MiniVLA-Nav v1 provides 1,174 episodes of language-instructed robot navigation in photorealistic simulations with RGB, depth, segmentation, and expert action data.
Touchdown: Natural language navigation and spatial reasoning in visual street envi- ronments
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
-
MiniVLA-Nav v1: A Multi-Scene Simulation Dataset for Language-Conditioned Robot Navigation
MiniVLA-Nav v1 provides 1,174 episodes of language-instructed robot navigation in photorealistic simulations with RGB, depth, segmentation, and expert action data.