One-to-Two Acting: A Novel Framework for Single-arm Agent Action Expansion to Dual Arms
For robotics researchers, this provides a practical method to leverage abundant single-arm data for dual-arm tasks, reducing the need for costly bimanual demonstrations.
ExS2D enables dual-arm manipulation using only single-arm demonstrations, reducing average execution steps by 54.4% while maintaining comparable success rates, and achieves zero-shot bimanual execution on real robots.
Dual-arm manipulation can improve throughput via parallel execution, but collecting bimanual demonstrations for training is costly and difficult. We present ExS2D, a hierarchical action expansion framework that enables dual-arm manipulation from single-arm supervision. ExS2D first generates structured subtasks from textual instructions while explicitly capturing temporal precedence. It then grounds each subtask into executable actions through subtask-guided action mapping in observation. Finally, precedence-aware action allocation and synchronized planning are performed by a multimodal large language model driven coordinator to select collision-free dual-arm executions. Simulation experiments demonstrate that ExS2D reduces the average execution steps by 54.4% while maintaining a comparable success rate to a single-arm baseline. Real-robot experiments on four tasks further demonstrate the reliability of ExS2D for dual-arm execution under few-shot single-arm samples, while using zero bimanual demonstrations.