Self-organization stochastic fuzzy control based on OCPFA and applied on self-balanced robot

Abstract

This paper constructs a stochastic fuzzy controller to realize self-balancing control of two-wheeled robot. The rule of fuzzy controller is stochastic, which is automatically generated by an OCPFA learning system and optimized online. The OCPFA learning system is in fact a Probabilistic Finite Automata (PFA) which based on Skinner Operant Conditioning (Skinner OC), and it is composed by a bionic reorientation mechanism and an OC learning mechanism. The reorientation mechanism take for orientation function of robot posture balance as the goal-orientation, and response to the output control variable of fuzzy stochastic controller; Learning mechanism updated probability contribution of output control variable by using the response information form the environment and then choose the optimal control variable according to the new probability contribution. The OCPFA learning system gradually adapts to the environment changes by interacting with the dynamic environment based on which the learning system realize the self-organization of stochastic fuzzy control rules and show character of autonomous learning. In the same time the theoretical prove that the process of autonomous learning is convergent in sense of probability. The simulation indicate the stochastic fuzzy controller can successfully applied in twowheeled robot self-balancing without requiring the model of the robot and the robot can show control behavior of autonomous learning which similar to animal's OC learning behavior.

Indirect Adaptive Fuzzy Controller for LEGO Mindstorms NXT Two-Wheeled Robot

“…Two-wheeled balancing robot system is usually used to evaluate the system performances for a specific controller [1,3]. For example, applying adaptive fuzzy control to two-wheeled robot for solving the upstanding-balancing problem via computer simulation [2,8].…”

“…Many designers integrated neural network or fuzzy control in designing such systems to balance two wheeled robot [4,7,9,10,12,13] via computer simulations. For example, a fuzzy controller was combined operant conditioning probabilistic finite automata (OCPFA) learning system and applied on self-balanced robot [1]. Actually, the system performances of fuzzy controller deeply depend on the designer skilled experiences.…”

Adaptive Fuzzy Cerebellar Model Articulation Controller for Two-Wheeled Robot

“…Constructing a two-wheeled balancing robot is one goal of programmers and control designers. In recent year, there were many reported papers using different control methods to design the twowheeled robot [3,11,14]. For example, fuzzy control design schemes were used in two-wheeled robot to solve the upstanding-balancing problem [4,17,18].…”

“…A number of controller designers proposed the hybrid control system, neural network or fuzzy control to solve the balancing problems of the two wheeled robots [12,16,20,22,24]. For example, a fuzzy controller was combined operant conditioning probabilistic finite automata (OCPFA) learning system and applied it to a self-balanced robot [3]. Essentially, the controller design of the fist sort depends on expert experiences and learning algorithms.…”