Sim4EndoR: A Reinforcement Learning Centered Simulation Platform for Task Automation of Endovascular Robotics

2025-04-04

AI Summary

Current robot-assisted percutaneous coronary intervention (PCI) systems rely heavily on manual operation, exhibiting high inter-operator variability and risk of human error. Method: This work introduces the first reinforcement learning (RL)-based simulation platform specifically designed for coronary intervention, enabling task-level autonomous guidewire navigation. We propose an anatomy-aware reward function that incorporates vascular geometric features to guide policy learning, and achieve end-to-end co-optimization of high-fidelity real-time physical simulation and neural policies to enhance sim-to-real transferability. The platform integrates proximal policy optimization (PPO) and soft actor-critic (SAC) algorithms, 3D medical image-based vascular modeling, and a comprehensive simulation validation framework. Contribution/Results: In multi-branch vascular scenarios, the system achieves >92% guidewire navigation success rate and reduces path deviation by 67%, significantly lowering hardware prototyping and trial costs. It provides a reproducible, safe, and efficient simulation foundation for clinical PCI robot autonomy.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Humans and AI: Human-Aware Planning and Behavior Prediction

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
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Robotic-assisted percutaneous coronary intervention (PCI) holds considerable promise for elevating precision and safety in cardiovascular procedures. Nevertheless, current systems heavily depend on human operators, resulting in variability and the potential for human error. To tackle these challenges, Sim4EndoR, an innovative reinforcement learning (RL) based simulation environment, is first introduced to bolster task-level autonomy in PCI. This platform offers a comprehensive and risk-free environment for the development, evaluation, and refinement of potential autonomous systems, enhancing data collection efficiency and minimizing the need for costly hardware trials. A notable aspect of the groundbreaking Sim4EndoR is its reward function, which takes into account the anatomical constraints of the vascular environment, utilizing the geometric characteristics of vessels to steer the learning process. By seamlessly integrating advanced physical simulations with neural network-driven policy learning, Sim4EndoR fosters efficient sim-to-real translation, paving the way for safer, more consistent robotic interventions in clinical practice, ultimately improving patient outcomes.

Problem

• Develops RL-based simulation for autonomous endovascular robotic tasks
• Reduces human error in robotic-assisted cardiovascular procedures
• Enhances sim-to-real translation for safer clinical interventions

Innovation

• RL-based simulation for endovascular task automation
• Reward function considers vascular anatomical constraints
• Integrates physical simulation with neural policy learning