One-Shot Real-World Demonstration Synthesis for Scalable Bimanual Manipulation

TL;DR

BiDemoSyn is a novel framework that synthesizes diverse, contact-rich bimanual demonstrations from a single real-world example, enabling scalable, physically feasible policy learning without extensive teleoperation or simulation.

Contribution

It introduces a task decomposition and adaptation approach that generates thousands of demonstrations efficiently, improving generalization and enabling cross-embodiment transfer.

Findings

Policies trained on BiDemoSyn data outperform recent baselines.

The method enables zero-shot transfer to new robotic platforms.

BiDemoSyn generates diverse demonstrations within hours from a single example.

Abstract

Learning dexterous bimanual manipulation policies critically depends on large-scale, high-quality demonstrations, yet current paradigms face inherent trade-offs: teleoperation provides physically grounded data but is prohibitively labor-intensive, while simulation-based synthesis scales efficiently but suffers from sim-to-real gaps. We present BiDemoSyn, a framework that synthesizes contact-rich, physically feasible bimanual demonstrations from a single real-world example. The key idea is to decompose tasks into invariant coordination blocks and variable, object-dependent adjustments, then adapt them through vision-guided alignment and lightweight trajectory optimization. This enables the generation of thousands of diverse and feasible demonstrations within several hours, without repeated teleoperation or reliance on imperfect simulation. Across six dual-arm tasks, we show that policies trained on BiDemoSyn data generalize robustly to novel object poses and shapes, significantly outperforming recent strong baselines. Beyond the one-shot setting, BiDemoSyn naturally extends to few-shot-based synthesis, improving object-level diversity and out-of-distribution generalization while maintaining strong data efficiency. Moreover, policies trained on BiDemoSyn data exhibit zero-shot cross-embodiment transfer to new robotic platforms, enabled by object-centric observations and a simplified 6-DoF end-effector action representation that decouples policies from embodiment-specific dynamics. By bridging the gap between efficiency and real-world fidelity, BiDemoSyn provides a scalable path toward practical imitation learning for complex bimanual manipulation without compromising physical grounding.