Few-Shot Physics-Informed Neural Network for Shape Reconstruction of Concentric-Tube Robots
For robotics researchers working on concentric-tube robots, this work provides a data-efficient method that combines physics priors with few-shot learning for accurate shape estimation, enabling real-time control.
The paper presents a physics-informed neural network (PINN) for shape reconstruction of concentric-tube robots, achieving a mean shape error below 1% of robot length while using minimal training data and outperforming a purely physics-based baseline.
Modeling concentric tube robots (CTRs) involves complex nonlinear continuum mechanics, and despite recent progress, physics-based models often lack an accurate representation of the experimental setups. To overcome these limitations, deep neural network-based models have been explored as alternatives with superior accuracy; however, they often overlook known mechanics, require large training datasets, and typically discard shape estimation of the robot. We present a physics-informed neural network (PINN) for kinematic modeling of a 6-DoF CTR with three pre-curved tubes that embeds the Cosserat rod differential equations and learns from few-shot observational data, balancing physics priors with data-driven fitting. PINN enables full-state estimation of shape, twist angle, torsional strain, bending moment, and orientation. Benchmark tests show a mean shape error below 1% of the robot length and accurately recovered other kinematic states, outperforming a purely physics-based Cosserat rod model baseline while using a minimal training set. The resulting model is also computationally efficient and robust, making it well-suited for real-time control applications.