CP-Gen uses keypoint-trajectory constraints to turn a single expert demonstration into many geometry- and pose-varied robot demos, and policies trained on them transfer zero-shot to the real world.
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
-
Constraint-Preserving Data Generation for Visuomotor Policy Learning
CP-Gen uses keypoint-trajectory constraints to turn a single expert demonstration into many geometry- and pose-varied robot demos, and policies trained on them transfer zero-shot to the real world.