RINSE scores robot demonstration trajectories for smoothness via SAL and TED metrics to curate higher-quality data for behavioral cloning, improving success rates with less data on benchmarks and real robots.
Octo: An open-source generalist robot policy
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2representative citing papers
OBEYED-VLA improves VLA robustness in cluttered real-world manipulation by disentangling perception into VLM-based object-centric grounding and geometry-aware stages, then fine-tuning the policy only on single-object demonstrations.
citing papers explorer
-
Learning from the Best: Smoothness-Driven Metrics for Data Quality in Imitation Learning
RINSE scores robot demonstration trajectories for smoothness via SAL and TED metrics to curate higher-quality data for behavioral cloning, improving success rates with less data on benchmarks and real robots.
-
Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Grounding
OBEYED-VLA improves VLA robustness in cluttered real-world manipulation by disentangling perception into VLM-based object-centric grounding and geometry-aware stages, then fine-tuning the policy only on single-object demonstrations.