Data-driven Kinematic Modeling in Soft Robots: System Identification and Uncertainty Quantification

2025-07-09

AI Summary

Soft robotic kinematic modeling suffers from low prediction accuracy and challenges in quantifying uncertainty due to strong nonlinearity. To address this, we propose a machine learning modeling framework based on split conformal prediction (SCP), which integrates a small amount of simulation and experimental data. We systematically evaluate the performance of linear regression, support vector machines (SVM), random forests, and gradient-boosted trees. Notably, this work presents the first distribution-free, statistically guaranteed uncertainty quantification for pose prediction in soft robots. Experimental results demonstrate that nonlinear ensemble models achieve superior generalization. The SCP-based framework yields prediction intervals with high empirical coverage and reasonable width, significantly enhancing modeling robustness and reliability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Precise kinematic modeling is critical in calibration and controller design for soft robots, yet remains a challenging issue due to their highly nonlinear and complex behaviors. To tackle the issue, numerous data-driven machine learning approaches have been proposed for modeling nonlinear dynamics. However, these models suffer from prediction uncertainty that can negatively affect modeling accuracy, and uncertainty quantification for kinematic modeling in soft robots is underexplored. In this work, using limited simulation and real-world data, we first investigate multiple linear and nonlinear machine learning models commonly used for kinematic modeling of soft robots. The results reveal that nonlinear ensemble methods exhibit the most robust generalization performance. We then develop a conformal kinematic modeling framework for soft robots by utilizing split conformal prediction to quantify predictive position uncertainty, ensuring distribution-free prediction intervals with a theoretical guarantee.

Problem

• Modeling nonlinear dynamics in soft robots accurately
• Quantifying prediction uncertainty in kinematic modeling
• Ensuring robust generalization with limited data

Innovation

• Data-driven machine learning for soft robots
• Nonlinear ensemble methods enhance generalization
• Conformal prediction quantifies position uncertainty