A self-supervised neural planner combines Eikonal, temporal difference, obstacle alignment, and causality losses with a learned L1 and L-infinity metric, improving success rates and generalization in robot motion planning.
Multidimensional scaling
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
-
Physics-informed Temporal Difference Metric Learning for Robot Motion Planning
A self-supervised neural planner combines Eikonal, temporal difference, obstacle alignment, and causality losses with a learned L1 and L-infinity metric, improving success rates and generalization in robot motion planning.