RIT* replaces Euclidean primitives in batch-informed tree search with Riemannian counterparts and an online collision-learned cost metric, improving final path cost by up to 63.5% in high-dimensional anisotropic benchmarks.
Reactive motion generation on learned Riemannian mani- folds,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
RIT*: Riemannian Informed Trees for Cost-Adaptive Optimal Motion Planning
RIT* replaces Euclidean primitives in batch-informed tree search with Riemannian counterparts and an online collision-learned cost metric, improving final path cost by up to 63.5% in high-dimensional anisotropic benchmarks.