Learning-based autonomous navigation, benchmark environments and simulation framework for endovascular interventions

doi:10.1016/j.compbiomed.2025.110844

Learning-based autonomous navigation, benchmark environments and simulation framework for endovascular interventions

2025-08-15

0

OA

AI

Seyed Mohammad Hadi Sadati

Franziska Mathis-Ullrich *

DOI：10.1016/j.compbiomed.2025.110844

Original

Original request for help

Save

Abstract

En 中文

• Novel benchmark environments for autonomous endovascular navigation using stEVE. • Successful simulation-to-reality transfer with 98% to 97% success rate. • Multi-instrument coordination challenges identified in DualDeviceNav benchmark. • Open-source framework enables reproducible endovascular robotics research. • Reward design ablation shows two-component combinations accelerate learning.

Keywords:

endovascular navigation

stEVE

simulation-to-reality transfer

multi-instrument coordination

reward design

Learning-based autonomous navigation, benchmark environments and simulation framework for endovascular interventions

Abstract

Journal

Organization