ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation
About
Training robust bimanual manipulation policies via imitation learning requires demonstration data with broad coverage over robot poses, contacts, and scene contexts. However, collecting diverse and precise real-world demonstrations is costly and time-consuming, which hinders scalability. Prior works have addressed this with data augmentation, typically for either eye-in-hand (wrist camera) setups with RGB inputs or for generating novel images without paired actions, leaving augmentation for eye-to-hand (third-person) RGB-D training with new action labels less explored. In this paper, we propose Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation (ROPA), an offline imitation learning data augmentation method that fine-tunes Stable Diffusion to synthesize third-person RGB and RGB-D observations of novel robot poses. Our approach simultaneously generates corresponding joint-space action labels while employing constrained optimization to enforce physical consistency through appropriate gripper-to-object contact constraints in bimanual scenarios. We evaluate our method on 5 simulated and 3 real-world tasks. Our results across 2625 simulation trials and 300 real-world trials demonstrate that ROPA outperforms baselines and ablations, showing its potential for scalable RGB and RGB-D data augmentation in eye-to-hand bimanual manipulation. Our project website is available at: https://ropaaug.github.io/.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Bimanual Robot Manipulation | Coordinated Lift Ball (CLB) Simulation | Success Rate72 | 7 | |
| Bimanual Robot Manipulation | Coordinated Lift Tray (CLT) Simulation | Success Rate35 | 7 | |
| Bimanual Robot Manipulation | Coordinated Push Box (CPB) Simulation | Success Rate62.7 | 7 | |
| Bimanual Robot Manipulation | Big Sweep Round (BSR) Simulation | Success Rate29 | 7 | |
| Bimanual Robot Manipulation | Coordinated Pick In Drawer (CPID) Simulation | Success Rate35 | 7 | |
| Push Block | Real-world | Success Rate20 | 6 | |
| Lift Ball | Real-world | Success Rate95 | 5 | |
| Lift Drawer | Real-world | Success Rate0.65 | 5 |