D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation

TL;DR

D-CODA introduces a diffusion-based method for generating diverse, viewpoint-consistent bimanual manipulation data with valid action labels, enhancing imitation learning for dual-arm tasks.

Contribution

It presents a novel diffusion model approach for scalable, viewpoint-consistent data augmentation in eye-in-hand bimanual manipulation, including joint-space action label generation.

Findings

Outperforms baselines and ablations in simulation and real-world tasks.

Demonstrates scalability with 2250 simulation and 300 real-world trials.

Effective in generating valid, coordinated dual-arm manipulation data.

Abstract

Learning bimanual manipulation is challenging due to its high dimensionality and tight coordination required between two arms. Eye-in-hand imitation learning, which uses wrist-mounted cameras, simplifies perception by focusing on task-relevant views. However, collecting diverse demonstrations remains costly, motivating the need for scalable data augmentation. While prior work has explored visual augmentation in single-arm settings, extending these approaches to bimanual manipulation requires generating viewpoint-consistent observations across both arms and producing corresponding action labels that are both valid and feasible. In this work, we propose Diffusion for COordinated Dual-arm Data Augmentation (D-CODA), a method for offline data augmentation tailored to eye-in-hand bimanual imitation learning that trains a diffusion model to synthesize novel, viewpoint-consistent wrist-camera images for both arms while simultaneously generating joint-space action labels. It employs constrained optimization to ensure that augmented states involving gripper-to-object contacts adhere to constraints suitable for bimanual coordination. We evaluate D-CODA on 5 simulated and 3 real-world tasks. Our results across 2250 simulation trials and 300 real-world trials demonstrate that it outperforms baselines and ablations, showing its potential for scalable data augmentation in eye-in-hand bimanual manipulation. Our project website is at: https://dcodaaug.github.io/D-CODA/.