A Dynamic-Growing Fuzzy-Neuro Controller, Application to a 3PSP Parallel Robot

2026-04-16 · Source: cs.AI updates on arXiv.org · Field: Technology & Digital — Robotics & Autonomous Systems, Artificial Intelligence & Machine Learning, Engineering & Applied Sciences · Depth: Expert, quick

Summary

A Dynamic Growing Fuzzy Neural Controller (DGFNC) is proposed for the position control of a 3PSP parallel robot, combining fuzzy systems and neural networks with an adaptive strategy. This self-organizing method adds new rules conservatively, eliminating the need for a pruning mechanism. The adaptive strategy adjusts the control system to parameter variations, while a sliding mode-based nonlinear controller ensures system stability. The DGFNC aims to achieve faster response times with reduced computational load, maintaining overall stability. The 3PSP robot, known for its complex dynamics, was chosen as the application to demonstrate the utility of this approach in industrial systems. Simulations support the effectiveness of the proposed DGFNC strategy.

Key takeaway

For research scientists developing advanced robotic control systems, this DGFNC approach offers a method to achieve faster response and stability with less computation. You should consider integrating dynamic growing fuzzy-neural architectures with adaptive and sliding mode control elements to manage complex robot dynamics effectively, potentially reducing the need for extensive pruning in self-organizing systems.

Key insights

A Dynamic Growing Fuzzy Neural Controller enhances robot control through adaptive, stable, and computationally efficient rule management.

Principles

• Combine fuzzy systems and neural networks for robust decision-making.
• Adaptive strategies can compensate for parameter variation.
• Conservative rule addition can omit pruning mechanisms.

Method

The DGFNC integrates a dynamic growing mechanism for rule addition, an adaptive strategy for parameter variation, and a sliding mode-based nonlinear controller for stability, applied to 3PSP parallel robot position control.

In practice

• Apply DGFNC to complex robotic systems.
• Use sliding mode control for system stability.
• Implement adaptive strategies for parameter changes.

Topics

• Dynamic Growing Fuzzy Neural Controller
• Fuzzy Neural Networks
• 3PSP Parallel Robot
• Position Control
• Adaptive Control

Best for: Research Scientist, AI Scientist, Robotics Engineer, Machine Learning Engineer

Related on AIssential

• A Dynamic-Growing Fuzzy-Neuro Controller, Application to a 3PSP Parallel Robot — A DGFNC combines fuzzy logic, neural networks, and adaptive control for robust robot position control.
• Hybrid Neural Network and Conventional Controller Approach for Robust Control of Highly Unstable Systems: Application to Tilt-Rotor Control — Direct neural network input-output control fails for highly unstable systems; hybrid SMC with NN-enhanced dynamics is robust.
• A neural blueprint for human-like intelligence in soft robots — A neural-inspired AI control system enables soft robots to learn once and adapt instantly to diverse tasks and disturbances.
• Factored Diffusion Policies:Compositionally Generalized Robot Control with a Single Score Network — Factored Diffusion Policies use a single diffusion network with additive score decomposition for compositionally generalized robot control.
• Optimal Take-off under Fuzzy Clearances — A hybrid fuzzy-optimal control system enhances unmanned aircraft obstacle avoidance with adaptive, interpretable constraint handling.
• A Nonlinear Separation Principle: Applications to Neural Networks, Control and Learning — A nonlinear separation principle enhances stability and performance in recurrent neural networks for control and learning.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by cs.AI updates on arXiv.org.