Autonomous Soft Robotic Guidewire Navigation via Imitation Learning

2025-10-10

AI Summary

Soft guidewires for endovascular neurointervention face challenges in accurate modeling, poor generalization across anatomies, and limited clinical adaptability during autonomous navigation. Method: This paper proposes a Transformer-based imitation learning framework tailored for neurointervention, incorporating target-conditioned inputs, relative action outputs, and an automated contrast injection mechanism. Within a simulated fluoroscopic environment, it integrates modular vascular geometry modeling with contrast-enhanced automation to establish a high-fidelity training闭环. Contribution/Results: Trained on 647 expert demonstrations across 36 vascular geometries, the model achieves an 83% aneurysm localization success rate on three unseen anatomies—significantly outperforming conventional baselines. To our knowledge, this is the first work to deeply integrate target-guided Transformer imitation learning with real-time clinical imaging feedback, substantially improving both generalization capability and procedural safety of soft guidewires in unknown vasculature.

Technology Category

• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Diffusion Models for Vision

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

In endovascular surgery, endovascular interventionists push a thin tube called a catheter, guided by a thin wire to a treatment site inside the patient's blood vessels to treat various conditions such as blood clots, aneurysms, and malformations. Guidewires with robotic tips can enhance maneuverability, but they present challenges in modeling and control. Automation of soft robotic guidewire navigation has the potential to overcome these challenges, increasing the precision and safety of endovascular navigation. In other surgical domains, end-to-end imitation learning has shown promising results. Thus, we develop a transformer-based imitation learning framework with goal conditioning, relative action outputs, and automatic contrast dye injections to enable generalizable soft robotic guidewire navigation in an aneurysm targeting task. We train the model on 36 different modular bifurcated geometries, generating 647 total demonstrations under simulated fluoroscopy, and evaluate it on three previously unseen vascular geometries. The model can autonomously drive the tip of the robot to the aneurysm location with a success rate of 83% on the unseen geometries, outperforming several baselines. In addition, we present ablation and baseline studies to evaluate the effectiveness of each design and data collection choice. Project website: https://softrobotnavigation.github.io/

Problem

• Automating soft robotic guidewire navigation in endovascular surgery
• Overcoming modeling challenges for precise aneurysm targeting
• Enhancing maneuverability via transformer-based imitation learning

Innovation

• Transformer-based imitation learning for guidewire navigation
• Goal conditioning and relative action outputs
• Automatic contrast dye injections for navigation