A PointNet-style network trained only on simulated LIDAR and IMU data predicts continuous, heading-aware terrain traversability costs that transfer to a real robot in qualitative field tests.
Title resolution pending
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
-
From Simulation to Field: Learning Terrain Traversability for Real-World Deployment
A PointNet-style network trained only on simulated LIDAR and IMU data predicts continuous, heading-aware terrain traversability costs that transfer to a real robot in qualitative field tests.