Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

Frontiers of Information Technology & Electronic Engineering >> 2019, Volume 20, Issue 2 doi: 10.1631/FITEE.1700206

Adaptive network fuzzy inference system based navigation controller for mobile robot

1. Department of Electronics and Information Engineering, Chonbuk National University, Jeonju 54896, Republic of Korea
2. Advanced Electronics and Information Research Center, Chonbuk National University, Jeonju 54896, Republic of Korea

Available online: 2019-04-04

Next Previous

Abstract

Autonomous navigation of a mobile robot in an unknown environment with highly cluttered obstacles is a fundamental issue in mobile robotics research. We propose an adaptive network fuzzy inference system (ANFIS) based navigation controller for a differential drive mobile robot in an unknown environment with cluttered obstacles. Ultrasonic sensors are used to capture the environmental information around the mobile robot. A training data set required to train the ANFIS controller has been obtained by designing a fuzzy logic based navigation controller. Additive white Gaussian noise has been added to the sensor readings and fed to the trained ANFIS controller during mobile robot navigation, to account for the effect of environmental noise on sensor readings. The robustness of the proposed navigation controller has been evaluated by navigating the mobile robot in three different environments. The performance of the proposed controller has been verified by comparing the travelled path length/efficiency and bending energy obtained by the proposed method with reference mobile robot navigation controllers, such as neural network, fuzzy logic, and ANFIS. Simulation results presented in this paper show that the proposed controller has better performance compared with reference controllers and can successfully navigate in different environments without any collision with obstacles.

Related Research