Interval Type-2 Neural Fuzzy Controller-Based Navigation of Cooperative Load-Carrying Mobile Robots in Unknown Environments.

Chun-Hui Lin,Shyh-Hau Wang,Cheng-Jian Lin

doi:10.3390/s18124181

Abstract

In this paper, a navigation method is proposed for cooperative load-carrying mobile robots. The behavior mode manager is used efficaciously in the navigation control method to switch between two behavior modes, wall-following mode (WFM) and goal-oriented mode (GOM), according to various environmental conditions. Additionally, an interval type-2 neural fuzzy controller based on dynamic group artificial bee colony (DGABC) is proposed in this paper. Reinforcement learning was used to develop the WFM adaptively. First, a single robot is trained to learn the WFM. Then, this control method is implemented for cooperative load-carrying mobile robots. In WFM learning, the proposed DGABC performs better than the original artificial bee colony algorithm and other improved algorithms. Furthermore, the results of cooperative load-carrying navigation control tests demonstrate that the proposed cooperative load-carrying method and the navigation method can enable the robots to carry the task item to the goal and complete the navigation mission efficiently.

Highlights

The robotics is rapidly progressed in recent years
The number of successful runs demonstrates that the mobile robots can traverse the training environment one time successfully from the start point to the goal during the simulation
The results revealed that the trained control method was implemented for cooperative load-carrying mobile robots

Summary

Introduction

The robotics is rapidly progressed in recent years. Many researchers [1,2,3,4] have applied robots to various fields. Paul et al [1] proposed a biomimetic robotic fish for informal science learning. Christopher et al [2] presented a new robotic harvester that can autonomously harvest sweet pepper in protected cropping environments. Michail et al [3] designed an autonomous robotic vehicle for monitoring the difficult fields to access or dangerous for humans. Maurizio et al [4] developed effective emotion-based assistive behaviors for a socially assistive robot intended for natural human-robot interaction scenarios with explicit social and assistive task functionalities

Results

Discussion

Conclusion