Contextual bandit algorithms (epsilon-greedy and LinUCB) with SPANet features let a feeding robot acquire previously unseen foods after about ten attempts per food.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptive Robot-Assisted Feeding: An Online Learning Framework for Acquiring Previously Unseen Food Items
Contextual bandit algorithms (epsilon-greedy and LinUCB) with SPANet features let a feeding robot acquire previously unseen foods after about ten attempts per food.