Active learning on RGB-D data enables binary reachability prediction for robotic fruit harvesting with 6-8% higher accuracy than random sampling using fewer labels.
Title resolution pending
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
-
Learning What Can Be Picked: Active Reachability Estimation for Efficient Robotic Fruit Harvesting
Active learning on RGB-D data enables binary reachability prediction for robotic fruit harvesting with 6-8% higher accuracy than random sampling using fewer labels.