{"ID":2863991,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.25518","arxiv_id":"2509.25518","title":"World Model for AI Autonomous Navigation in Mechanical Thrombectomy","abstract":"Autonomous navigation for mechanical thrombectomy (MT) remains a critical challenge due to the complexity of vascular anatomy and the need for precise, real-time decision-making. Reinforcement learning (RL)-based approaches have demonstrated potential in automating endovascular navigation, but current methods often struggle with generalization across multiple patient vasculatures and long-horizon tasks. We propose a world model for autonomous endovascular navigation using TD-MPC2, a model-based RL algorithm. We trained a single RL agent across multiple endovascular navigation tasks in ten real patient vasculatures, comparing performance against the state-of-the-art Soft Actor-Critic (SAC) method. Results indicate that TD-MPC2 significantly outperforms SAC in multi-task learning, achieving a 65% mean success rate compared to SAC's 37%, with notable improvements in path ratio. TD-MPC2 exhibited increased procedure times, suggesting a trade-off between success rate and execution speed. These findings highlight the potential of world models for improving autonomous endovascular navigation and lay the foundation for future research in generalizable AI-driven robotic interventions.","short_abstract":"Autonomous navigation for mechanical thrombectomy (MT) remains a critical challenge due to the complexity of vascular anatomy and the need for precise, real-time decision-making. Reinforcement learning (RL)-based approaches have demonstrated potential in automating endovascular navigation, but current methods often str...","url_abs":"https://arxiv.org/abs/2509.25518","url_pdf":"https://arxiv.org/pdf/2509.25518v2","authors":"[\"Harry Robertshaw\",\"Han-Ru Wu\",\"Alejandro Granados\",\"Thomas C Booth\"]","published":"2025-09-29T21:21:30Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.RO\",\"eess.IV\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}