SimDuoReal: Object-Centric Bimanual Policy for Emergent Dexterity
Organizations: Amazon FAR · UCSD · University of Chicago · CMU ·
Abstract
Bimanual dexterous manipulation requires coordinated arm and hand control, yet specifying such coordination manually is challenging and often task-specific. In this work, we explore whether complex bimanual dexterity can emerge from a simple object-centric learning objective. We train reinforcement learning policies under a shared object-centric reward, varying their training environments rather than tuning separate rewards for each behavior. We find that the policies discover pre-grasp manipulation, grasping and regrasping, in-hand adjustment and handover to reach object-pose goals without hand-designed motion sequences. We then refine the experts on transition states and use DAgger and reinforcement learning to distill them into a single policy that composes these behaviors for diverse bimanual tasks. On real hardware, the same policy succeeds in 61 of 80 trials (76.3%) across four tasks with unseen objects and no task-specific fine-tuning. In simulated barcode scanning, our policy achieves 85.0% success, compared with 60.4% for two single-arm policies without handover. These results suggest that this objective provides a simple and scalable interface for learning general bimanual dexterity, shifting the burden from manually designing robot coordination to specifying what should happen to the object.
Figures & tables
| Task | Handover | Two-Object Coordination | Precision | SR |
| Barcode scanning | ✓ | ✓ | 15/20 | |
| Peg insertion | ✓ | ✓ | ✓ | 15/20 |
| Cleaning | ✓ | ✓ | 16/20 | |
| Cooking | ✓ | 15/20 | ||
| Average (%) | 76.25 |
| Method | SR (%) | Prog. (%) | Time (s) |
| Chained expert teachers | |||
| SimDuoReal teacher w/o cross-workspace expert | 60.4 | 79.6 | 9.2 4.9 |
| SimDuoReal teacher w/o transition-aware refinement | 79.4 | 88.1 | 9.1 4.4 |
| SimDuoReal teacher | 84.3 | 89.8 | 8.7 4.0 |
| Unified student policy | |||
| SimDuoReal w/o expert scenes | 68.3 | 84.8 | 8.8 4.4 |
Bimanual Robotic Manipulation
Bimanual robotic manipulation coordinates two robot arms to handle objects, tools, and tasks that require collaboration.
See all 208 papers