AGRO-SUVIDE: Agentic Robotics for Surgical Viscoelastic Debridement

2026-09-28

AI Summary

This study addresses surgeon fatigue caused by the repetitive removal of viscoelastic tissue fragments during surgery by proposing the first modular agentic robotic framework for autonomous viscoelastic debridement. The approach integrates visual-kinematic analysis with programmatic model encoding to construct a skill library through automated demonstration parsing, leveraging graph-based structures for dynamic runtime assembly and verification. Furthermore, model-free policy learning and code generation mechanisms are introduced to endow the system with self-improvement capabilities. Experimental results demonstrate a single-fragment removal success rate of 85% and 60% for three consecutive fragment removals. Notably, the framework generalizes effectively to five-fragment scenarios, achieving an 80% success rate for individual removals, thereby successfully enabling autonomous surgical debridement.

Abstract

Augmented dexterity has the potential to reduce the fatigue experienced by surgeons during repetitive surgical tasks. In this paper, we propose the first AGentic RObotics framework for SUrgical VIscoelastic DEbridement (AGRO-SUVIDE), the repeated removal of small fragments attached to a viscoelastic substrate. Leveraging the self-improving and coding capability of agents, AGRO-SUVIDE adopts a modular framework. Specifically, the demonstration analysis module automatically identifies recurring skills from a single expert demonstration, using both visual and kinematic information. The construction module then builds each skill, either as a procedural model-based skill the agent codes against a scaffolded library or as a model-free policy-based skill. At runtime, the monitoring module composes the skills into a loop-style graph sized to the number of fragments it observes, then verifies pre- and post-conditions of each skill to decide whether to advance or retry. We evaluate AGRO-SUVIDE through 340 physical trials on the da Vinci Research Kit (dVRK). AGRO-SUVIDE achieves an average single-fragment removal success rate of 85%, completing consecutive three-fragment removal at 60% and at 95% with one human intervention. It further generalizes to unseen five-fragment scenarios with an average success rate of 80% for single-fragment removal. Project page: https://surgical-robotics.github.io/AGRO-SUVIDE/

Problem

• surgical robotics
• viscoelastic debridement
• augmented dexterity
• repetitive surgical tasks

Innovation

• Agentic Robotics
• Surgical Debridement
• Modular Framework
• Skill Composition
• Augmented Dexterity