Safe Uncertainty-Aware Learning of Robotic Suturing

2025-05-22

AI Summary

Robotic-assisted minimally invasive suturing faces challenges of high operator workload and limited interpretability and safety guarantees in AI-based control methods. Method: This paper proposes an autonomous control framework integrating diffusion policy ensembles with model-agnostic control barrier functions (CBFs), enabling formal safety verification and uncertainty-aware decision-making. The framework combines expert demonstration learning with the dVRK+Phantom surgical simulation platform. Contribution/Results: It achieves, for the first time in suturing tasks, quantitative assessment of cognitive uncertainty and action-level real-time safety constraints. Under multiple perturbations—including needle drop, camera drift, and tissue displacement—the system demonstrates robustness and dynamic error correction, reliably detecting out-of-distribution (OOD) anomalies while guaranteeing that 100% of executed actions remain within the formally defined safe set.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Safety and Robustness
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Agentic search

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.

Problem

• Developing safe uncertainty-aware learning for robotic suturing automation
• Ensuring explainability and robust safety in AI surgical methods
• Detecting Out-Of-Distribution scenarios to prevent unsafe actions

Innovation

• Ensemble Model of Diffusion Policies for uncertainty
• Control Barrier Function for safety guarantees
• Out-Of-Distribution detection via epistemic uncertainty