A VR Training System for Robot-Assisted Vascular Intervention with Dual-Mode Control and Model-Based Interaction Response

Yining Shang; Shuxiang Guo; Sheng Cao; Pengcheng Li; Bin Wang; Mingchao Ding

cs.ROOct 14, 2026

A VR Training System for Robot-Assisted Vascular Intervention with Dual-Mode Control and Model-Based Interaction Response

Authors: Yining Shang, Shuxiang Guo, Sheng Cao, Pengcheng Li, Bin Wang, Mingchao Ding

Organizations: Key Laboratory of Convergence Biomedical Engineering System and Healthcare Technology, Ministry of Industry and Information Technology, Beijing Institute of Technology, Beijing 100081, China. · Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, Guangdong 518055, China. · Department of Peripheral Vascular Intervention, Aerospace Center Hospital, School of Life Science, Beijing Institute of Technology, Beijing 100081, China.

Abstract

Virtual reality training for robot-assisted vascular intervention requires accurate robotic control and effective feedback on guidewire--vessel interactions. This paper presents a VR training system combining asynchronous dual-mode command mapping with sensorless interaction estimation. The system supports velocity-controlled navigation and position-driven incremental manipulation. Guidewire deformation and a Hunt--Crossley-type contact response are combined and temporally filtered to estimate interaction intensity, while trajectory-based visualization supports post-procedure review. Tests confirmed distinct command-dispatch patterns across three velocity gears and the position mode. During hybrid-scene navigation, the estimated response remained low during straight insertion and increased as the guidewire bent within the vascular model. Trajectory analysis yielded a model-derived cumulative trauma work (CTW) value of 15.166 in normalized units and localized regions of elevated interaction. In a preliminary study with 15 novices, physical-phantom task success increased from 53.3% to 93.3% after VR training, while mean completion time decreased from 132.4 s to 96.7 s. These results demonstrate the system's dual-mode operation, deformation-sensitive feedback, and potential to improve subsequent physical-phantom task performance.

Figures & tables

Fig. 1: VR training architecture. The physical leader console drives virtual catheter and guidewire motion in SOFA. The console also supports a physical follower robot, which is outside the illustrated training loop.

Fig. 2: Control and interaction-estimation data flow. Asynchronous commands drive SOFA instruments; curvature and proximity cues are fused and filtered for numerical and color-coded feedback. Estimates and tip positions are recorded for post-procedure analysis.

Panel of Figure 3 — Fig. 3: Experimental components. (a) The joystick serving as the leader-side control device was connected to a computer running the SOFA-based vascular intervention training environment. (b) The corresponding transparent physical vascular phantom was used with the physical follower robot for physical–virtual comparison and pre–post training assessment.

Panel of Figure 4 — Fig. 4: Qualitative comparison of guidewire configurations in the SOFA-based VR environment and the geometry-matched physical vascular phantom. The images show guidewire paths through corresponding curved vessel segments.

Fig. 5: Command dispatch for equal-distance guidewire movements using Gears 1, 3, and 5 and Position Mode.

Navigation stage	Expected level	Stage-averaged curvature-derived response (a.u.)
Straight tube (nonvascular segment)	Low	$0.0\pm 0.0$
Curved vessel (entry segment)	Medium	$9.1\pm 1.5$
Curved vessel (deeper segment)	High	$11.9\pm 1.4$

TABLE I: Time-averaged curvature-derived interaction responses for three navigation stages. Values are reported as mean

\pm

sample SD across 20 repeated trials.

Panel of Figure 7 — Fig. 6: Sequential snapshots of guidewire navigation and the curvature-derived interaction response in the hybrid simulation scene. Panels (a)–(d) correspond to the straight tube (nonvascular segment), panels (e)–(f) correspond to the curved-vessel entry segment, and panels (g)–(i) correspond to the deeper curved-vessel segment. The three stages form consecutive intervals of the same navigation trajectory and correspond to the stages evaluated in Table I .

Fig. 7: Post-procedure spatial distribution of estimated interaction intensity, with CTW summarizing displacement-weighted interaction burden.

Metric	Pre-training	Post-training	Change	$p$ -value
Task success, $n$ (%)	8 (53.3%)	14 (93.3%)	+40.0 pp	0.031
Completion time (s)	132.4 $\pm$ 31.8	96.7 $\pm$ 24.1	$-27.0\%$	$<0.001$
Incorrect entries, $n$	2 [1, 3]	1 [0, 1]	$-50.0\%$	0.008
Excessive wall contacts, $n$	5 [4, 7]	3 [2, 4]	$-40.0\%$	0.004

TABLE II: Physical-phantom task performance before and after VR training (

n=15

). Completion time is presented as mean

\pm

SD; count outcomes are presented as median [interquartile range].

Virtual Reality

Virtual reality studies immersive, interactive environments and the technologies and human experiences that make them useful.

See all 40 papers

A Master-to-Simulation Interface with Demonstration-Trajectory Guidance for Vascular Intervention
Oct 14, 2026Mingyu Zou, Shuxiang Guo, Sheng Cao +4Robotic Endovascular Intervention Robotic Manipulation
Beijing Institute of Technology, Beijing 100081, China · Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, Guangdong 518055, China · School of Life Science and the Key Laboratory of Convergence Medical Engineering System and Healthcare Technology, Ministry of Industry and Information Technology, Beijing Institute of Technology, Beijing 100081, China +2
Manual, Joystick, or Haptic Control? An In Vitro Comparison of Navigation Strategies for Robotic Interventional Neuroradiology Procedures
Jul 8, 2026Benjamin Jackson, Nikola Fischer, Harry Robershaw +16Robot Teleoperation Human-in-the-Loop Evaluation
School of Biomedical Engineering & Imaging Sciences, King’s College London, UK
A Compact Top-Loading Robot for Endovascular Interventions: Design, Control and Evaluation
Jul 13, 2026Jonas Fischer, Lennart Karstensen, Franziska Mathis-UllrichRobotic Endovascular Intervention Robotic Manipulation
Laboratory for Surgical Planning and Robot Cognition (SPARC), Friedrich-Alexander-University Erlangen-Nürnberg, Nürnberger Straße 74, Erlangen, 91052, Bavaria, Germany.

Oct 14, 2026J/K move · Enter open · S save

A Master-to-Simulation Interface with Demonstration-Trajectory Guidance for Vascular Intervention

Mingyu Zou, Shuxiang Guo, Sheng Cao, Pengcheng Li+3

Beijing Institute of Technology, Beijing 100081, China · Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, Guangdong 518055, China · School of Life Science and the Key Laboratory of Convergence Medical Engineering System and Healthcare Technology, Ministry of Industry and Information Technology, Beijing Institute of Technology, Beijing 100081, China+2

Robotic Endovascular Intervention Robotic Manipulation Robot Teleoperation Robotics Simulation

Open paper AskPDF arXiv

Robotic vascular intervention can reduce radiation exposure to physicians and improve manipulation stability, but effective guidance remains challenging because conventional fluoroscopic images provide limited spatial information. This paper developed a vascular intervention interactive system that connects a real robotic master controller with the SOFA(Simulation Open Framework Architecture) physical simulation platform and reused successful operation trajectories as visual guidance in physical phantom experiments. Experiments were conducted to validate the master-to-SOFA control loop and to compare three guidance conditions: no guidance, centerline guidance, and successful-trajectory guidance. The control validation results showed reliable command delivery under velocity-mode operation. In the physical phantom experiment, centerline guidance showed no obvious improvement over no guidance. In contrast, successful trajectory guidance provided a clear performance benefit. Compared with the no-guidance condition, it reduced task completion time, collision number, rollback number, and rotation number by approximately 66.8%, 34.3%, 55.6%, and 66.7%, respectively. These results indicate that successful trajectories obtained under instrument-vessel interaction can provide practical guidance cues, offering a simple and effective visual assistance strategy for robotic vascular intervention experiments.

Abstract

Virtual Reality

Explore similar work

A Master-to-Simulation Interface with Demonstration-Trajectory Guidance for Vascular Intervention

Manual, Joystick, or Haptic Control? An In Vitro Comparison of Navigation Strategies for Robotic Interventional Neuroradiology Procedures

A Compact Top-Loading Robot for Endovascular Interventions: Design, Control and Evaluation