A ground robot repeated paths taught only in a simulated 3D scene built from drone photos, with average lateral errors of 18 to 20 cm over 12 km of autonomous driving.
UA V localization using autoencoded satellite images,
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
-
UAV See, UGV Do: Aerial Imagery and Virtual Teach Enabling Zero-Shot Ground Vehicle Repeat
A ground robot repeated paths taught only in a simulated 3D scene built from drone photos, with average lateral errors of 18 to 20 cm over 12 km of autonomous driving.