Autonomous Soft Robotic Guidewire Navigation via Imitation Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Barnes, Noah, Kim, Ji Woong, Di, Lingyun, Qu, Hannah, Bhattacharjee, Anuruddha, Janowski, Miroslaw, Gandhi, Dheeraj, Felix, Bailey, Jiang, Shaopeng, Young, Olivia, Fuge, Mark, Sochol, Ryan D., Brown, Jeremy D., Krieger, Axel
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915544724144128
author Barnes, Noah
Kim, Ji Woong
Di, Lingyun
Qu, Hannah
Bhattacharjee, Anuruddha
Janowski, Miroslaw
Gandhi, Dheeraj
Felix, Bailey
Jiang, Shaopeng
Young, Olivia
Fuge, Mark
Sochol, Ryan D.
Brown, Jeremy D.
Krieger, Axel
author_facet Barnes, Noah
Kim, Ji Woong
Di, Lingyun
Qu, Hannah
Bhattacharjee, Anuruddha
Janowski, Miroslaw
Gandhi, Dheeraj
Felix, Bailey
Jiang, Shaopeng
Young, Olivia
Fuge, Mark
Sochol, Ryan D.
Brown, Jeremy D.
Krieger, Axel
contents In endovascular surgery, endovascular interventionists push a thin tube called a catheter, guided by a thin wire to a treatment site inside the patient's blood vessels to treat various conditions such as blood clots, aneurysms, and malformations. Guidewires with robotic tips can enhance maneuverability, but they present challenges in modeling and control. Automation of soft robotic guidewire navigation has the potential to overcome these challenges, increasing the precision and safety of endovascular navigation. In other surgical domains, end-to-end imitation learning has shown promising results. Thus, we develop a transformer-based imitation learning framework with goal conditioning, relative action outputs, and automatic contrast dye injections to enable generalizable soft robotic guidewire navigation in an aneurysm targeting task. We train the model on 36 different modular bifurcated geometries, generating 647 total demonstrations under simulated fluoroscopy, and evaluate it on three previously unseen vascular geometries. The model can autonomously drive the tip of the robot to the aneurysm location with a success rate of 83% on the unseen geometries, outperforming several baselines. In addition, we present ablation and baseline studies to evaluate the effectiveness of each design and data collection choice. Project website: https://softrobotnavigation.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2510_09497
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Autonomous Soft Robotic Guidewire Navigation via Imitation Learning
Barnes, Noah
Kim, Ji Woong
Di, Lingyun
Qu, Hannah
Bhattacharjee, Anuruddha
Janowski, Miroslaw
Gandhi, Dheeraj
Felix, Bailey
Jiang, Shaopeng
Young, Olivia
Fuge, Mark
Sochol, Ryan D.
Brown, Jeremy D.
Krieger, Axel
Robotics
Artificial Intelligence
In endovascular surgery, endovascular interventionists push a thin tube called a catheter, guided by a thin wire to a treatment site inside the patient's blood vessels to treat various conditions such as blood clots, aneurysms, and malformations. Guidewires with robotic tips can enhance maneuverability, but they present challenges in modeling and control. Automation of soft robotic guidewire navigation has the potential to overcome these challenges, increasing the precision and safety of endovascular navigation. In other surgical domains, end-to-end imitation learning has shown promising results. Thus, we develop a transformer-based imitation learning framework with goal conditioning, relative action outputs, and automatic contrast dye injections to enable generalizable soft robotic guidewire navigation in an aneurysm targeting task. We train the model on 36 different modular bifurcated geometries, generating 647 total demonstrations under simulated fluoroscopy, and evaluate it on three previously unseen vascular geometries. The model can autonomously drive the tip of the robot to the aneurysm location with a success rate of 83% on the unseen geometries, outperforming several baselines. In addition, we present ablation and baseline studies to evaluate the effectiveness of each design and data collection choice. Project website: https://softrobotnavigation.github.io/
title Autonomous Soft Robotic Guidewire Navigation via Imitation Learning
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2510.09497