Title | A Supervised-Reinforced Successive Training Framework for a Fuzzy Inference System and Its Application in Robotic Odor Source Searching |
Author | |
Corresponding Author | Fu, Chenglong |
Publication Years | 2022-05-31
|
DOI | |
Source Title | |
ISSN | 1662-5218
|
Volume | 16 |
Abstract | Fuzzy inference systems have been widely applied in robotic control. Previous studies proposed various methods to tune the fuzzy rules and the parameters of the membership functions (MFs). Training the systems with only supervised learning requires a large amount of input-output data, and the performance of the trained system is confined by that of the target system. Training the systems with only reinforcement learning (RL) does not require prior knowledge but is time-consuming, and the initialization of the system remains a problem. In this paper, a supervised-reinforced successive training framework is proposed for a multi-continuous-output fuzzy inference system (MCOFIS). The parameters of the fuzzy inference system are first tuned by a limited number of input-output data from an existing controller with supervised training and then are utilized to initialize the system in the reinforcement training stage. The proposed framework is applied in a robotic odor source searching task and the evaluation results demonstrate that the performance of the fuzzy inference system trained by the successive framework is superior to the systems trained by only supervised learning or RL. The system trained by the proposed framework can achieve around a 10% higher success rate compared to the systems trained by only supervised learning or RL. |
Keywords | |
URL | [Source Record] |
Indexed By | |
Language | English
|
SUSTech Authorship | Corresponding
|
Funding Project | National Key R&D Program of China[2018YFC2001601]
; National Natural Science Foundation of China[
|
WOS Research Area | Computer Science
; Robotics
; Neurosciences & Neurology
|
WOS Subject | Computer Science, Artificial Intelligence
; Robotics
; Neurosciences
|
WOS Accession No | WOS:000810949500001
|
Publisher | |
EI Accession Number | 20222612262742
|
EI Keywords | Electronic Nose
; Fuzzy Inference
; Fuzzy Neural Networks
; Fuzzy Systems
; Membership Functions
; Robotics
; Supervised Learning
|
ESI Classification Code | Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory:721.1
; Artificial Intelligence:723.4
; Expert Systems:723.4.1
; Robotics:731.5
; Chemistry:801
; Mathematics:921
; Electric And Electronic Instruments:942.1
; Systems Science:961
|
Data Source | Web of Science
|
Citation statistics |
Cited Times [WOS]:0
|
Document Type | Journal Article |
Identifier | http://kc.sustech.edu.cn/handle/2SGJ60CL/343058 |
Department | Southern University of Science and Technology |
Affiliation | 1.Shenzhen Key Lab Biomimet Robot & Intelligent Syst, Shenzhen, Peoples R China 2.Southern Univ Sci & Technol, Guangdong Prov Key Lab Human Augmentat & Rehabil, Shenzhen, Peoples R China |
First Author Affilication | Southern University of Science and Technology |
Corresponding Author Affilication | Southern University of Science and Technology |
Recommended Citation GB/T 7714 |
Chen, Xinxing,Leng, Yuquan,Fu, Chenglong. A Supervised-Reinforced Successive Training Framework for a Fuzzy Inference System and Its Application in Robotic Odor Source Searching[J]. Frontiers in Neurorobotics,2022,16.
|
APA |
Chen, Xinxing,Leng, Yuquan,&Fu, Chenglong.(2022).A Supervised-Reinforced Successive Training Framework for a Fuzzy Inference System and Its Application in Robotic Odor Source Searching.Frontiers in Neurorobotics,16.
|
MLA |
Chen, Xinxing,et al."A Supervised-Reinforced Successive Training Framework for a Fuzzy Inference System and Its Application in Robotic Odor Source Searching".Frontiers in Neurorobotics 16(2022).
|
Files in This Item: | There are no files associated with this item. |
|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment