A framework converts egocentric human videos to robot-compatible datasets for co-training VLA models, yielding better navigation performance than single-source training.
Survey of imitation learning for robotic manipulation,
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
-
Co-training with Ego-centric Video and Demonstration for Robot Navigation Task
A framework converts egocentric human videos to robot-compatible datasets for co-training VLA models, yielding better navigation performance than single-source training.