Safe Uncertainty-Aware Learning of Robotic Suturing

TL;DR

This paper introduces a safety-focused, uncertainty-aware learning framework for robotic suturing, combining ensemble diffusion policies and control barrier functions to enhance robustness and safety in minimally invasive surgery automation.

Contribution

It presents a novel combination of ensemble diffusion models and control barrier functions to ensure safety and uncertainty quantification in robotic surgical tasks.

Findings

The learned policy is robust to perturbations like needle dropping and camera movement.

The system can detect Out-Of-Distribution scenarios effectively.

Control Barrier Functions successfully enforce safety constraints during unsafe predictions.

Abstract

Robot-Assisted Minimally Invasive Surgery is currently fully manually controlled by a trained surgeon. Automating this has great potential for alleviating issues, e.g., physical strain, highly repetitive tasks, and shortages of trained surgeons. For these reasons, recent works have utilized Artificial Intelligence methods, which show promising adaptability. Despite these advances, there is skepticism of these methods because they lack explainability and robust safety guarantees. This paper presents a framework for a safe, uncertainty-aware learning method. We train an Ensemble Model of Diffusion Policies using expert demonstrations of needle insertion. Using an Ensemble model, we can quantify the policy's epistemic uncertainty, which is used to determine Out-Of-Distribution scenarios. This allows the system to release control back to the surgeon in the event of an unsafe scenario. Additionally, we implement a model-free Control Barrier Function to place formal safety guarantees on the predicted action. We experimentally evaluate our proposed framework using a state-of-the-art robotic suturing simulator. We evaluate multiple scenarios, such as dropping the needle, moving the camera, and moving the phantom. The learned policy is robust to these perturbations, showing corrective behaviors and generalization, and it is possible to detect Out-Of-Distribution scenarios. We further demonstrate that the Control Barrier Function successfully limits the action to remain within our specified safety set in the case of unsafe predictions.