A cascaded diffusion planner with a coarse global model, a local refiner, and a one-shot collision-patching step improves success rates by roughly 3 to 5 percentage points over prior learned planners in simulated navigation and manipulation.
Ifor: Iterative flow minimization for robotic object rear- rangement,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Cascaded Diffusion Models for Neural Motion Planning
A cascaded diffusion planner with a coarse global model, a local refiner, and a one-shot collision-patching step improves success rates by roughly 3 to 5 percentage points over prior learned planners in simulated navigation and manipulation.