Active SLAM is formulated as a POMDP with a novel exploration cost encoding state geometry, yielding rigorously justified near-optimal approximate policies learned via standard algorithms.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LTR² is the first LiDAR-teach radar-repeat navigation system using a Cross-Modal Registration network and adaptive fine-tuning to achieve centimeter-level accuracy and robustness over 40+ km deployments in adverse conditions.
citing papers explorer
-
SLAM as a Stochastic Control Problem with Partial Information: Optimal Solutions and Rigorous Approximations
Active SLAM is formulated as a POMDP with a novel exploration cost encoding state geometry, yielding rigorously justified near-optimal approximate policies learned via standard algorithms.
-
LiDAR Teach, Radar Repeat: Robust Cross-Modal Navigation in Degenerate and Varying Environments
LTR² is the first LiDAR-teach radar-repeat navigation system using a Cross-Modal Registration network and adaptive fine-tuning to achieve centimeter-level accuracy and robustness over 40+ km deployments in adverse conditions.