RNN controller trained on human demos achieves 4ml pouring error on unseen containers for water and comparable accuracy for oil and syrup.
Learning to pour using deep deterministic pol- icy gradients
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Accurate Robotic Pouring for Serving Drinks
RNN controller trained on human demos achieves 4ml pouring error on unseen containers for water and comparable accuracy for oil and syrup.