AirNav delivers a new 137K-sample UAV VLN benchmark with diverse natural instructions and reports AirVLN-R1 reaching 51.82% success on test-unseen data plus preliminary sim-to-real results.
TURN_RIGHT
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AirNav: A Large-Scale UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions
AirNav delivers a new 137K-sample UAV VLN benchmark with diverse natural instructions and reports AirVLN-R1 reaching 51.82% success on test-unseen data plus preliminary sim-to-real results.