Artificial Bee Colony Optimization Algorithm Incorporated With Fuzzy Theory for Real-Time Machine Learning Control of Articulated Robotic Manipulators

Hsu-Chih Huang,Chun-Chia Chuang

doi:10.1109/access.2020.3032715

Abstract

This paper presents a real-time machine learning control (MLC) of articulated robotic manipulators using artificial bee colony optimization (ABC) algorithm incorporated with fuzzy theory. The modified ABC with dynamic weight is used to optimize the fuzzy structure and fractional order. The fractional parameters, fuzzy membership functions and rule base are determined by means of the ABC computation. This ABC-fuzzy hybrid learning algorithm is applied to real-time MLC of robotic manipulators by including fractional order proportional-integral-derivative (FOPID) control strategy. The MLC's control gain parameters are online tuned via the ABC-fuzzy optimization. With the kinematics analysis of a six-degree-of-freedom (DOF) articulated arm via reverse coordinates approach, an ABC-fuzzy MLC is developed to achieve motion control. A real-time operating system (RTOS) on a microprocessor collaborates with the ABC-fuzzy MLC to meet critical timing constraint by considering the dynamics of actuators. Finally, the mechatronic design and experimental setup of a six-DOF articulated robotic manipulator are constructed. Experimental results and comparative works are provided to demonstrate the merit of the proposed methods. Compared with the conventional control schemes, the proposed ABC-fuzzy MLC has theoretical and practice significance in term of real-time capability, online parameter tuning, convergent behavior and hybrid MLC. The proposed MLC methodologies are applicable to designing real-time modern controllers in both industry and academia.

Highlights

Real-time systems have grown in demand in the market especially in industrial environments [1], [2]
The proposed artificial bee colony optimization (ABC)-fuzzy machine learning control (MLC) system determines the realtime optimal control commands to the plants. This intelligent MLC approach is superior to the traditional fuzzy control systems because the fuzzy structure and fractional order are initially optimized through ABC process and the control gain parameters are online tuned
In the proposed cost-effective MLC robotic system, the embedded dual-core ARM Cortex-A9 performs the inverse kinematics, motion profile and ABC-fuzzy fractional order proportional-integral-derivative (FOPID) control law in C/C++ language. The hardware components such as pulse width modulation (PWM) circuit and quadrature encoder pulse (QEP) module are implemented by Verilog hardware description language

Summary

INTRODUCTION

Real-time systems have grown in demand in the market especially in industrial environments [1], [2]. The metaheuristic ABC is utilized to optimize both fractional order parameters and fuzzy structure This ABC-fuzzy approach is employ to develop a real-time online FOPID MLC using a RTOS. Taking the advantages of ABCfuzzy MLC, online tuning and real-time control, the proposed ABC-fuzzy FOPID MLC is applied to industrial articulated robotic manipulators. Once the initial fuzzy structure and fractional order are optimized, the ABC-fuzzy computation is utilized to online tune the FOPID parameters in the real-time MLC. The proposed ABC-fuzzy MLC system determines the realtime optimal control commands to the plants This intelligent MLC approach is superior to the traditional fuzzy control systems because the fuzzy structure and fractional order are initially optimized through ABC process and the control gain parameters are online tuned. The dynamic plant model and motion planning are employed to design a ABC-fuzzy MLC controller of robot arm with real-time FPGA implementation

FORWARD KINEMATICS

EXPERIMENTAL RESULTS OF TRAJECTORY TRACKING

CONCLUSION