robotics
The Rescue Planner Integrated Away Part of Its Uncertainty
Rao-Blackwellization reduces sampling variance inside high-dimensional online robot planning.
Summary
Rao-Blackwellization reduces sampling variance inside high-dimensional online robot planning.
The planner keeps a hybrid continuous-discrete belief and analytically propagates tractable state components instead of sampling every uncertainty. Integrated with FastSLAM 2.0 in a search-and-rescue task, it achieved higher cumulative rewards with fewer particles and planning simulations than purely sampling-based methods at equal compute budgets. The advantage applies where sufficient statistics remain tractable.
Why it matters
Rao-Blackwellization reduces sampling variance inside high-dimensional online robot planning.
Limits and context
- The advantage applies where sufficient statistics remain tractable.
Key claims
Rao-Blackwellization reduces sampling variance inside high-dimensional online robot planning.
Qualification: The advantage applies where sufficient statistics remain tractable.
Evidence: source-2026-09-02-008
Sources
- arXiv preprint 2609.01351arXiv · primary research
Corrections
No corrections have been recorded for this story.