ROPA augments bimanual imitation learning datasets by generating synthetic RGB-D observations and actions via fine-tuned diffusion models with physical consistency constraints.
RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation
ROPA augments bimanual imitation learning datasets by generating synthetic RGB-D observations and actions via fine-tuned diffusion models with physical consistency constraints.