Toward Safe Autonomous Robotic Endovascular Interventions using World Models

ArXi:2604.20151v1 Announce Type: cross Autonomous mechanical thrombectomy (MT) presents substantial challenges due to highly variable vascular geometries and the requirements for accurate, real-time control. While reinforcement learning (RL) has emerged as a promising paradigm for the automation of endovascular navigation, existing approaches often show limited robustness when faced with diverse patient anatomies or extended navigation horizons.