Catheter Robot Atlas

Library

Simulation to robot

26 studies in which a controller or model trained in simulation ran on a physical catheter or guidewire robot, with success in simulation and on the robot as each paper reports it. 19 are linked to a robot record.

YearStudyRobotSimulatorTrained Real setupSuccess in simSuccess on robotCode
2026alabay2026_vista
arXiv:2608.30220
magnetically actuated untethered microrobot (not a catheter robot)3D digital twin of vessels (not a physics policy simulator)none (rule-based milestones)vascular phantoms with flow + live rat IVC n/anavigation time -62%, corrective commands -98%, radiation -57% vs human-in-the-loopN.R.
2026Learning Expert Strategy for Autonomous Robotic Endovascular Intervention via Decoupled Procedural Execution
arXiv:2607.00066 (accepted IROS 2026)
ALLVASSim4EndoR (SOFA) as digital twin of the phantompolicy (SAC high-level) + online nonlinear MPC filter (not learned)heated silicone phantom with circulation, coronary and transfemoral routes, 20 trials 98%, 96%, 98% (50 episodes per target); SAC alone 92/94/90%18/20 (90.0%), 4.2 +/- 0.8 min per trialno
2026EVEGARS: End-to-End Vision-Based Endovascular Guidewire Autonomous Reinforcement Learning in Large-Scale Simulations from Clinical Dataset
PRCV (LNCS)
guidewire robot under X-ray with "ex-vivo model" and remote station…EVEGARS: pymunk 2D rigid-body, 120 ARCADE angiogram maskspolicy (PPO, ResNet-50 + ViT encoder) from images4 delivery tasks in an undescribed "ex-vivo model", trials per task N.R. 91% (denominator N.R.)85%, 80%, 80%, 70% (human 100%, 95%, 100%, 95%; behaviour cloning 0%)no
2026Progressive Experience Fusion for Multi-Task World Model Control in Endovascular Navigation
arXiv:2608.18647
KCL lead-screwstEVE / SOFA; 30 training + 10 held-out CTAspolicy (multi-task, progressive experience fusion), fine-tuned 40k steps in a simulation…unseen printed phantom, 5 runs per sub-task 90% on 10 unseen vasculatures60% without, 67% with fine-tuning (p = 0.623)no
2026Toward Safe Autonomous Robotic Endovascular Interventions using World Models
arXiv:2604.20151 (submitted IROS 2026)
KCL lead-screwstEVE / SOFA v23.12; 0.0441 in catheter + 0.035 in guidewire; 15 CTAs (5 held out)policy (TD-MPC2 world model vs SAC)printed phantom of one training vessel under mobile C-arm; 5 runs per task, n = 25 hold-out 58% (n = 250) TD-MPC2 vs 36% SAC68% vs 60% (p = 0.567); left common carotid 0/5 bothno
2026Toward AI Autonomous Navigation for Mechanical Thrombectomy Using Hierarchical Modular Multi-Agent Reinforcement Learning (HM-MARL)
IEEE RA-L 11(4) (arXiv:2602.18663)
KCL lead-screwstEVE / SOFA; Navien 0.058 in catheter + 0.035 in guidewire (E 47 and 43 MPa); 10 patient…policy (hierarchical modular multi-agent SAC, HM-MARL)3D-printed transparent phantom (Clear V4) in glycerine; 10 bench episodes per task A1,2 right 100%; A2,3 right 100%; A1,2 left 100%; A2,3 left 94% (50 episodes)100%, 70% (80% with 10-anatomy agent), 0%, 0%no
2026Vision-Language Procedural Reasoning for Context-Aware Reward Modeling of Robotic Endovascular Guidewire Navigation
arXiv:2606.30698 (accepted IROS 2026)
ALLVASSOFA digital twin of each phantompolicy (SAC) trained with reward weights set by a fine-tuned Qwen2.5-VL-3B stage…three anthropomorphic phantoms (coronary, carotid, renal) with pump flow, 30 trials per… N.R.100%, 97%, 100% with VLM-shaped reward; SAC alone 70%, 73%, 73%; expert manual 93%, 97%,…no
2026From Patient-Specific Digital Twin to Real-World Phantom: Autonomous Right Heart Catheterization
IEEE Robotics & Automation Magazine (Mar 2026)
custom 2-DoF Swan-Ganz catheter robot: active-passive roller set with…SOFA + BeamAdapter patient-specific digital twin (phantom E 10 kPa, nu 0.49, density 1.2…policy by supervised learning (CNN decision model, behaviour cloning of user key-press…three water-filled patient-specific right-heart phantoms, static and pulsatile heartbeat,… N.R. (twin used to generate data, no sim success rate)>= 96% static, >= 94% dynamic; trajectory consistency >= 34.63% better than expertno
2025Learning-based autonomous navigation, benchmark environments and simulation framework for endovascular interventions
Comput. Biol. Med. 196 (arXiv:2410.01956)
Wire manipulatorstEVE / SOFA BeamAdapter; stEVE_bench BasicWireNav, ArchVariety, DualDeviceNavpolicy (SAC + LSTM)3D-printed rigid aortic arch phantoms; camera bench 100+100 trials, fluoroscopy 10 trials BasicWireNav 98/100; ArchVariety 90/100; DualDeviceNav 40/100 (sim only)BasicWireNav camera 97/100 (9/10 on the first 10), fluoroscopy 10/10; ArchVariety camera…yes: github.com/lkarstensen/stEVE,…
2025RL-MG: Reinforcement Learning Framework for Magnetic Guidewire Path Following
RCAR 2025
Magnet gantrySOFA + BeamAdapter (Kirchhoff rod), dipole field from COMSOL; SolidWorks vessel modelspolicy (DDPG, 400 episodes)femoral-artery model, 4 paths x 3 trials N.R. (error 2.5/3.1/2.2/2.4 mm, time 7.0/13.0/12.0/9.0 s)N.R. (error 3.6/3.8/3.1/2.8 mm, time 31.0/64.0/45.0/67.0 s)
2025FreezeSeg2RL: Frozen Segmentation Pretraining for Reinforcement Learning On Vascular Interventional Robot Autonomous Delivering
PRICAI 2025 (Springer LNCS, print 2026)
XMU wire robotpymunk 2D X-ray simulation platform (same group as EVEGARS); ARCADE tasks + 4…perception (frozen DeepLabV3+ segmentation encoder pretrained on 5,138 simulated images)…4 delivery tasks, 120 s limit, trials per task N.R. 56.1% ARCADE tasks, 44.8% in-vitro-model tasks (simulated, Table 4)85%, 80%, 80%, 70% (human 100/95/100/95; BC 0%); without data augmentation 25%, 15%, 15%,…no
2025Transferring Virtual Surgical Skills to Reality: AI Agents Mastering Surgical Decision-Making in Vascular Interventional Robotics
IEEE/ASME T-MECH 30(2)
XMU wire robotPymunk 2Dpolicy (multiprocess PPO, three training stages)transparent vessel model, 4 targets, 40 runs per target 99.30, 99.26 and 98.34 % across three training stages (not the hardware targets)82.5 / 87.5 / 82.5 / 72.5 % (surgeon 100 %, replayed surgeon commands 0 %)
2025A simulation environment for robot-assisted endovascular interventions
IJCARS
CathBotSOFA + BeamAdapter; Signorini contact with Coulomb friction 0.62; vessel FEnonesilicone aorta phantom with fiducials, bead registration n/an/ano
2025Sim2Real Learning With Domain Randomization for Autonomous Guidewire Navigation in Robotic-Assisted Endovascular Procedures
IEEE T-ASE 22
United ImagingSOFA 23.06 + BeamAdapter; one 0.9 mm guidewire (density 1.55 g/cm3)policy (PPO + GAE + domain randomisation; SAC, DDPG baselines)simplified vascular phantom with physical twin; 4-5 trials per method; 2 human operators… PPO 7/10 and 8/10; PPO+DR 8/10 and 9/10; PPO+GAE+DR 9/10 and 9/10 (targets A, B)PPO 60% (5 trials); PPO+GAE+DR 100% (5); SAC and DDPG 75% (4); human 100% (3) in 35-39 sno (supplement at DOI)
2025Sim4EndoR: A Reinforcement Learning Centered Simulation Platform for Task Automation of Endovascular Robotics
ICRA
United ImagingSim4EndoR: SOFA v23.06 + BeamAdapter + Blender; phantom CT-scanned for a matching sim…policy (DDPG, PPO, SAC; path-length reward)coronary phantom, 2 end points, 5 trials each Task A 5/5, Task B 4/5 (DDPG)Task A 5/5, Task B 3/5no
2025A Robust Deep Reinforcement Learning Framework for Image-Based Autonomous Guidewire Navigation
ICRA
KAIST wire benchSOFA (new random left-coronary tree each training episode)policy (PPO with local-map sub-goals along an A* path)planar phantom, one bench, four paths, 40 runs per test 86.9% (67 episodes x 3) vs 53.7% without vessel randomisation93.3%, 89.2%, 91.7% (three tests); Cho 2022 controller 83.3%, rule-based 19.2% in test Ino (video on YouTube)
2024CathSim: An Open-Source Simulator for Endovascular Intervention
IEEE T-MRB 6(3)
CathBotCathSim (MuJoCo; rigid-link catheter chain, rigid wall)none for this comparison (RL baselines elsewhere in paper)silicone Type-I arch phantom, CathBot force experiment n/an/ayes (github.com/airvlab/cathsim)
2024FBG-driven simulation for virtual augmentation of fluoroscopic images during endovascular interventions
Healthc. Technol. Lett. 11(6)
N.R. (user study with FBG-guided catheter on rigid 3D-printed aorta)SOFA (Timoshenko beam, catheter + wire overlap)none (FBG shape pulls simulation, gain 0.8)rigid aorta phantom, 8 locations n/an/ano
2024wen2024_guidewire_seg
arXiv:2410.07460
none (perception only)synthetic fluoroscopy from simulationperception (SAM adapted, style transfer + self-training)public cardiac dataset + in-house neurovascular dataset n/aN.R. hereannounced
2022Sim-to-Real Transfer of Image-Based Autonomous Guidewire Navigation Trained by Deep Deterministic Policy Gradient with Behavior Cloning for Fast Learning
IROS
KAIST wire benchSOFA (virtual planar vessel map)policy (DDPG after behaviour cloning from a rule-based expert)planar phantom of a different shape, camera 30 Hz, 4 targets x 10 episodes 100/100, 41.08 s (expert 66.17 s)40/40, 35.06 s (expert 63.2 s)no (video only)
2022A Simulation Framework for Magnetic Continuum Robots
IEEE Robot. Autom. Lett. 7(3)
magnetic continuum robot, 1.5 mm (4.5 Fr) OD, three NdFeB ring…SOFA + BeamAdapter (1D Kirchhoff-rod FEM, Lagrange-multiplier contact, Coulomb friction…Noneplanar, 4 mm high, rigid POM and PMMA models (calibration, vasculature-like, free-form);… n/amean tip position error 5.1 to 6.8 mm and orientation error 3.8 to 7.2 deg over the three…yes…
2022Learning-based autonomous vascular guidewire navigation without human demonstration in the venous system of a porcine liver
IJCARS 17(11)
Wire manipulatorSOFA + BeamAdapter (rigid wall, empty lumen; 0.035 in Terumo Radifocus angled stiff…policy (deep RL, controller with recurrent layers; algorithm not re-checked); perception…ex vivo porcine liver (one organ; CT mesh from the same liver) with pump flow; 10 targets… 150/150 (100%) at training end9/30 (30%): wrong branch 10, entanglement 11no
2022Robotic Actuation and Control of a Catheter for Structural Intervention Cardiology
IROS 2022
MitraClip stabiliserUnity scene of the CT-reconstructed heart; Cosserat-rod kinematic model of the catheterpolicy (BC + GAIL path planner)patient-specific silicone phantom N.R.N.R. (position error 1.12 / 1.09 / 1.66 mm X/Y/Z, max 2.64 mm)
2020Autonomous guidewire navigation in a two dimensional vascular phantom
Curr. Dir. Biomed. Eng. 6(1), 20200007
Wire manipulatorSOFA + BeamAdapter; phantom walls rigid, lumen empty; wall friction and guidewire…policy (DDPG + HER)rigid 2D phantom, stereolithography print, filled with glycerine-water; a loop that… maximum 96% after 52,500 training episodes (100 test episodes every 500 training…'the same results as navigating in the simulation environment' (no number, episodes…no
2019Deep Reinforcement Learning for the Navigation of Neurovascular Catheters
Curr. Dir. Biomed. Eng. 5(1)
Wire manipulatorSOFA + BeamAdapter; rigid vessel walls, wall-guidewire friction 0.1, empty lumen (no…policy (DDPG, with HER and human demonstrations as options, OpenAI Baselines; DQN with…idealised PMMA phantom, constant 10 mm vessel diameter, a bifurcation followed by a bi-… DDPG + HER 89.6% (sparse reward), DQN + Rainbow 86.5% (dense reward), average success…7/10 (the trained DDPG model on the test bench) (Sec. 3)no
2019Automatic control of cardiac ablation catheter with deep reinforcement learning method
J. Mech. Sci. Technol. 33(11)
tendon-driven steerable EP-catheter robot, 3 motors (translation,…Unity (catheter + heart collision model; rendered to angiography-like images)policy (dueling DQN)printed rigid right-atrium phantom, 100 episodes per model 98%, 96%, 97%, 96% (four models)73% (no randomisation); 78%, 75% (one noise type); 87% (both)no

Data: api/sim2real.json.