SuFIA: Language-Guided Augmented Dexterity
for Robotic Surgical Assistants

1University of Toronto, 2University of Bern, 3University of California, Berkeley,
4NVIDIA, 5Georgia Institute of Technology


In this work, we present SuFIA, the first framework for natural language-guided augmented dexterity for robotic surgical assistants. SuFIA incorporates the strong reasoning capabilities of large language models (LLMs) with perception modules to implement high-level planning and low-level control of a robot for surgical sub-task execution. This enables a learning-free approach to surgical augmented dexterity without any in-context examples or motion primitives. SuFIA uses a human-in-the-loop paradigm by restoring control to the surgeon in the case of insufficient information, mitigating unexpected errors for mission-critical tasks. We evaluate SuFIA on four surgical sub-tasks in a simulation environment and two sub-tasks on a physical surgical robotic platform in the lab, demonstrating its ability to perform common surgical sub-tasks through supervised autonomous operation under challenging physical and workspace conditions.


Example Tasks

Suture Needle Handover

In this task, the robot hands over a suture needle from one arm to the other. SuFIA queries a language model to understand the surgeon's request and plan the handover motion and also communicates its intentions to the surgeon. SuFIA directly devises and executes the low-level robot actions and trajectories for the handover motion. The robot can adapt to the surgeon's preferences and adjust the handover motion accordingly.

Vessel Dilation

In this task, a spring clamp assembly holds a soft vessel phantom from two points. The dVRK arm is required to grip the vessel rim from a third point facing the robot and dilate the vessel by pulling backward.