A two-module framework (motion anticipation plus utility inference) lets assistive robots adapt to user preferences from interaction alone, improving simulated task success and comfort.
Task decoupling in preference-based rein- forcement learning for personalized human-robot interaction,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Learning Human-Aware Robot Policies for Adaptive Assistance
A two-module framework (motion anticipation plus utility inference) lets assistive robots adapt to user preferences from interaction alone, improving simulated task success and comfort.