Overhead multi-modal learning with PU human-trajectory supervision and LiDAR priors yields global off-road costmaps that nearly match human path length and sharply cut interventions versus local planners.
Towards learned traversability for robot navigation: From underfoot to the far field,
1 Pith paper cite this work, alongside 72 external citations. Polarity classification is still indexing.
1
Pith paper citing it
72
external citations · OpenAlex
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Traversability-Aware Global Planners for Long Horizon Off-Road Navigation
Overhead multi-modal learning with PU human-trajectory supervision and LiDAR priors yields global off-road costmaps that nearly match human path length and sharply cut interventions versus local planners.