A Learning-based Model Reference Adaptive Controller Implemented on a Prosthetic Hand Wrist

2025-10-21

AI Summary

To address poor adaptability, high computational cost, and low tracking accuracy in tendon-driven soft continuum prosthetic wrist control, this paper proposes a real-time controller integrating Model Reference Adaptive Control (MRAC) with a lightweight neural network. The method innovatively combines Timoshenko beam dynamics modeling with online neural-network-based tendon force estimation, enabling dynamic tendon force identification and error-feedback compensation under low computational overhead. Simulation results yield an RMSE of 6.14×10⁻⁴ m; experiments achieve an average RMSE of 5.66×10⁻³ m, a steady-state error of 8.05×10⁻³ m, and a settling time of 1.58 s. The approach significantly enhances motion naturalness, response speed, and environmental adaptability—making it particularly suitable for resource-constrained wearable assistive devices.

Technology Category

• Intelligent Robots: State Estimation
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

The functionality and natural motion of prosthetic hands remain limited by the challenges in controlling compliant wrist mechanisms. Current control strategies often lack adaptability and incur high computational costs, which impedes real-time deployment in assistive robotics. To address this gap, this study presents a computationally efficient Neural Network (NN)-based Model Reference Adaptive Controller (MRAC) for a tendon-driven soft continuum wrist integrated with a prosthetic hand. The dynamic modeling of the wrist is formulated using Timoshenko beam theory, capturing both shear and bending deformations. The proposed NN-MRAC estimates the required tendon forces from deflection errors and minimizes deviation from a reference model through online adaptation. Simulation results demonstrate improved precision with a root mean square error (RMSE) of $6.14 imes 10^{-4}$ m and a settling time of $3.2$s. Experimental validations confirm real-time applicability, with an average RMSE of $5.66 imes 10^{-3}$ m, steady-state error of $8.05 imes 10^{-3}$ m, and settling time of $1.58$ s. These results highlight the potential of the controller to enhance motion accuracy and responsiveness in soft prosthetic systems, thereby advancing the integration of adaptive intelligent control in wearable assistive devices.

Problem

• Developing adaptive control for prosthetic hand wrist mechanisms
• Reducing computational costs in real-time assistive robotics
• Improving motion precision in soft continuum prosthetic systems

Innovation

• Neural Network-based Model Reference Adaptive Controller
• Dynamic modeling using Timoshenko beam theory
• Online adaptation minimizes deviation from reference model