) predictor + low-level visual predictor operating in tandem
- Mitigates error accumulation — the symbolic layer provides a stabilizing prior that limits how far visual rollouts can drift
- Targets TAMP (Task and Motion Planning) — multi-step manipulation problems that have historically resisted end-to-end learning
Why This Matters
Matches LeCun's hierarchical planning thesis — he argues that a true world model must operate at multiple levels of abstraction (airport trip: "go to airport" at high level, "move left foot" at low level). H-WM is one operationalization of that argument for robotics: the symbolic layer handles "pick up cup, move to sink, release" while the visual layer handles pixel-level outcomes.
Notes
First-pass stub. Key robotics-application anchor for the world-models concept page.
Source: H-WM
RELATED · IN THE BASE