Modeling and Control of a Pneumatic Soft Robotic Catheter Using Neural Koopman Operators

2026-03-04

AI Summary

This work addresses the challenge of accurately modeling and controlling soft robotic catheters, whose highly nonlinear dynamics hinder precise control, and overcomes the limitations of conventional Koopman-based approaches that rely on handcrafted basis functions. The authors propose an end-to-end neural Koopman operator framework that jointly learns the lifting map and the Koopman operator, enabling automatic feature extraction and data-driven modeling of soft catheter systems for the first time. This approach facilitates high-precision open-loop control without requiring continuous visual feedback, substantially reducing X-ray exposure during cardiac ablation procedures. In interactive position control and simulated ablation tasks, the method achieves a mean positional error of 2.1 ± 0.4 mm and an angular error of 4.9 ± 0.6°, outperforming existing models and Koopman variants.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Catheter-based interventions are widely used for the diagnosis and treatment of cardiac diseases. Recently, robotic catheters have attracted attention for their ability to improve precision and stability over conventional manual approaches. However, accurate modeling and control of soft robotic catheters remain challenging due to their complex, nonlinear behavior. The Koopman operator enables lifting the original system data into a linear "lifted space", offering a data-driven framework for predictive control; however, manually chosen basis functions in the lifted space often oversimplify system behaviors and degrade control performance. To address this, we propose a neural network-enhanced Koopman operator framework that jointly learns the lifted space representation and Koopman operator in an end-to-end manner. Moreover, motivated by the need to minimize radiation exposure during X-ray fluoroscopy in cardiac ablation, we investigate open-loop control strategies using neural Koopman operators to reliably reach target poses without continuous imaging feedback. The proposed method is validated in two experimental scenarios: interactive position control and a simulated cardiac ablation task using an atrium-like cavity. Our approach achieves average errors of 2.1 +- 0.4 mm in position and 4.9 +- 0.6 degrees in orientation, outperforming not only model-based baselines but also other Koopman variants in targeting accuracy and efficiency. These results highlight the potential of the proposed framework for advancing soft robotic catheter systems and improving catheter-based interventions.

Problem

• soft robotic catheter
• nonlinear dynamics
• modeling and control
• radiation exposure
• Koopman operator

Innovation

• Neural Koopman Operator
• Soft Robotic Catheter
• Data-Driven Control
• Lifted Space Learning
• Open-Loop Control