Contact-Aware Prediction for Reliable Autonomous Deformable Tissue Retraction in Robotic Surgery

Abstract

Contact dynamics critically influence the sim-to-real performance of deformable tissue retraction—a representative contact-rich manipulation task in robotic surgery. The uncertainty in instrument-tissue interactions further complicates its automation. To address these challenges, we propose an architecture for contact dynamics prediction and online inference. We emphasize that the pre-contact phase and the fine adjustment of the contact location are critical for achieving stable retraction performance in surgical scenarios. By leveraging characteristics of the pre-contact phase, we efficiently extract the contact dynamics with timescale-sensitive state space model based on 2D images. Then, we perform smooth switching of control strategies based on posterior beliefs for fine adjustment of the contact location and resistance to unexpected disturbances. The proposed architecture only requires a few hours of real-world data collected with minimal human intervention to learn, predict and transfer. We demonstrate the interaction and generalization ability of the proposed architecture on a real robotic system and especially evaluate the resistance and recovery ability under unexpected disturbances. We also present autonomous tissue retraction task integrated with electrosurgical cutting and tissue dissection on an ex vivo porcine model to showcase an optimized surgical workflow.