Output Feedback Control for PAM-Actuated Parallel Robots With Interval Type-2 Fuzzy Neural Networks
- 20 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 56 (1) , 606-616
Abstract
By mimicking the movement of biological muscles, pneumatic artificial muscles (PAMs) are developed as a novel type of bionic actuator known for their compliance and high safety; however, the inherent characteristics of PAMs (e.g., hysteresis and creep) increase the difficulty in modeling and control. Moreover, unmodeled dynamics in PAM-actuated parallel robots are unavoidable, which further complicates the efficient tracking task of PAM-actuated parallel robots. Therefore, we propose an output feedback controller with interval type-2 fuzzy neural networks (IT2FNNs) for PAM-actuated parallel robots to obtain satisfactory tracking results. Specifically, compared with most existing methods using the interval type-1 fuzzy neural network (NN), the IT2FNN used is more beneficial for dealing with unmodeled dynamics and system uncertainties on PAM-actuated parallel robots. Meanwhile, considering that most practical systems are often only equipped with displacement/angle sensors and lack velocity sensors, an observer is designed to estimate unmeasurable velocity signals. Next, based on Lyapunov techniques, the convergence of tracking errors is proven through theoretical analysis. To our knowledge, this article is the first to apply IT2FNNs with observation information to PAM-actuated parallel robots with unknown dynamics and unmeasurable velocity signals, and provides rigorous stability analysis. Further, several experiments are implemented, and the corresponding results illustrate the effectiveness and robustness of the proposed controller.Keywords
Funding Information
- National Natural Science Foundation of China (62533014)
- National Natural Science Foundation of China (623B2053)
- National Natural Science Foundation of China (62373198)
- Shenzhen Science and Technology Program (RCJC20231211090028054)
- Natural Science Foundation of Tianjin Municipality (24JCZXJC00220)
- Beijing-Tianjin-Hebei Basic Research Cooperation Special Project (F2024205028)
- Fundamental Research Funds for the Central Universities (078-63253237)
This publication has 32 references indexed in Scilit:
- Backstepping integral sliding mode control for pneumatic manipulators via adaptive extended state observersISA Transactions, 2023
- Computed torque control and force analysis for mechanical leg with variable rotation axis powered by servo pneumatic muscleISA Transactions, 2023
- A Lower Limb Rehabilitation Assistance Training Robot System Driven by an Innovative Pneumatic Artificial Muscle SystemSoft Robotics, 2023
- Adaptive proxy-based sliding mode control for a class of second-order nonlinear systems and its application to pneumatic muscle actuatorsISA Transactions, 2022
- An Adaptive Finite-Time Force-Sensorless Tracking Control Scheme for Pneumatic Muscle Actuators by an Optimal Force EstimationIEEE Robotics and Automation Letters, 2021
- Design and Hierarchical Force-Position Control of Redundant Pneumatic Muscles-Cable-Driven Ankle Rehabilitation RobotIEEE Robotics and Automation Letters, 2021
- Adaptive control for a motion mechanism with pneumatic artificial muscles subject to dead-zonesMechanical Systems and Signal Processing, 2021
- A comprehensive dynamic model for pneumatic artificial muscles considering different input frequencies and mechanical loadsMechanical Systems and Signal Processing, 2021
- Design and control of soft rehabilitation robots actuated by pneumatic muscles: State of the artFuture Generation Computer Systems, 2020
- Parameter optimization of interval Type-2 fuzzy neural networks based on PSO and BBBC methodsIEEE/CAA Journal of Automatica Sinica, 2019