Learning-Based Adaptive Control for Surgical Robotic Exposure Task on Deformable Tissues

TL;DR

This paper introduces a learning-based adaptive control framework for autonomous tissue retraction in surgery, utilizing visual feedback and deep deformation models to improve exposure of regions of interest on deformable tissues.

Contribution

It presents a novel adaptive control method that combines visual boundary monitoring with deep deformation estimation for autonomous surgical tissue retraction.

Findings

Framework achieves zero-shot adaptation in simulations and real-world experiments.

Successfully completes autonomous tissue retraction from initial grasp to full ROI exposure.

Demonstrates potential for real surgical assistance applications.

Abstract

In various surgical procedures, regions of interest (ROIs) such as organs or lesions are often occluded by overlying tissues, requiring surgeons to achieve adequate exposure for precise intervention. However, the irregular geometry, nonlinear biomechanical properties of overlying tissues, and limited intraoperative visibility of the ROI pose significant challenges to the autonomous execution of tissue retraction. To address this, we formulate a realistic model of the tissue retraction task and propose a learning-based adaptive control framework for achieving ROI exposure. The method optimizes control inputs online by monitoring changes in the visual boundary of the tissue, while leveraging a deep deformation estimation model trained on simulation data to identify the optimal grasping point and ensure the convergence and safety of the adaptive controller. Through simulations and real-world experiments on different deformable materials, it has been demonstrated that this framework exhibits zero-shot adaptation to similar tasks and can complete the autonomous retraction process, from initial grasp selection to full ROI exposure. Therefore, it has the potential to be applied in actual surgical assistance scenarios.