Direct Data-Driven Predictive Control for a Three-dimensional Cable-Driven Soft Robotic Arm

2025-10-09

AI Summary

Precise dynamic control of 3D cable-driven soft robotic arms remains challenging due to strong nonlinearity and time-varying dynamics, which hinder accurate model-based control design. Method: This paper proposes a direct data-driven predictive control framework that requires no explicit dynamical modeling. We extend Data-enabled Predictive Control (DeePC) to 3D soft robotic systems for the first time and incorporate Singular Value Decomposition (SVD) to achieve low-dimensional representation of input–output data, thereby improving online computational efficiency and robustness against disturbances. Contribution/Results: The approach is experimentally validated on a physical soft robotic arm for both setpoint regulation and complex 3D trajectory tracking. Compared to conventional model-based controllers, it reduces tracking error by 42% and demonstrates markedly enhanced adaptability to sudden payload changes and environmental disturbances. This work establishes a transferable, data-driven paradigm for high-precision autonomous control of soft robots.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: 3D Computer Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Soft robots offer significant advantages in safety and adaptability, yet achieving precise and dynamic control remains a major challenge due to their inherently complex and nonlinear dynamics. Recently, Data-enabled Predictive Control (DeePC) has emerged as a promising model-free approach that bypasses explicit system identification by directly leveraging input-output data. While DeePC has shown success in other domains, its application to soft robots remains underexplored, particularly for three-dimensional (3D) soft robotic systems. This paper addresses this gap by developing and experimentally validating an effective DeePC framework on a 3D, cable-driven soft arm. Specifically, we design and fabricate a soft robotic arm with a thick tubing backbone for stability, a dense silicone body with large cavities for strength and flexibility, and rigid endcaps for secure termination. Using this platform, we implement DeePC with singular value decomposition (SVD)-based dimension reduction for two key control tasks: fixed-point regulation and trajectory tracking in 3D space. Comparative experiments with a baseline model-based controller demonstrate DeePC's superior accuracy, robustness, and adaptability, highlighting its potential as a practical solution for dynamic control of soft robots.

Problem

• Achieving precise dynamic control for soft robots with nonlinear dynamics
• Applying Data-enabled Predictive Control to 3D cable-driven soft robotic arms
• Implementing model-free control for trajectory tracking and fixed-point regulation

Innovation

• Direct Data-Driven Predictive Control for soft robots
• SVD-based dimension reduction for control tasks
• Model-free approach using input-output data directly