Develops a probabilistically complete sampling-based planner that learns lower-dimensional Wasserstein ambiguity tubes from data and uses a bandit-based checker to find safe paths under unknown disturbances for linear robotic systems.
Efficient uncertainty propagation with guarantees in wasserstein distance,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Provably Safe Motion Planning Under Unknown Disturbances
Develops a probabilistically complete sampling-based planner that learns lower-dimensional Wasserstein ambiguity tubes from data and uses a bandit-based checker to find safe paths under unknown disturbances for linear robotic systems.