SimRetract: Zero-Shot Sim-to-Real Robotic Assistance for Retractor Take-Over in Open Surgery

arXiv:2610.38234 · cs.RO · Submitted 2026-10-28 · Read on arXiv

cs.RO

Submitted: 2026-10-28

Updated: 2026-10-30

License: http://creativecommons.org/licenses/by/4.0/

The gist: We demonstrate the first zero-shot sim-to-real transfer for a surgeon-robot collaboration task in open surgery: retractor take-over.

Abstract

We demonstrate the first zero-shot sim-to-real transfer for a surgeon-robot collaboration task in open surgery: retractor take-over. A robot arm takes a retractor from the surgeon's hand and preserves retraction at handoff, using a policy trained only on simulated demonstrations, without human demonstrations or real-world fine-tuning. Imitation learning from real demonstrations is limited by collection and labeling costs, and by performance degradation when the environment changes. Our framework, SimRetract, generates simulated demonstrations designed for transfer: the policy observes masked instrument images and grasp geometry, learns to recover from off-nominal states, and acts with margin for execution drift. Deployed zero-shot, it grasps the retractor in 90% of 50 surgeon-defined phantom presentations and preserves retraction at handoff in 78%. Results on unseen retractors suggest potential for generalization to instruments with similar grasp geometry. Across ten policy configurations and 1,200 simulated and real trials, we localize the sim-to-real gap to components: in simulation, grasp rates across ablations span 80-96%, while on the real robot removing the instrument mask alone drops performance to 22% grasped and 12% held. Transfer-oriented design thus makes zero-shot sim-to-real transfer feasible for a surgical assistance task without human demonstrations. Code is available here: https://anonymous.4open.science/r/simretract-58D2.

Related papers