Toward Safe Autonomous Robotic Endovascular Interventions using World Models

arXiv 2026 49.6 method, application

TLDR

A world-model-based RL framework (TD-MPC2) for autonomous endovascular navigation, validated in simulation and in vitro with patient-specific phantoms.

Reasoning

The paper presents a clear contribution by applying TD-MPC2 to a challenging medical robotics task, with both simulated and real-world (in vitro) validation. Strengths include rigorous comparison to SAC and demonstration of safety constraints; weaknesses include moderate success rates and longer procedure times, and limited scope to a single navigation task.

Read-first score

Read-first score 49.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 33.

Recency 6%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 18%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,experiment,result

Citation impact 18%

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.58999954

Topical relevance 29%

47.1

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Reproducibility 18%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Citation velocity 12%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

FrontierBridgeMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 227.

Keyword Scores

world model

model-based reinforcement learning world model

world dynamics prediction

world simulator

interactive world model

generative world model

video world model

Deep Analysis

Innovations

First demonstration of autonomous mechanical thrombectomy navigation validated across both hold out in silico data and fluoroscopy-guided in vitro experiments
Use of world-model-based framework (TD-MPC2) for endovascular navigation

Methodology

The study employs TD-MPC2, a model-based reinforcement learning method that integrates planning and learned dynamics, to train an agent on multiple navigation tasks across hold out patient-specific vasculatures. The agent is benchmarked against the state-of-the-art Soft Actor-Critic (SAC) algorithm in simulation and further validated in vitro using patient-specific vascular phantoms under fluoroscopic guidance.

Key Results

In simulation, TD-MPC2 achieved a significantly higher mean success rate than SAC (58% vs 36%, p<0.001) with mean tip contact forces of 0.15 N, well below the 1.5 N vessel rupture threshold. In vitro, TD-MPC2 achieved comparable success rates (68% vs 60%) but superior path ratios (p=0.017) at the cost of longer procedure times (p<0.001).

Limitations

Longer procedure times compared to SAC (p<0.001)

Resources

Paper