LeCropFollow enables zero-shot sim-to-real visual navigation in unstructured crop fields by optimizing trajectories in a latent manifold from self-supervised semantic heatmaps with TD-MPC2, reducing semantic failures 2.4x versus keypoint baselines in corn gaps.
Breaking the field phenotyping bottleneck in maize with autonomous robots,
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
-
LeCropFollow: Latent Space Planning for Navigation in Unstructured Crop Fields
LeCropFollow enables zero-shot sim-to-real visual navigation in unstructured crop fields by optimizing trajectories in a latent manifold from self-supervised semantic heatmaps with TD-MPC2, reducing semantic failures 2.4x versus keypoint baselines in corn gaps.