A neural behavior classifier trained on teleoperated joint trajectories is proposed and tested as an offline meta-evaluator for imitation learning policies in human-robot interaction.
Title resolution pending
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
-
Learning to Evaluate Autonomous Behaviour in Human-Robot Interaction
A neural behavior classifier trained on teleoperated joint trajectories is proposed and tested as an offline meta-evaluator for imitation learning policies in human-robot interaction.